111 results on '"Eui Jin Hwang"'
Search Results
2. Evaluation of chest X-ray with automated interpretation algorithms for mass tuberculosis screening in prisons: a cross-sectional studyResearch in context
- Author
-
Thiego Ramon Soares, Roberto Dias de Oliveira, Yiran E. Liu, Andrea da Silva Santos, Paulo Cesar Pereira dos Santos, Luma Ravena Soares Monte, Lissandra Maia de Oliveira, Chang Min Park, Eui Jin Hwang, Jason R. Andrews, and Julio Croda
- Subjects
Automated interpretation ,Diagnostics ,Prisons ,Tuberculosis ,X-ray ,Public aspects of medicine ,RA1-1270 - Abstract
Summary: Background: The World Health Organization (WHO) recommends systematic tuberculosis (TB) screening in prisons. Evidence is lacking for accurate and scalable screening approaches in this setting. We aimed to assess the accuracy of artificial intelligence-based chest x-ray interpretation algorithms for TB screening in prisons. Methods: We performed prospective TB screening in three male prisons in Brazil from October 2017 to December 2019. We administered a standardized questionnaire, performed a chest x-ray in a mobile unit, and collected sputum for confirmatory testing using Xpert MTB/RIF and culture. We evaluated x-ray images using three algorithms (CAD4TB version 6, Lunit version 3.1.0.0 and qXR version 3) and compared their accuracy. We utilized multivariable logistic regression to assess the effect of demographic and clinical characteristics on algorithm accuracy. Finally, we investigated the relationship between abnormality scores and Xpert semi-quantitative results. Findings: Among 2075 incarcerated individuals, 259 (12.5%) had confirmed TB. All three algorithms performed similarly overall with area under the receiver operating characteristic curve (AUC) of 0.88–0.91. At 90% sensitivity, only LunitTB and qXR met the WHO Target Product Profile requirements for a triage test, with specificity of 84% and 74%, respectively. All algorithms had variable performance by age, prior TB, smoking, and presence of TB symptoms. LunitTB was the most robust to this heterogeneity but nonetheless failed to meet the TPP for individuals with previous TB. Abnormality scores of all three algorithms were significantly correlated with sputum bacillary load. Interpretation: Automated x-ray interpretation algorithms can be an effective triage tool for TB screening in prisons. However, their specificity is insufficient in individuals with previous TB. Funding: This study was supported by the US National Institutes of Health (grant numbers R01 AI130058 and R01 AI149620) and the State Secretary of Health of Mato Grosso do Sul.
- Published
- 2023
- Full Text
- View/download PDF
3. Deep learning computer-aided detection system for pneumonia in febrile neutropenia patients: a diagnostic cohort study
- Author
-
Eui Jin Hwang, Jong Hyuk Lee, Jae Hyun Kim, Woo Hyeon Lim, Jin Mo Goo, and Chang Min Park
- Subjects
Radiography ,Thoracic ,Deep learning ,Artificial intelligence ,Pneumonia ,Febrile neutropenia ,Diseases of the respiratory system ,RC705-779 - Abstract
Abstract Background Diagnosis of pneumonia is critical in managing patients with febrile neutropenia (FN), however, chest X-ray (CXR) has limited performance in the detection of pneumonia. We aimed to evaluate the performance of a deep learning-based computer-aided detection (CAD) system in pneumonia detection in the CXRs of consecutive FN patients and investigated whether CAD could improve radiologists’ diagnostic performance when used as a second reader. Methods CXRs of patients with FN (a body temperature ≥ 38.3 °C, or a sustained body temperature ≥ 38.0 °C for an hour; absolute neutrophil count
- Published
- 2021
- Full Text
- View/download PDF
4. Methods of Visualizing the Results of an Artificial-Intelligence-Based Computer-Aided Detection System for Chest Radiographs: Effect on the Diagnostic Performance of Radiologists
- Author
-
Sungho Hong, Eui Jin Hwang, Soojin Kim, Jiyoung Song, Taehee Lee, Gyeong Deok Jo, Yelim Choi, Chang Min Park, and Jin Mo Goo
- Subjects
chest radiography ,artificial intelligence ,deep learning ,computer-aided detection ,diagnostic accuracy ,Medicine (General) ,R5-920 - Abstract
It is unclear whether the visualization methods for artificial-intelligence-based computer-aided detection (AI-CAD) of chest radiographs influence the accuracy of readers’ interpretation. We aimed to evaluate the accuracy of radiologists’ interpretations of chest radiographs using different visualization methods for the same AI-CAD. Initial chest radiographs of patients with acute respiratory symptoms were retrospectively collected. A commercialized AI-CAD using three different methods of visualizing was applied: (a) closed-line method, (b) heat map method, and (c) combined method. A reader test was conducted with five trainee radiologists over three interpretation sessions. In each session, the chest radiographs were interpreted using AI-CAD with one of the three visualization methods in random order. Examination-level sensitivity and accuracy, and lesion-level detection rates for clinically significant abnormalities were evaluated for the three visualization methods. The sensitivity (p = 0.007) and accuracy (p = 0.037) of the combined method are significantly higher than that of the closed-line method. Detection rates using the heat map method (p = 0.043) and the combined method (p = 0.004) are significantly higher than those using the closed-line method. The methods for visualizing AI-CAD results for chest radiographs influenced the performance of radiologists’ interpretations. Combining the closed-line and heat map methods for visualizing AI-CAD results led to the highest sensitivity and accuracy of radiologists.
- Published
- 2023
- Full Text
- View/download PDF
5. Determination of the optimum definition of growth evaluation for indeterminate pulmonary nodules detected in lung cancer screening
- Author
-
Jong Hyuk Lee, Eui Jin Hwang, Woo Hyeon Lim, and Jin Mo Goo
- Subjects
Medicine ,Science - Abstract
Objective To determine the optimum definition of growth for indeterminate pulmonary nodules detected in lung cancer screening. Materials and methods Individuals with indeterminate nodules as defined by volume of 50–500 mm3 (solid nodules) and solid component volume of 50–500 mm3 or average diameter of non-solid component ≥8 mm (part-solid nodules) on baseline lung cancer screening low-dose chest CT (LDCT) were included. The average diameters and volumes of the nodules were measured on baseline and follow-up LDCTs with semi-automated segmentation. Sensitivities and specificities for lung cancer diagnosis of nodule growth defined by a) percentage volume growth ≥25% (defined in the NELSON study); b) absolute diameter growth >1.5 mm (defined in the Lung-RADS version 1.1); and c) subjective decision by a radiologist were evaluated. Sensitivities and specificities of diagnostic referral based on various thresholds of volume doubling time (VDT) were also evaluated. Results Altogether, 115 nodules (one nodule per individual; 93 solid and 22 part-solid nodules; 105 men; median age, 68 years) were evaluated (median follow-up interval: 201 days; interquartile range: 127–371 days). Percentage volume growth ≥25% exhibited higher sensitivity but lower specificity than those of diametrical measurement compared to absolute diameter growth >1.5 mm (sensitivity, 69.2% vs. 42.3%, p = 0.023; specificity, 82.0% vs. 96.6%, p = 0.002). The radiologist had an equivalent sensitivity (53.9%; p = 0.289) but higher specificity (98.9%; p = 0.002) compared to those of volume growth, but did not differ from those of diameter growth (p>0.05 both in sensitivity and specificity). Compared to the VDT threshold of 600 days (sensitivity, 61.5%; specificity, 87.6%), VDT thresholds ≤200 and ≤300 days exhibited significantly lower sensitivity (30.8%, p = 0.013) and higher specificity (94.4%, p = 0.041), respectively. Conclusion Growth evaluation of screening-detected indeterminate nodules with volumetric measurement exhibited higher sensitivity but lower specificity compared to diametric measurements.
- Published
- 2022
6. Significant Abnormalities Other than Lung Cancer in Korean Lung Cancer CT Screening
- Author
-
Soon Ho Yoon, Junghee Hong, Eui Jin Hwang, Heekyung Kim, Hyun-ju Lim, Young Joo Suh, Hyae Young Kim, and Jin Mo Goo
- Subjects
lung neoplasms ,early detection of cancer ,computed tomography ,x-ray ,incidental findings ,Medical physics. Medical radiology. Nuclear medicine ,R895-920 - Abstract
A low-dose chest CT is performed for early detection of lung cancer, but the CT scan frequently shows several incidental abnormalities. Identification of the incidental findings may enable early detection of diseases other than lung cancer, thereby improving the survival of the individual undergoing screening. However, insignificant incidental abnormalities may cause unnecessary additional examination and costs. It is crucial for radiologists to appropriately comprehend and report significant incidental abnormalities other than lung cancer for successful implementation of the national lung cancer screening program in Korea.
- Published
- 2019
- Full Text
- View/download PDF
7. COVID-19 pneumonia on chest X-rays: Performance of a deep learning-based computer-aided detection system.
- Author
-
Eui Jin Hwang, Ki Beom Kim, Jin Young Kim, Jae-Kwang Lim, Ju Gang Nam, Hyewon Choi, Hyungjin Kim, Soon Ho Yoon, Jin Mo Goo, and Chang Min Park
- Subjects
Medicine ,Science - Abstract
Chest X-rays (CXRs) can help triage for Coronavirus disease (COVID-19) patients in resource-constrained environments, and a computer-aided detection system (CAD) that can identify pneumonia on CXR may help the triage of patients in those environment where expert radiologists are not available. However, the performance of existing CAD for identifying COVID-19 and associated pneumonia on CXRs has been scarcely investigated. In this study, CXRs of patients with and without COVID-19 confirmed by reverse transcriptase polymerase chain reaction (RT-PCR) were retrospectively collected from four and one institution, respectively, and a commercialized, regulatory-approved CAD that can identify various abnormalities including pneumonia was used to analyze each CXR. Performance of the CAD was evaluated using area under the receiver operating characteristic curves (AUCs), with reference standards of the RT-PCR results and the presence of findings of pneumonia on chest CTs obtained within 24 hours from the CXR. For comparison, 5 thoracic radiologists and 5 non-radiologist physicians independently interpreted the CXRs. Afterward, they re-interpreted the CXRs with corresponding CAD results. The performance of CAD (AUCs, 0.714 and 0.790 against RT-PCR and chest CT, respectively hereinafter) were similar with those of thoracic radiologists (AUCs, 0.701 and 0.784), and higher than those of non-radiologist physicians (AUCs, 0.584 and 0.650). Non-radiologist physicians showed significantly improved performance when assisted with the CAD (AUCs, 0.584 to 0.664 and 0.650 to 0.738). In addition, inter-reader agreement among physicians was also improved in the CAD-assisted interpretation (Fleiss' kappa coefficient, 0.209 to 0.322). In conclusion, radiologist-level performance of the CAD in identifying COVID-19 and associated pneumonia on CXR and enhanced performance of non-radiologist physicians with the CAD assistance suggest that the CAD can support physicians in interpreting CXRs and helping image-based triage of COVID-19 patients in resource-constrained environment.
- Published
- 2021
- Full Text
- View/download PDF
8. Portable high-intensity focused ultrasound system with 3D electronic steering, real-time cavitation monitoring, and 3D image reconstruction algorithms: a preclinical study in pigs
- Author
-
Jin Woo Choi, Jae Young Lee, Eui Jin Hwang, Inpyeong Hwang, Sungmin Woo, Chang Joo Lee, Eun-Joo Park, and Byung Ihn Choi
- Subjects
High-intensity focused ultrasound ablation ,Ablation techniques ,Animal research ,Equipment and supplies ,Medical technology ,R855-855.5 - Abstract
Purpose: The aim of this study was to evaluate the safety and accuracy of a new portable ultrasonography-guided high-intensity focused ultrasound (USg-HIFU) system with a 3-dimensional (3D) electronic steering transducer, a simultaneous ablation and imaging module, real-time cavitation monitoring, and 3D image reconstruction algorithms. Methods: To address the accuracy of the transducer, hydrophones in a water chamber were used to assess the generation of sonic fields. An animal study was also performed in five pigs by ablating in vivo thighs by single-point sonication (n=10) or volume sonication (n=10) and ex vivo kidneys by single-point sonication (n=10). Histological and statistical analyses were performed. Results: In the hydrophone study, peak voltages were detected within 1.0 mm from the targets on the y- and z-axes and within 2.0-mm intervals along the x-axis (z-axis, direction of ultrasound propagation; y- and x-axes, perpendicular to the direction of ultrasound propagation). Twenty-nine of 30 HIFU sessions successfully created ablations at the target. The in vivo porcine thigh study showed only a small discrepancy (width, 0.5-1.1 mm; length, 3.0 mm) between the planning ultrasonograms and the pathological specimens. Inordinate thermal damage was not observed in the adjacent tissues or sonic pathways in the in vivo thigh and ex vivo kidney studies. Conclusion: Our study suggests that this new USg-HIFU system may be a safe and accurate technique for ablating soft tissues and encapsulated organs.
- Published
- 2014
- Full Text
- View/download PDF
9. Impact of Reconstruction Algorithms on CT Radiomic Features of Pulmonary Tumors: Analysis of Intra- and Inter-Reader Variability and Inter-Reconstruction Algorithm Variability.
- Author
-
Hyungjin Kim, Chang Min Park, Myunghee Lee, Sang Joon Park, Yong Sub Song, Jong Hyuk Lee, Eui Jin Hwang, and Jin Mo Goo
- Subjects
Medicine ,Science - Abstract
To identify the impact of reconstruction algorithms on CT radiomic features of pulmonary tumors and to reveal and compare the intra- and inter-reader and inter-reconstruction algorithm variability of each feature.Forty-two patients (M:F = 19:23; mean age, 60.43±10.56 years) with 42 pulmonary tumors (22.56±8.51mm) underwent contrast-enhanced CT scans, which were reconstructed with filtered back projection and commercial iterative reconstruction algorithm (level 3 and 5). Two readers independently segmented the whole tumor volume. Fifteen radiomic features were extracted and compared among reconstruction algorithms. Intra- and inter-reader variability and inter-reconstruction algorithm variability were calculated using coefficients of variation (CVs) and then compared.Among the 15 features, 5 first-order tumor intensity features and 4 gray level co-occurrence matrix (GLCM)-based features showed significant differences (p
- Published
- 2016
- Full Text
- View/download PDF
10. 2023 Survey on User Experience of Artificial Intelligence Software in Radiology by the Korean Society of Radiology.
- Author
-
Eui Jin Hwang, Ji Eun Park, Kyoung Doo Song, Dong Hyun Yang, Kyung Won Kim, June-Goo Lee, Jung Hyun Yoon, Kyunghwa Han, Dong Hyun Kim, Hwiyoung Kim, and Chang Min Park
- Published
- 2024
- Full Text
- View/download PDF
11. Deep Learning–Based Kernel Adaptation Enhances Quantification of Emphysema on Low-Dose Chest CT for Predicting Long-Term Mortality.
- Author
-
Hyungin Park, Eui Jin Hwang, and Jin Mo Goo
- Published
- 2024
- Full Text
- View/download PDF
12. Generalization of Photography and the Emergence of ‘Female Photo Taker’ in Everyday Life: Focusing on the Public Discourse of Casual Photo-taking in the 1960~80s
- Author
-
Eui-Jin Hwang
- Published
- 2023
13. Identification of Active Pulmonary Tuberculosis Among Patients With Positive Interferon-Gamma Release Assay Results
- Author
-
Jongsoo Park, Eui Jin Hwang, Jong Hyuk Lee, Wonju Hong, Ju Gang Nam, Woo Hyeon Lim, Jae Hyun Kim, Jin Mo Goo, and Chang Min Park
- Subjects
Pulmonary and Respiratory Medicine ,Radiology, Nuclear Medicine and imaging - Published
- 2023
14. Caveats in Using Abnormality/Probability Scores from Artificial Intelligence Algorithms: Neither True Probability nor Level of Trustworthiness.
- Author
-
Seong Ho Park and Eui Jin Hwang
- Published
- 2024
- Full Text
- View/download PDF
15. AI Improves Nodule Detection on Chest Radiographs in a Health Screening Population: A Randomized Controlled Trial
- Author
-
Ju Gang Nam, Eui Jin Hwang, Jayoun Kim, Nanhee Park, Eun Hee Lee, Hyun Jin Kim, Miyeon Nam, Jong Hyuk Lee, Chang Min Park, and Jin Mo Goo
- Subjects
Radiology, Nuclear Medicine and imaging - Published
- 2023
16. Effects of Implementing Artificial Intelligence-Based Computer-Aided Detection for Chest Radiographs in Daily Practice on the Rate of Referral to Chest Computed Tomography in Pulmonology Outpatient Clinic.
- Author
-
Wonju Hong, Eui Jin Hwang, Chang Min Park, and Jin Mo Goo
- Published
- 2023
- Full Text
- View/download PDF
17. Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology
- Author
-
Yisak, Kim, Ji Yoon, Park, Eui Jin, Hwang, Sang Min, Lee, and Chang Min, Park
- Subjects
Pulmonary and Respiratory Medicine ,Review Article on Artificial Intelligence in Thoracic Disease: from Bench to Bed - Abstract
OBJECTIVE: This review will focus on how AI—and, specifically, deep learning—can be applied to complement aspects of the current healthcare system. We describe how AI-based tools can augment existing clinical workflows by discussing the applications of AI to worklist prioritization and patient triage, the performance-boosting effects of AI as a second reader, and the use of AI to facilitate complex quantifications. We also introduce prominent examples of recent AI applications, such as tuberculosis screening in resource-constrained environments, the detection of lung cancer with screening CT, and the diagnosis of COVID-19. We also provide examples of prognostic predictions and new discoveries beyond existing clinical practices. BACKGROUND: Artificial intelligence (AI) has shown promising performance for thoracic diseases, particularly in the field of thoracic radiology. However, it has not yet been established how AI-based image analysis systems can help physicians in clinical practice. METHODS: This review included peer-reviewed research articles on AI in the thorax published in English between 2015 and 2021. CONCLUSIONS: With advances in technology and appropriate preparation of physicians, AI could address various clinical problems that have not been solved due to a lack of clinical resources or technological limitations. KEYWORDS: Artificial intelligence (AI); deep learning (DL); computer aided diagnosis (CAD); thoracic radiology; pulmonary medicine
- Published
- 2021
18. Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs
- Author
-
Eui Jin Hwang, Jeong Su Lee, Chang Min Park, Woo Hyeon Lim, Tae-Hyung Kim, Kyu Sung Choi, Jae Hyun Kim, Jin Mo Goo, Jong Hyuk Lee, and Tae Won Choi
- Subjects
Male ,medicine.medical_specialty ,Radiography ,Sensitivity and Specificity ,Metastasis ,Cohort Studies ,Deep Learning ,medicine ,Humans ,Pulmonary metastasis ,Radiology, Nuclear Medicine and imaging ,Lung ,Tuberculosis, Pulmonary ,Generalized estimating equation ,Retrospective Studies ,business.industry ,Cancer ,Middle Aged ,medicine.disease ,medicine.anatomical_structure ,Propensity score matching ,Radiographic Image Interpretation, Computer-Assisted ,Female ,Radiography, Thoracic ,Radiology ,business ,Cohort study - Abstract
Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.
- Published
- 2021
19. 3-hydroxymorphinan enhances mitochondrial biogenesis and adipocyte browning through AMPK-dependent pathway
- Author
-
Eui Jin Hwang, Do Hyeon Pyun, Tae Jin Kim, Ji Hoon Jeong, Joon Seok Bang, A. M. Abd El-Aty, Hyunjung Lee, Hyoung-Chun Kim, and Tae Woo Jung
- Subjects
Mitochondrial ROS ,Cell Survival ,Blotting, Western ,Biophysics ,AMP-Activated Protein Kinases ,Mitochondrion ,medicine.disease_cause ,Dextromethorphan ,Biochemistry ,Neuroprotection ,Mice ,chemistry.chemical_compound ,3T3-L1 Cells ,Adipocyte ,Adipocytes ,medicine ,Animals ,Phosphorylation ,Molecular Biology ,Uncoupling Protein 1 ,Organelle Biogenesis ,Lipogenesis ,AMPK ,Cell Biology ,Lipid Metabolism ,Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-alpha ,Mitochondria ,Cell biology ,Oxidative Stress ,Adipocytes, Brown ,chemistry ,Mitochondrial biogenesis ,RNA Interference ,Oxidative stress ,Signal Transduction - Abstract
3-hydroxymorphinan (3-HM), a metabolite of dextromethorphan, has previously been reported to have anti-inflammatory, anti-oxidative stress, and neuroprotective effects. However, its effect on energy metabolism in adipocytes remains unclear. Herein, we investigated 3-hydroxymorphinan (3-HM) effects on mitochondrial biogenesis, oxidative stress, and lipid accumulation in 3T3-L1 adipocytes. Further, we explored 3-HM-associated molecular mechanisms. Mouse adipocyte 3T3-L1 cells were treated with 3-HM, and various protein expression levels were determined by western blotting analysis. Mitochondria accumulation and lipid accumulation were measured by staining methods. Cell toxicity was assessed by cell viability assay. We found that treatment of 3T3-L1 adipocytes with 3-HM increased expression of brown adipocyte markers, such as uncoupling protein-1 (UCP-1) and peroxisome proliferator-activated receptor-gamma coactivator 1-alpha (PGC-1α). 3-HM promotes mitochondrial biogenesis and its-mediated gene expression. Additionally, 3-HM treatment suppressed mitochondrial ROS generation and superoxide along with improved mitochondrial complex I activity. We found that treatment of 3-HM enhanced AMPK phosphorylation. siRNA-mediated suppression of AMPK reversed all these changes in 3T3-L1 adipocytes. In sum, 3-HM promotes mitochondrial biogenesis and browning and attenuates oxidative stress and lipid accumulation in 3T3-L1 adipocytes via AMPK signaling. Thus, 3-HM-mediated AMPK activation can be considered a therapeutic approach for treating obesity and related diseases.
- Published
- 2021
20. Value of a deep learning-based algorithm for detecting Lung-RADS category 4 nodules on chest radiographs in a health checkup population: estimation of the sample size for a randomized controlled trial
- Author
-
Chang Min Park, Eun Hee Lee, Jongsoo Park, Eui Jin Hwang, Wonju Hong, Ju Gang Nam, Hyun Jin Kim, and Jin Mo Goo
- Subjects
education.field_of_study ,medicine.medical_specialty ,medicine.diagnostic_test ,business.industry ,Radiography ,Population ,Retrospective cohort study ,Interventional radiology ,General Medicine ,Asymptomatic ,law.invention ,Randomized controlled trial ,law ,Sample size determination ,medicine ,Radiology, Nuclear Medicine and imaging ,Radiology ,medicine.symptom ,education ,business ,Algorithm ,Neuroradiology - Abstract
To explore the value of a deep learning-based algorithm in detecting Lung CT Screening Reporting and Data System category 4 nodules on chest radiographs from an asymptomatic health checkup population. Data from an annual retrospective cohort of individuals who underwent chest radiographs for health checkup purposes and chest CT scanning within 3 months were collected. Among 3073 individuals, 118 with category 4 nodules on CT were selected. A reader performance test was performed using those 118 radiographs and randomly selected 51 individuals without any nodules. Four radiologists independently evaluated the radiographs without and with the results of the algorithm; and sensitivities/specificities were compared. The sample size needed to confirm the difference in detection rates was calculated, i.e., the number of true-positive radiographs divided by the total number of radiographs. The sensitivity of the radiologists substantially increased aided by the algorithm (38.8% [183/472] to 45.1% [213/472]; p 80% power. Although readers substantially increased sensitivity in detecting nodules on chest radiographs from a health checkup population aided by the algorithm, detection rate difference was only 0.24%, requiring a sample size >80,000 for a randomized controlled trial. • Aided by a deep learning algorithm, pooled radiologists improved their sensitivity in detecting Lung-RADS category 4 nodules on chest radiographs from a health checkup population (38.8% [183/472] to 45.1% [213/472]; p < .001), without increasing false-positive rate. • The prevalence of the Lung-RADS category 4 nodules was 3.8% (118/3073) on the population, resulting in only 0.24% increase of the detection rate for the radiologists with assistance of the algorithm. • To confirm the significant detection rate increase by a randomized controlled trial, a sample size of 84,000 would be required.
- Published
- 2021
21. Automatic prediction of left cardiac chamber enlargement from chest radiographs using convolutional neural network
- Author
-
Chang Min Park, Hyewon Choi, Seung-Jin Yoo, Min-Soo Kim, Eun Ah Park, Hyun-Lim Yang, Da Som Kim, Keonwoo Noh, Eui Jin Hwang, Ju Gang Nam, Hye Young Sun, Jin Mo Goo, and Jinwook Kim
- Subjects
medicine.medical_specialty ,Receiver operating characteristic ,medicine.diagnostic_test ,business.industry ,Radiography ,Ultrasound ,Interventional radiology ,General Medicine ,medicine.disease ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,030220 oncology & carcinogenesis ,Cohort ,Left atrial enlargement ,medicine ,Radiology, Nuclear Medicine and imaging ,Radiology ,business ,Left cardiac chamber ,Neuroradiology - Abstract
To develop deep learning–based cardiac chamber enlargement-detection algorithms for left atrial (DLCE-LAE) and ventricular enlargement (DLCE-LVE), on chest radiographs For training and internal validation of DLCE-LAE and -LVE, 5,045 chest radiographs (CRs; 2,463 normal and 2,393 LAE) and 1,012 CRs (456 normal and 456 LVE) matched with the same-day echocardiography were collected, respectively. External validation was performed using 107 temporally independent CRs. Reader performance test was conducted using the external validation dataset by five cardiothoracic radiologists without and with the results of DLCE. Classification performance of DLCE was evaluated and compared with those of the readers and conventional radiographic features, including cardiothoracic ratio, carinal angle, and double contour. In addition, DLCE-LAE was tested on 5,277 CRs from a healthcare screening program cohort. DLCE-LAE showed areas under the receiver operating characteristics curve (AUROCs) of 0.858 on external validation. On reader performance test, DLCE-LAE showed better results than pooled radiologists (AUROC 0.858 vs. 0.651; p < .001) and significantly increased their performance when used as a second reader (AUROC 0.651 vs. 0.722; p < .001). DLCE-LAE also showed a significantly higher AUROC than conventional radiographic findings (AUROC 0.858 vs. 0.535–0.706; all ps < .01). In the healthcare screening cohort, DLCE-LAE successfully detected 71.0% (142/200) CRs with moderate-to-severe LAE (93.5% [29/31] of severe cases), while yielding 11.8% (492/4,184) false-positive rate. DLCE-LVE showed AUROCs of 0.966 and 0.594 on internal and external validation, respectively. DLCE-LAE outperformed and improved cardiothoracic radiologists’ performance in detecting LAE and showed promise in screening individuals with moderate-to-severe LAE in a healthcare screening cohort. • Our deep learning algorithm outperformed cardiothoracic radiologists in detecting left atrial enlargement on chest radiographs. • Cardiothoracic radiologists improved their performance in detecting left atrial enlargement when aided by the algorithm. • On a healthcare-screening cohort, our algorithm detected 71.0% (142/200) radiographs with moderate-to-severe left atrial enlargement while yielding 11.8% (492/4,184) false-positive rate.
- Published
- 2021
22. Optimum diameter threshold for lung nodules at baseline lung cancer screening with low-dose chest CT: exploration of results from the Korean Lung Cancer Screening Project
- Author
-
Jaeyoun Yi, Eui Jin Hwang, Yeol Kim, Hyae Young Kim, and Jin Mo Goo
- Subjects
medicine.medical_specialty ,Lung ,business.industry ,Low dose ,Ultrasound ,Chest ct ,General Medicine ,medicine.disease ,030218 nuclear medicine & medical imaging ,Effective diameter ,03 medical and health sciences ,0302 clinical medicine ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,medicine ,Radiology, Nuclear Medicine and imaging ,Radiology ,Lung cancer ,business ,Transverse diameter ,Lung cancer screening - Abstract
To explore the optimum diameter threshold for solid nodules to define positive results at baseline screening low-dose CT (LDCT) and to compare two-dimensional and volumetric measurement of lung nodules for the diagnosis of lung cancers. We included consecutive participants from the Korean Lung Cancer Screening project between 2017 and 2018. The average transverse diameter and effective diameter (diameter of a sphere with the same volume) of lung nodules were measured by semi-automated segmentation. Diagnostic performances for lung cancers diagnosed within 1 year after LDCT were evaluated using area under receiver-operating characteristic curves (AUCs), sensitivities, and specificities, with diameter thresholds for solid nodules ranging from 6 to 10 mm. The reduction of unnecessary follow-up LDCTs and the diagnostic delay of lung cancers were estimated for each threshold. Fifty-two lung cancers were diagnosed among 10,424 (10,141 men; median age 62 years) participants within 1 year after LDCT. Average transverse (0.980) and effective diameters (0.981) showed similar AUCs (p = .739). Elevating the average transverse diameter threshold from 6 to 9 mm resulted in a significantly increased specificity (91.7 to 96.7%, p < .001), a modest reduction in sensitivity (96.2 to 94.2%, p = .317), a 60.2% estimated reduction of unnecessary follow-up LDCTs, and a diagnostic delay in 1.9% of lung cancers. Elevating the threshold to 10 mm led to a significant reduction in sensitivity (86.5%, p = .025). Elevating the diameter threshold for solid nodules from 6 to 9 mm may lead to a substantial reduction in unnecessary follow-up LDCTs with a small proportion of diagnostic delay of lung cancers. • Elevation of the diameter threshold for solid nodules from 6 to 9 mm can substantially reduce unnecessary follow-up LDCTs with a small proportion of diagnostic delay of lung cancers. • The average transverse and effective diameters of lung nodules showed similar performances for the prediction of a lung cancer diagnosis.
- Published
- 2021
23. Effects of Expert-Determined Reference Standards in Evaluating the Diagnostic Performance of a Deep Learning Model: A Malignant Lung Nodule Detection Task on Chest Radiographs
- Author
-
Jung Eun Huh, Jong Hyuk Lee, Eui Jin Hwang, and Chang Min Park
- Subjects
Radiology, Nuclear Medicine and imaging - Published
- 2023
24. Conventional Versus Artificial Intelligence-Assisted Interpretation of Chest Radiographs in Patients With Acute Respiratory Symptoms in Emergency Department: A Pragmatic Randomized Clinical Trial
- Author
-
Eui Jin Hwang, Jin Mo Goo, Ju Gang Nam, Chang Min Park, Ki Jeong Hong, and Ki Hong Kim
- Subjects
Radiology, Nuclear Medicine and imaging - Published
- 2023
25. Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population
- Author
-
Hye Young Sun, Sunggyun Park, Jin Mo Goo, Eui Jin Hwang, Hyungjin Kim, Jong Hyuk Lee, and Chang Min Park
- Subjects
Male ,Validation study ,Lung Neoplasms ,health care facilities, manpower, and services ,Radiography ,education ,Population ,Sensitivity and Specificity ,Deep Learning ,health services administration ,Republic of Korea ,medicine ,Humans ,Mass Screening ,Radiology, Nuclear Medicine and imaging ,Lung cancer ,Health screening ,Mass screening ,Retrospective Studies ,education.field_of_study ,business.industry ,Deep learning ,Retrospective cohort study ,Middle Aged ,respiratory system ,medicine.disease ,respiratory tract diseases ,Female ,Radiography, Thoracic ,Artificial intelligence ,business ,Algorithm - Abstract
Background The performance of a deep learning algorithm for lung cancer detection on chest radiographs in a health screening population is unknown. Purpose To validate a commercially available deep learning algorithm for lung cancer detection on chest radiographs in a health screening population. Materials and Methods Out-of-sample testing of a deep learning algorithm was retrospectively performed using chest radiographs from individuals undergoing a comprehensive medical check-up between July 2008 and December 2008 (validation test). To evaluate the algorithm performance for visible lung cancer detection, the area under the receiver operating characteristic curve (AUC) and diagnostic measures, including sensitivity and false-positive rate (FPR), were calculated. The algorithm performance was compared with that of radiologists using the McNemar test and the Moskowitz method. Additionally, the deep learning algorithm was applied to a screening cohort undergoing chest radiography between January 2008 and December 2012, and its performances were calculated. Results In a validation test comprising 10 285 radiographs from 10 202 individuals (mean age, 54 years ± 11 [standard deviation]; 5857 men) with 10 radiographs of visible lung cancers, the algorithm's AUC was 0.99 (95% confidence interval: 0.97, 1), and it showed comparable sensitivity (90% [nine of 10 radiographs]) to that of the radiologists (60% [six of 10 radiographs]
- Published
- 2020
26. Variability in interpretation of low-dose chest CT using computerized assessment in a nationwide lung cancer screening program: comparison of prospective reading at individual institutions and retrospective central reading
- Author
-
Yeol Kim, Soon Ho Yoon, Gong Yong Jin, Eui Jin Hwang, Jaeyoun Yi, Hyae Young Kim, and Jin Mo Goo
- Subjects
medicine.medical_specialty ,medicine.diagnostic_test ,business.industry ,Low dose ,Chest ct ,Interventional radiology ,General Medicine ,030218 nuclear medicine & medical imaging ,Central laboratory ,03 medical and health sciences ,0302 clinical medicine ,Tomography x ray computed ,030220 oncology & carcinogenesis ,medicine ,Computerized system ,Radiology, Nuclear Medicine and imaging ,Radiology ,business ,Lung cancer screening ,Neuroradiology - Abstract
To evaluate the degree of variability in computer-assisted interpretation of low-dose chest CTs (LDCTs) among radiologists in a nationwide lung cancer screening (LCS) program, through comparison with a retrospective interpretation from a central laboratory. Consecutive baseline LDCTs (n = 3353) from a nationwide LCS program were investigated. In the institutional reading, 20 radiologists in 14 institutions interpreted LDCTs using computer-aided detection and semi-automated segmentation systems for lung nodules. In the retrospective central review, a single radiologist re-interpreted all LDCTs using the same system, recording any non-calcified nodules ≥ 3 mm without arbitrary rejection of semi-automated segmentation to minimize the intervention of radiologist’s discretion. Positive results (requiring additional follow-up LDCTs or diagnostic procedures) were initially classified by the lung CT screening reporting and data system (Lung-RADS) during the interpretation, while the classifications based on the volumetric criteria from the Dutch-Belgian lung cancer screening trial (NELSON) were retrospectively applied. Variabilities in positive rates were assessed with coefficients of variation (CVs). In the institutional reading, positive rates by the Lung-RADS ranged from 7.5 to 43.3%, and those by the NELSON ranged from 11.4 to 45.0% across radiologists. The central review exhibited higher positive rates by Lung-RADS (20.0% vs. 27.3%; p
- Published
- 2020
27. Prediction of visceral pleural invasion in lung cancer on CT: deep learning model achieves a radiologist-level performance with adaptive sensitivity and specificity to clinical needs
- Author
-
Eui Jin Hwang, Jongsoo Park, Hyungjin Kim, Chang Min Park, Young Tae Kim, Hyewon Choi, Jin Mo Goo, and Wonju Hong
- Subjects
medicine.medical_specialty ,Lung ,Receiver operating characteristic ,medicine.diagnostic_test ,business.industry ,Retrospective cohort study ,Interventional radiology ,General Medicine ,Odds ratio ,medicine.disease ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,Medicine ,Radiology, Nuclear Medicine and imaging ,Radiology ,Stage (cooking) ,business ,Lung cancer ,Neuroradiology - Abstract
To develop and validate a preoperative CT-based deep learning model for the prediction of visceral pleural invasion (VPI) in early-stage lung cancer. In this retrospective study, dataset 1 (for training, tuning, and internal validation) included 676 patients with clinical stage IA lung adenocarcinomas resected between 2009 and 2015. Dataset 2 (for temporal validation) included 141 patients with clinical stage I adenocarcinomas resected between 2017 and 2018. A CT-based deep learning model was developed for the prediction of VPI and validated in terms of discrimination and calibration. An observer performance study and a multivariable regression analysis were performed. The area under the receiver operating characteristic curve (AUC) of the model was 0.75 (95% CI, 0.67–0.84), which was comparable to those of board-certified radiologists (AUC, 0.73–0.79; all p > 0.05). The model had a higher standardized partial AUC for a specificity range of 90 to 100% than the radiologists (all p 0.05), and its output was an independent predictor for VPI (adjusted odds ratio, 1.07; 95% CI, 1.03–1.11; p
- Published
- 2020
28. Deep Learning for Detecting Pneumothorax on Chest Radiographs after Needle Biopsy: Clinical Implementation
- Author
-
Wonju Hong, Eui Jin Hwang, Jong Hyuk Lee, Jongsoo Park, Jin Mo Goo, and Chang Min Park
- Subjects
Male ,Deep Learning ,Lung Neoplasms ,Biopsy, Needle ,Humans ,Pneumothorax ,Radiology, Nuclear Medicine and imaging ,Female ,Radiography, Thoracic ,Aged ,Retrospective Studies - Abstract
Background Accurate detection of pneumothorax on chest radiographs, the most common complication of percutaneous transthoracic needle biopsies (PTNBs), is not always easy in practice. A computer-aided detection (CAD) system may help detect pneumothorax. Purpose To investigate whether a deep learning-based CAD system can improve detection performance for pneumothorax on chest radiographs after PTNB in clinical practice. Materials and Methods A CAD system for post-PTNB pneumothorax detection on chest radiographs was implemented in an institution in February 2020. This retrospective cohort study consecutively included chest radiographs interpreted with CAD assistance (CAD-applied group; February 2020 to November 2020) and those interpreted before implementation (non-CAD group; January 2018 to January 2020). The reference standard was defined by consensus reading by two radiologists. The diagnostic accuracy for pneumothorax was compared between the two groups using generalized estimating equations. Matching was performed according to whether the radiograph reader and PTNB operator were the same using the greedy method. Results A total of 676 radiographs from 655 patients (mean age: 67 years ± 11; 390 men) in the CAD-applied group and 676 radiographs from 664 patients (mean age: 66 years ± 12; 400 men) in the non-CAD group were included. The incidence of pneumothorax was 18.2% (123 of 676 radiographs) in the CAD-applied group and 22.5% (152 of 676 radiographs) in the non-CAD group (
- Published
- 2022
29. Evaluation of Chest X-Ray With Automated Interpretation Algorithms for Mass Tuberculosis Screening in Prisons
- Author
-
Thiego Ramon Soares, Roberto Dias de Oliveira, Yiran E. Liu, Andrea da Silva Santos, Paulo Cesar Pereira dos Santos, Luma Ravena Soares Monte, Lissandra Maia de Oliveira, Chang Min Park, Eui Jin Hwang, Jason R. Andrews, and Julio Croda
- Subjects
History ,Polymers and Plastics ,Business and International Management ,Industrial and Manufacturing Engineering - Abstract
RationaleThe World Health Organization (WHO) recommends systematic tuberculosis (TB) screening in prisons. Evidence is lacking for accurate and scalable screening approaches in this setting.ObjectivesTo assess the diagnostic accuracy of artificial intelligence-based chest x-ray interpretation algorithms for TB screening in prisons.MethodsProspective TB screening study in three prisons in Brazil from October 2017 to December 2019. We administered a standardized questionnaire, performed chest x-ray in a mobile unit, and collected sputum for confirmatory testing using Xpert MTB/RIF and culture. We evaluated x-ray images using three algorithms (CAD4TB version 6, LunitTB and qXR) and compared their diagnostic accuracy. We utilized multivariable logistic regression to assess the effect of demographic and clinical characteristics on algorithm accuracy. Finally, we investigated the relationship between abnormality scores and Xpert semi-quantitative results.Measurements and Main ResultsAmong 2,075 incarcerated individuals, 259 (12.5%) had confirmed TB. All three algorithms performed similarly overall with AUCs of 0.87-0.91. At 90% sensitivity, only LunitTB and qXR met the WHO Target Product Profile requirements for a triage test, with specificity of 84% and 74%, respectively. All algorithms had variable performance by age, prior TB, smoking, and presence of TB symptoms. LunitTB was the most robust to this heterogeneity, but nonetheless failed to meet the TPP for individuals with previous TB. Abnormality scores of all three algorithms were significantly correlated with sputum bacillary load.ConclusionsAutomated x-ray interpretation algorithms can be an effective triage tool for TB screening in prisons. However, their specificity is insufficient in individuals with previous TB.
- Published
- 2022
30. Implementation of the cloud-based computerized interpretation system in a nationwide lung cancer screening with low-dose CT: comparison with the conventional reading system
- Author
-
Soon Ho Yoon, Yeol Kim, Jin Mo Goo, Hyae Young Kim, Jaeyoun Yi, and Eui Jin Hwang
- Subjects
Nodule detection ,medicine.medical_specialty ,Lung ,medicine.diagnostic_test ,business.industry ,Nodule (medicine) ,Interventional radiology ,General Medicine ,medicine.disease ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,medicine ,Low dose ct ,Radiology, Nuclear Medicine and imaging ,Radiology ,medicine.symptom ,Lung cancer ,business ,Lung cancer screening ,Neuroradiology - Abstract
We aimed to compare the CT interpretation before and after the implementation of a computerized system for lung nodule detection and measurements in a nationwide lung cancer screening program. Our screening program started in April 2017, with 14 participating institutions. Initially, all CTs were interpreted using interpretation systems in each institution and manual nodule measurement (conventional system). A cloud-based CT interpretation system, equipped with semi-automated measurement and CAD (computer-aided detection) for lung nodules (cloud-based system), was implemented during the project. Positive rates and performances for lung cancer diagnosis based on the Lung-RADS version 1.0 were compared between the conventional and cloud-based systems. A total of 1821 (M:F = 1782:39, mean age 62.7 years, 16 confirmed lung cancers) and 4666 participants (M:F = 4560:106, mean age 62.8 years, 31 confirmed lung cancers) were included in the conventional and cloud-based systems, respectively. Significantly more nodules were detected in the cloud-based system (0.76 vs. 1.07 nodule/participant, p
- Published
- 2020
31. Implementation of a Deep Learning-Based Computer-Aided Detection System for the Interpretation of Chest Radiographs in Patients Suspected for COVID-19
- Author
-
Chang Min Park, Soon Ho Yoon, Hyungjin Kim, Jin Mo Goo, and Eui Jin Hwang
- Subjects
Adult ,Male ,medicine.medical_specialty ,Coronavirus disease 2019 (COVID-19) ,Radiography ,Pneumonia, Viral ,Radiography, thoracic ,030218 nuclear medicine & medical imaging ,COVID-19 diagnostic testing ,Thoracic Imaging ,03 medical and health sciences ,Betacoronavirus ,0302 clinical medicine ,Daily practice ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,In patient ,Reference standards ,Pandemics ,Aged ,Retrospective Studies ,business.industry ,SARS-CoV-2 ,COVID-19 ,Retrospective cohort study ,Deep learning ,Pneumonia ,Middle Aged ,medicine.disease ,Computer aided detection ,030220 oncology & carcinogenesis ,Original Article ,Female ,Radiology ,business ,Coronavirus Infections ,Tomography, X-Ray Computed - Abstract
OBJECTIVE: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. MATERIALS AND METHODS: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. RESULTS: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). CONCLUSION: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.
- Published
- 2020
32. Deep learning algorithm for surveillance of pneumothorax after lung biopsy: a multicenter diagnostic cohort study
- Author
-
Jung Im Kim, Chang Min Park, Eui Jin Hwang, Seung-Jin Yoo, Jin Mo Goo, Jung Hee Hong, Ju Gang Nam, Hyewon Choi, Da Som Kim, and Kyung Hee Lee
- Subjects
Adult ,Male ,medicine.medical_specialty ,Percutaneous ,Radiography ,Lung biopsy ,Sensitivity and Specificity ,030218 nuclear medicine & medical imaging ,Cohort Studies ,03 medical and health sciences ,Deep Learning ,0302 clinical medicine ,Radiologists ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,Lung ,Aged ,Retrospective Studies ,Neuroradiology ,medicine.diagnostic_test ,Receiver operating characteristic ,business.industry ,Biopsy, Needle ,Pneumothorax ,Interventional radiology ,General Medicine ,Middle Aged ,medicine.disease ,respiratory tract diseases ,ROC Curve ,Area Under Curve ,030220 oncology & carcinogenesis ,Female ,Radiography, Thoracic ,Radiology ,business ,Algorithm ,Algorithms ,Cohort study - Abstract
Pneumothorax is the most common and potentially life-threatening complication arising from percutaneous lung biopsy. We evaluated the performance of a deep learning algorithm for detection of post-biopsy pneumothorax in chest radiographs (CRs), in consecutive cohorts reflecting actual clinical situation. We retrospectively included post-biopsy CRs of 1757 consecutive patients (1055 men, 702 women; mean age of 65.1 years) undergoing percutaneous lung biopsies from three institutions. A commercially available deep learning algorithm analyzed each CR to identify pneumothorax. We compared the performance of the algorithm with that of radiology reports made in the actual clinical practice. We also conducted a reader study, in which the performance of the algorithm was compared with those of four radiologists. Performances of the algorithm and radiologists were evaluated by area under receiver operating characteristic curves (AUROCs), sensitivity, and specificity, with reference standards defined by thoracic radiologists. Pneumothorax occurred in 17.5% (308/1757) of cases, out of which 16.6% (51/308) required catheter drainage. The AUROC, sensitivity, and specificity of the algorithm were 0.937, 70.5%, and 97.7%, respectively, for identification of pneumothorax. The algorithm exhibited higher sensitivity (70.2% vs. 55.5%, p
- Published
- 2020
33. A narrative review of deep learning applications in lung cancer research: from screening to prognostication
- Author
-
Jong Hyuk Lee, Eui Jin Hwang, Hyungjin Kim, and Chang Min Park
- Subjects
Oncology ,Review Article - Abstract
BACKGROUND AND OBJECTIVE: Deep learning (DL) algorithms have been developed for various tasks, including lung nodule detection on chest radiographs or lung cancer computed tomography screening, potential candidate selection in lung cancer screening, malignancy prediction for indeterminate pulmonary nodules, lung cancer staging, treatment response prediction, prognostication, and prediction of genetic mutations in lung cancer. Furthermore, these DL algorithms have been applied in various clinical settings in order for them to be generalized in real-world clinical practice. Multiple DL algorithms have been corroborated to be on par with experts or current clinical prediction models for several specific tasks. However, no article has yet comprehensively reviewed DL algorithms dedicated to lung cancer research. This narrative review presents an overview of the literature dealing with DL techniques applied in lung cancer research and briefly summarizes the results according to the DL algorithms’ clinical use cases. METHODS: we performed a narrative review by searching the Embase and OVID-MEDLINE databases for articles published in English from October, 2016 until September, 2021 and reviewing the bibliographies of key references to identify important literature related to DL in lung cancer research. The background, development, results, and clinical implications of each DL algorithm are briefly discussed. Lastly, we end this review article by highlighting future directions in lung cancer research using DL techniques. KEY CONTENT AND FINDINGS: DL algorithms have been introduced to show comparable or higher performance than human experts in various clinical settings. Specifically, they have been actively applied to detect lung nodules in chest radiographs or computed tomography (CT) examinations, optimize candidate selection for lung cancer screening (LCS), predict the malignancy of lung nodules, stage lung cancer, and predict treatment response, patients’ prognoses, and genetic mutations in lung cancers. CONCLUSIONS: DL algorithms have corroborated their potential value for various tasks, ranging from lung cancer screening to prognostication of lung cancer patients. Future research is warranted for the clinical application of these algorithms in daily clinical practice and verification of their real-world clinical usefulness.
- Published
- 2021
34. Artificial intelligence system for identification of false-negative interpretations in chest radiographs
- Author
-
Eui Jin Hwang, Jongsoo Park, Wonju Hong, Hyun-Ju Lee, Hyewon Choi, Hyungjin Kim, Ju Gang Nam, Jin Mo Goo, Soon Ho Yoon, Chang Hyun Lee, and Chang Min Park
- Subjects
Radiography ,Artificial Intelligence ,Radiologists ,Humans ,Radiology, Nuclear Medicine and imaging ,Radiography, Thoracic ,General Medicine ,Middle Aged ,Retrospective Studies - Abstract
To investigate the efficacy of an artificial intelligence (AI) system for the identification of false negatives in chest radiographs that were interpreted as normal by radiologists.We consecutively collected chest radiographs that were read as normal during 1 month (March 2020) in a single institution. A commercialized AI system was retrospectively applied to these radiographs. Radiographs with abnormal AI results were then re-interpreted by the radiologist who initially read the radiograph ("AI as the advisor" scenario). The reference standards for the true presence of relevant abnormalities in radiographs were defined by majority voting of three thoracic radiologists. The efficacy of the AI system was evaluated by detection yield (proportion of true-positive identification among the entire examination) and false-referral rate (FRR, proportion of false-positive identification among all examinations). Decision curve analyses were performed to evaluate the net benefits of applying the AI system.A total of 4208 radiographs from 3778 patients (M:F = 1542:2236; median age, 56 years) were included. The AI system identified initially overlooked relevant abnormalities with a detection yield and an FRR of 2.4% and 14.0%, respectively. In the "AI as the advisor" scenario, radiologists detected initially overlooked relevant abnormalities with a detection yield and FRR of 1.2% and 0.97%, respectively. In a decision curve analysis, AI as an advisor scenario exhibited a positive net benefit when the cost-to-benefit ratio was below 1:0.8.An AI system could identify relevant abnormalities overlooked by radiologists and could enable radiologists to correct their false-negative interpretations by providing feedback to radiologists.• In consecutive chest radiographs with normal interpretations, an artificial intelligence system could identify relevant abnormalities that were initially overlooked by radiologists. • The artificial intelligence system could enable radiologists to correct their initial false-negative interpretations by providing feedback to radiologists when overlooked abnormalities were present.
- Published
- 2021
35. Use of Artificial Intelligence-Based Software as Medical Devices for Chest Radiography: A Position Paper from the Korean Society of Thoracic Radiology
- Author
-
Chang Min Park, Sang Min Lee, Jin Mo Goo, Kyongmin Sarah Beck, Kwang Nam Jin, Eui Jin Hwang, Byoung Wook Choi, Joon Beom Seo, Soon Ho Yoon, and Myung Jin Chung
- Subjects
Computer-aided detection ,medicine.medical_specialty ,Artificial intelligence ,business.industry ,Radiography ,Deep learning ,Chest radiography ,Computer aided detection ,Software ,Editorial ,Republic of Korea ,Medicine ,Position paper ,Humans ,Radiology, Nuclear Medicine and imaging ,Medical physics ,Radiography, Thoracic ,business ,Radiology - Published
- 2021
36. Persistent pulmonary subsolid nodules: How long should they be observed until clinically relevant growth occurs?
- Author
-
Chang Min Park and Eui Jin Hwang
- Subjects
Adult ,Male ,Pulmonary and Respiratory Medicine ,Surgical resection ,medicine.medical_specialty ,Lung Neoplasms ,Adenocarcinoma of Lung ,Diagnosis, Differential ,Multidetector Computed Tomography ,medicine ,Humans ,Lung cancer ,Letter to the Editor ,Aged ,Neoplasm Staging ,Retrospective Studies ,Aged, 80 and over ,High probability ,Natural course ,business.industry ,Middle Aged ,Prognosis ,medicine.disease ,Optimal management ,Natural history ,Editorial Commentary ,Disease Progression ,Female ,Radiology ,business ,Follow-Up Studies ,Forecasting - Abstract
The long-term natural course and outcomes of subsolid nodules (SSNs) in terms of true growth, substantial growth, and stage shift need to be clarified.Between 2002 and 2016, 128 subjects with persistent SSNs of 3cm or smaller were enrolled. The baseline and interval changes in the series computed tomography (CT) findings during the follow-up period were subsequently reviewed.The mean follow-up period was 3.57±2.93years. The cumulative percentage of growth nodules of the part-solid nodule (PSN) group was significantly higher than that of the ground-glass nodule (GGN) group by Kaplan-Meier estimation (all p0.0001). For true SSN growth, GGNs usually take a median follow-up of 7 years to grow; PSNs usually take a median follow-up of 3 years to grow. For substantial SSN growth, GGNs usually take a median follow-up of 9 years to grow; PSNs usually take a median follow-up of 3 years to grow. For stage shift, GGNs usually take a median follow-up of 12 years to grow; PSNs usually take a median follow-up of 9 years to grow.The natural course in terms of true growth, substantial growth, and stage shift differed significantly according to their nodule type, which could contribute to the development of follow-up guidelines and management strategy of pulmonary SSNs.
- Published
- 2019
37. Quantitative Thoracic Magnetic Resonance Criteria for the Differentiation of Cysts from Solid Masses in the Anterior Mediastinum
- Author
-
Soon Ho Yoon, Jin Mo Goo, Jeanne B. Ackman, Ho Yun Lee, Hyungjin Kim, Mun Young Paek, Eui Jin Hwang, Jihang Kim, and Heekyung Kim
- Subjects
Male ,Thymoma ,Quantitative magnetic resonance imaging ,Thymic cyst ,Anterior mediastinum ,Mediastinal Neoplasms ,Sensitivity and Specificity ,Thoracic Imaging ,Diagnosis, Differential ,Maximum diameter ,Image Processing, Computer-Assisted ,Medicine ,Effective diffusion coefficient ,Humans ,Radiology, Nuclear Medicine and imaging ,Aged ,medicine.diagnostic_test ,Receiver operating characteristic ,business.industry ,Magnetic resonance imaging ,Middle Aged ,Magnetic Resonance Imaging ,Prevascular mass ,Mediastinal Cyst ,ROC Curve ,Area Under Curve ,Original Article ,Female ,Signal intensity ,business ,Nuclear medicine ,human activities ,MRI - Abstract
Objective To evaluate quantitative magnetic resonance imaging (MRI) parameters for differentiation of cysts from and solid masses in the anterior mediastinum. Materials and Methods The development dataset included 18 patients from two institutions with pathologically-proven cysts (n = 6) and solid masses (n = 12) in the anterior mediastinum. We measured the maximum diameter, normalized T1 and T2 signal intensity (nT1 and nT2), normalized apparent diffusion coefficient (nADC), and relative enhancement ratio (RER) of each lesion. RERs were obtained by non-rigid registration and subtraction of precontrast and postcontrast T1-weighted images. Differentiation criteria between cysts and solid masses were identified based on receiver operating characteristics analysis. For validation, two separate datasets were utilized: 15 patients with 8 cysts and 7 solid masses from another institution (validation dataset 1); and 11 patients with clinically diagnosed cysts stable for more than two years (validation dataset 2). Sensitivity and specificity were calculated from the validation datasets. Results nT2, nADC, and RER significantly differed between cysts and solid masses (p = 0.032, 0.013, and < 0.001, respectively). The following criteria differentiated cysts from solid masses: RER < 26.1%; nADC > 0.63; nT2 > 0.39. In validation dataset 1, the sensitivity of the RER, nADC, and nT2 criteria was 87.5%, 100%, and 75.0%, and the specificity was 100%, 40.0%, and 57.4%, respectively. In validation dataset 2, the sensitivity of the RER, nADC, and nT2 criteria was 90.9%, 90.9%, and 72.7%, respectively. Conclusion Quantitative MRI criteria using nT2, nADC, and particularly RER can assist differentiation of cysts from solid masses in the anterior mediastinum.
- Published
- 2019
38. Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs
- Author
-
Eui Jin, Hwang, Sunggyun, Park, Kwang-Nam, Jin, Jung Im, Kim, So Young, Choi, Jong Hyuk, Lee, Jin Mo, Goo, Jaehong, Aum, Jae-Joon, Yim, Chang Min, Park, and Mi-Jin, Kang
- Subjects
Adult ,Male ,0301 basic medicine ,Microbiology (medical) ,Tuberculosis ,Radiography ,030106 microbiology ,Tuberculosis screening ,Sensitivity and Specificity ,Automation ,03 medical and health sciences ,Deep Learning ,0302 clinical medicine ,Pulmonary tuberculosis ,medicine ,Humans ,Cutoff ,030212 general & internal medicine ,Articles and Commentaries ,Lung ,Tuberculosis, Pulmonary ,computer-aided detection ,Aged ,chest radiograph ,medicine.diagnostic_test ,Receiver operating characteristic ,business.industry ,Deep learning ,Middle Aged ,Thorax ,medicine.disease ,Infectious Diseases ,ROC Curve ,tuberculosis ,Female ,Artificial intelligence ,business ,Chest radiograph ,Algorithm ,Algorithms - Abstract
Background Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. Methods We developed a deep learning–based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. Results DLAD demonstrated classification performance of 0.977–1.000 and localization performance of 0.973–1.000. Sensitivities and specificities for classification were 94.3%–100% and 91.1%–100% using the high-sensitivity cutoff and 84.1%–99.0% and 99.1%–100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746–0.971) and localization (0.993 vs 0.664–0.925) compared to all groups of physicians. Conclusions Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists., A deep learning–based algorithm outperformed radiologists in detecting active pulmonary tuberculosis on chest radiographs and thus may play an important role in diagnosis and screening of tuberculosis in select situations, contributing to the reduction of the high burden of tuberculosis worldwide.
- Published
- 2018
39. Thoracic recurrence in patients with curatively-resected colorectal cancer: incidence, risk factors, and value of chest CT as a postoperative surveillance tool
- Author
-
Eui Jin Hwang, Chang Min Park, Jeong Hoon Lee, Jin Mo Goo, Hyery Kim, Young-Joo Suh, and Ijin Joo
- Subjects
Male ,Thorax ,medicine.medical_specialty ,Colorectal cancer ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Risk Factors ,Republic of Korea ,Biomarkers, Tumor ,Humans ,Medicine ,Radiology, Nuclear Medicine and imaging ,Postoperative Period ,Stage (cooking) ,Survival rate ,Colectomy ,Aged ,Retrospective Studies ,business.industry ,Incidence ,Retrospective cohort study ,General Medicine ,Odds ratio ,Thoracic Neoplasms ,medicine.disease ,Carcinoembryonic Antigen ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,Resection margin ,Abdomen ,Female ,Radiology ,Neoplasm Recurrence, Local ,Colorectal Neoplasms ,Tomography, X-Ray Computed ,business - Abstract
To investigate the incidence of thoracic recurrence and the diagnostic value of chest CT for postoperative surveillance in curatively-resected colorectal cancer (CRC) patients. This retrospective study consisted of 648 CRC patients (M:F, 393:255; mean age, 66.2 years) treated with curative surgery between January 2010 and December 2012. The presence of CRC recurrence over follow-ups was analysed and recurrence-free survival and risk factors of recurrence were assessed using Kaplan–Meier analysis with log-rank test and Cox-regression analysis, respectively. Over a median follow-up of 57 months, thoracic recurrence occurred in 8.0% (52/648) of patients with a median recurrence-free survival rate of 19.5 months. Among the 52 patients with thoracic recurrence, 18 (2.7%) had isolated thoracic recurrence, and only five (0.8%) were diagnosed through chest CT. Risk factors of overall thoracic recurrence included age, positive resection margin, presence of venous invasion, positive pathologic N-class, and presence of abdominal recurrence (odds ratio [OR] = 1.78, 19.691, 2.993, 2.502, and 31.137; p = 0.045, 0.004, 0.001, 0.005, and p < 0.001, respectively). As for isolated thoracic recurrence, serum carcinoembryonic antigen level ≥ 5 ng/mL during postoperative follow-up (OR = 9.112; p < 0.001) was demonstrated to be the only predictive factor. There were no thoracic recurrences in patients with CRC stages 0 and I. In patients with curatively-resected CRCs, routine surveillance using chest CT may be of limited value, particularly in those with CRC stages 0 or I, as recurrence only detectable through chest CT was shown to be rare. • Postoperative thoracic recurrence only detectable through chest CT was shown to be rare. • There were no thoracic recurrences in colorectal cancers stage 0 and I. • Postoperative surveillance chest CT is of limited value in patients with curatively resected colorectal cancers.
- Published
- 2018
40. COVID-19 pneumonia on chest X-rays: Performance of a deep learning-based computer-aided detection system
- Author
-
Hyungjin Kim, Soon Ho Yoon, Hyewon Choi, Chang Min Park, Jin Mo Goo, Ju Gang Nam, Jin Young Kim, Eui Jin Hwang, Jae-Kwang Lim, and Ki Beom Kim
- Subjects
Male ,Viral Diseases ,Critical Care and Emergency Medicine ,Pulmonology ,Radiography ,Health Care Providers ,CAD ,Artificial Gene Amplification and Extension ,Polymerase Chain Reaction ,030218 nuclear medicine & medical imaging ,Diagnostic Radiology ,0302 clinical medicine ,Cohen's kappa ,Medical Conditions ,Medicine and Health Sciences ,Medicine ,030212 general & internal medicine ,Medical Personnel ,Lung ,Tomography ,Virus Testing ,Multidisciplinary ,Radiology and Imaging ,Middle Aged ,Professions ,Infectious Diseases ,Radiographic Image Interpretation, Computer-Assisted ,Female ,Radiography, Thoracic ,Radiology ,Research Article ,medicine.medical_specialty ,Coronavirus disease 2019 (COVID-19) ,Imaging Techniques ,Science ,Neuroimaging ,Research and Analysis Methods ,03 medical and health sciences ,Deep Learning ,Diagnostic Medicine ,Physicians ,Republic of Korea ,Radiologists ,Humans ,Molecular Biology Techniques ,Molecular Biology ,Aged ,Retrospective Studies ,Receiver operating characteristic ,business.industry ,COVID-19 ,Biology and Life Sciences ,Retrospective cohort study ,Covid 19 ,Pneumonia ,Reverse Transcriptase-Polymerase Chain Reaction ,medicine.disease ,Triage ,Computed Axial Tomography ,Health Care ,People and Places ,Population Groupings ,business ,Tomography, X-Ray Computed ,Neuroscience - Abstract
Chest X-rays (CXRs) can help triage for Coronavirus disease (COVID-19) patients in resource-constrained environments, and a computer-aided detection system (CAD) that can identify pneumonia on CXR may help the triage of patients in those environment where expert radiologists are not available. However, the performance of existing CAD for identifying COVID-19 and associated pneumonia on CXRs has been scarcely investigated. In this study, CXRs of patients with and without COVID-19 confirmed by reverse transcriptase polymerase chain reaction (RT-PCR) were retrospectively collected from four and one institution, respectively, and a commercialized, regulatory-approved CAD that can identify various abnormalities including pneumonia was used to analyze each CXR. Performance of the CAD was evaluated using area under the receiver operating characteristic curves (AUCs), with reference standards of the RT-PCR results and the presence of findings of pneumonia on chest CTs obtained within 24 hours from the CXR. For comparison, 5 thoracic radiologists and 5 non-radiologist physicians independently interpreted the CXRs. Afterward, they re-interpreted the CXRs with corresponding CAD results. The performance of CAD (AUCs, 0.714 and 0.790 against RT-PCR and chest CT, respectively hereinafter) were similar with those of thoracic radiologists (AUCs, 0.701 and 0.784), and higher than those of non-radiologist physicians (AUCs, 0.584 and 0.650). Non-radiologist physicians showed significantly improved performance when assisted with the CAD (AUCs, 0.584 to 0.664 and 0.650 to 0.738). In addition, inter-reader agreement among physicians was also improved in the CAD-assisted interpretation (Fleiss’ kappa coefficient, 0.209 to 0.322). In conclusion, radiologist-level performance of the CAD in identifying COVID-19 and associated pneumonia on CXR and enhanced performance of non-radiologist physicians with the CAD assistance suggest that the CAD can support physicians in interpreting CXRs and helping image-based triage of COVID-19 patients in resource-constrained environment.
- Published
- 2021
41. Extension of Coronavirus Disease 2019 on Chest CT and Implications for Chest Radiographic Interpretation
- Author
-
Hyewon Choi, Xiaolong Qi, Soon Ho Yoon, Sang Joon Park, Kyung Hee Lee, Jin Yong Kim, Young Kyung Lee, Hongseok Ko, Ki Hwan Kim, Chang Min Park, Yun-Hyeon Kim, Junqiang Lei, Jung Hee Hong, Hyungjin Kim, Eui Jin Hwang, Seung Jin Yoo, Ju Gang Nam, Chang Hyun Lee, and Jin Mo Goo
- Subjects
Radiology, Nuclear Medicine and imaging ,Erratum - Abstract
To study the extent of pulmonary involvement in coronavirus 19 (COVID-19) with quantitative CT and to assess the impact of disease burden on opacity visibility on chest radiographs.This retrospective study included 20 pairs of CT scans and same-day chest radiographs from 17 patients with COVID-19, along with 20 chest radiographs of controls. All pulmonary opacities were semiautomatically segmented on CT images, producing an anteroposterior projection image to match the corresponding frontal chest radiograph. The quantitative CT lung opacification mass (QCTThe mean QCTQCT
- Published
- 2020
42. Undetected Lung Cancer at Posteroanterior Chest Radiography: Potential Role of a Deep Learning–based Detection Algorithm
- Author
-
Chang Min Park, Da Som Kim, Eui Jin Hwang, Ju Gang Nam, Jin Mo Goo, Hyewon Choi, and Seung-Jin Yoo
- Subjects
musculoskeletal diseases ,Nodule detection ,Lung ,business.industry ,Radiography ,Deep learning ,education ,030204 cardiovascular system & hematology ,medicine.disease ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Text mining ,medicine.anatomical_structure ,Medicine ,Radiology, Nuclear Medicine and imaging ,Artificial intelligence ,business ,Lung cancer ,Algorithm ,Original Research - Abstract
PURPOSE: To evaluate the performance of a deep learning–based algorithm in detecting lung cancers not reported on posteroanterior chest radiographs during routine practice. MATERIALS AND METHODS: The retrospective test dataset included 168 posteroanterior chest radiographs acquired between March 2017 and December 2018 (168 patients; mean age, 71.9 years ± 9.5 [standard deviation]; age range, 42–91 years) with 187 lung cancers (mean size, 2.3 cm ± 1.2) undetected during initial clinical evaluation, and 50 normal chest radiographs. CT served as the reference standard for ground truth. Four thoracic radiologists independently reevaluated the chest radiographs for lung nodules both without and with the aid of the algorithm. The performances of the algorithm and the radiologists were evaluated and compared on a per–chest radiograph basis and a per-lesion basis, according to the area under the receiver operating characteristic curve (AUROC) and area under the jackknife free-response ROC curve (AUFROC). RESULTS: The algorithm showed excellent diagnostic performances both in terms of per-chest radiograph classification (AUROC, 0.899) and per-lesion localization (AUFROC, 0.744); both of these values were significantly higher than those of the radiologists (AUROC, 0.634–0.663; AUFROC, 0.619–0.651; P < .001 for all). The algorithm also demonstrated higher sensitivity (69.6% [117 of 168] vs 47.0% [316 of 672]; P < .001) and specificity (94.0% [47 of 50] vs 78.0% [156 of 200]; P = .01). When assisted by the algorithm, the radiologists’ AUROC (0.634–0.663 vs 0.685–0.724; P < 0.01 for all) and pooled AUFROC (0.636 vs 0.688; P = .03) substantially improved. The false-positive rate of the algorithm, that is, the total number of false-positive nodules divided by the total number of chest radiographs, was similar to that of pooled radiologists (21.1% [46 of 218] vs 19.0% [166 of 872]; P > .05). CONCLUSION: A deep learning–based nodule detection algorithm showed excellent detection performance of lung cancers that were not reported on chest radiographs during routine practice and significantly reduced reading errors when used as a second reader. Supplemental material is available for this article. © RSNA, 2020 See also commentary by White in this issue.
- Published
- 2020
43. Clinical Implications of Size of Cavities in Patients With Nontuberculous Mycobacterial Pulmonary Disease: A Single-Center Cohort Study
- Author
-
Jinwoo Lee, Nakwon Kwak, Eui Jin Hwang, Sun Mi Choi, Sung A. Kim, Hye Rin Kang, Jae-Joon Yim, and Chang Hoon Lee
- Subjects
nontuberculous mycobacteria ,medicine.medical_specialty ,cavity ,Single Center ,Logistic regression ,Major Articles ,03 medical and health sciences ,0302 clinical medicine ,Internal medicine ,medicine ,In patient ,030212 general & internal medicine ,biology ,business.industry ,Hazard ratio ,Odds ratio ,bacterial infections and mycoses ,biology.organism_classification ,mortality ,AcademicSubjects/MED00290 ,Infectious Diseases ,030228 respiratory system ,Oncology ,Cohort ,outcome ,Nontuberculous mycobacteria ,business ,Cohort study - Abstract
Background The presence of cavities is associated with unfavorable prognosis in patients with nontuberculous mycobacterial pulmonary disease (NTM-PD). However, little is known about the characteristics of such cavities and their impact on clinical outcomes. The aim of this study was to investigate the size of cavities and their implications on treatment outcomes and mortality in patients with NTM-PD. Methods We included patients diagnosed with NTM-PD at Seoul National University Hospital between January 1, 2007, and December 31, 2018. We measured the size of cavities on chest computed tomography scans performed at the time of diagnosis and used multivariable logistic regression and Cox proportional hazards regression analysis to investigate the impact of these measurements on treatment outcomes and mortality. Results The study cohort comprised 421 patients (noncavitary, n = 329; cavitary, n = 92) with NTM-PD. During a median follow-up period of 49 months, 118 (35.9%) of the 329 patients with noncavitary and 64 (69.6%) of the 92 patients with cavitary NTM-PD received antibiotic treatment. Cavities >2 cm were associated with worse treatment outcomes (adjusted odds ratio, 0.41; 95% CI, 0.17–0.96) and higher mortality (adjusted hazard ratio, 2.52; 95% CI, 1.09–5.84), while there was no difference in treatment outcomes or mortality between patients with cavities ≤2 cm and patients with noncavitary NTM-PD. Conclusions Clinical outcomes are different according to the size of cavities in patients with cavitary NTM-PD; thus, the measurement of the size of cavities could help in making clinical decisions.
- Published
- 2020
44. Automatic prediction of left cardiac chamber enlargement from chest radiographs using convolutional neural network
- Author
-
Ju Gang, Nam, Jinwook, Kim, Keonwoo, Noh, Hyewon, Choi, Da Som, Kim, Seung-Jin, Yoo, Hyun-Lim, Yang, Eui Jin, Hwang, Jin Mo, Goo, Eun-Ah, Park, Hye Young, Sun, Min-Soo, Kim, and Chang Min, Park
- Subjects
Radiography ,Deep Learning ,Humans ,Radiography, Thoracic ,Neural Networks, Computer ,Algorithms - Abstract
To develop deep learning-based cardiac chamber enlargement-detection algorithms for left atrial (DLCE-LAE) and ventricular enlargement (DLCE-LVE), on chest radiographs METHODS: For training and internal validation of DLCE-LAE and -LVE, 5,045 chest radiographs (CRs; 2,463 normal and 2,393 LAE) and 1,012 CRs (456 normal and 456 LVE) matched with the same-day echocardiography were collected, respectively. External validation was performed using 107 temporally independent CRs. Reader performance test was conducted using the external validation dataset by five cardiothoracic radiologists without and with the results of DLCE. Classification performance of DLCE was evaluated and compared with those of the readers and conventional radiographic features, including cardiothoracic ratio, carinal angle, and double contour. In addition, DLCE-LAE was tested on 5,277 CRs from a healthcare screening program cohort.DLCE-LAE showed areas under the receiver operating characteristics curve (AUROCs) of 0.858 on external validation. On reader performance test, DLCE-LAE showed better results than pooled radiologists (AUROC 0.858 vs. 0.651; p.001) and significantly increased their performance when used as a second reader (AUROC 0.651 vs. 0.722; p.001). DLCE-LAE also showed a significantly higher AUROC than conventional radiographic findings (AUROC 0.858 vs. 0.535-0.706; all ps.01). In the healthcare screening cohort, DLCE-LAE successfully detected 71.0% (142/200) CRs with moderate-to-severe LAE (93.5% [29/31] of severe cases), while yielding 11.8% (492/4,184) false-positive rate. DLCE-LVE showed AUROCs of 0.966 and 0.594 on internal and external validation, respectively.DLCE-LAE outperformed and improved cardiothoracic radiologists' performance in detecting LAE and showed promise in screening individuals with moderate-to-severe LAE in a healthcare screening cohort.• Our deep learning algorithm outperformed cardiothoracic radiologists in detecting left atrial enlargement on chest radiographs. • Cardiothoracic radiologists improved their performance in detecting left atrial enlargement when aided by the algorithm. • On a healthcare-screening cohort, our algorithm detected 71.0% (142/200) radiographs with moderate-to-severe left atrial enlargement while yielding 11.8% (492/4,184) false-positive rate.
- Published
- 2020
45. Optimum diameter threshold for lung nodules at baseline lung cancer screening with low-dose chest CT: exploration of results from the Korean Lung Cancer Screening Project
- Author
-
Eui Jin, Hwang, Jin Mo, Goo, Hyae Young, Kim, Jaeyoun, Yi, and Yeol, Kim
- Subjects
Male ,Delayed Diagnosis ,Lung Neoplasms ,Republic of Korea ,Humans ,Middle Aged ,Tomography, X-Ray Computed ,Lung ,Early Detection of Cancer - Abstract
To explore the optimum diameter threshold for solid nodules to define positive results at baseline screening low-dose CT (LDCT) and to compare two-dimensional and volumetric measurement of lung nodules for the diagnosis of lung cancers.We included consecutive participants from the Korean Lung Cancer Screening project between 2017 and 2018. The average transverse diameter and effective diameter (diameter of a sphere with the same volume) of lung nodules were measured by semi-automated segmentation. Diagnostic performances for lung cancers diagnosed within 1 year after LDCT were evaluated using area under receiver-operating characteristic curves (AUCs), sensitivities, and specificities, with diameter thresholds for solid nodules ranging from 6 to 10 mm. The reduction of unnecessary follow-up LDCTs and the diagnostic delay of lung cancers were estimated for each threshold.Fifty-two lung cancers were diagnosed among 10,424 (10,141 men; median age 62 years) participants within 1 year after LDCT. Average transverse (0.980) and effective diameters (0.981) showed similar AUCs (p = .739). Elevating the average transverse diameter threshold from 6 to 9 mm resulted in a significantly increased specificity (91.7 to 96.7%, p.001), a modest reduction in sensitivity (96.2 to 94.2%, p = .317), a 60.2% estimated reduction of unnecessary follow-up LDCTs, and a diagnostic delay in 1.9% of lung cancers. Elevating the threshold to 10 mm led to a significant reduction in sensitivity (86.5%, p = .025).Elevating the diameter threshold for solid nodules from 6 to 9 mm may lead to a substantial reduction in unnecessary follow-up LDCTs with a small proportion of diagnostic delay of lung cancers.• Elevation of the diameter threshold for solid nodules from 6 to 9 mm can substantially reduce unnecessary follow-up LDCTs with a small proportion of diagnostic delay of lung cancers. • The average transverse and effective diameters of lung nodules showed similar performances for the prediction of a lung cancer diagnosis.
- Published
- 2020
46. Prediction of visceral pleural invasion in lung cancer on CT: deep learning model achieves a radiologist-level performance with adaptive sensitivity and specificity to clinical needs
- Author
-
Hyewon, Choi, Hyungjin, Kim, Wonju, Hong, Jongsoo, Park, Eui Jin, Hwang, Chang Min, Park, Young Tae, Kim, and Jin Mo, Goo
- Subjects
Deep Learning ,Lung Neoplasms ,Radiologists ,Humans ,Tomography, X-Ray Computed ,Sensitivity and Specificity ,Retrospective Studies - Abstract
To develop and validate a preoperative CT-based deep learning model for the prediction of visceral pleural invasion (VPI) in early-stage lung cancer.In this retrospective study, dataset 1 (for training, tuning, and internal validation) included 676 patients with clinical stage IA lung adenocarcinomas resected between 2009 and 2015. Dataset 2 (for temporal validation) included 141 patients with clinical stage I adenocarcinomas resected between 2017 and 2018. A CT-based deep learning model was developed for the prediction of VPI and validated in terms of discrimination and calibration. An observer performance study and a multivariable regression analysis were performed.The area under the receiver operating characteristic curve (AUC) of the model was 0.75 (95% CI, 0.67-0.84), which was comparable to those of board-certified radiologists (AUC, 0.73-0.79; all p 0.05). The model had a higher standardized partial AUC for a specificity range of 90 to 100% than the radiologists (all p 0.05). The high sensitivity cutoff (0.245) yielded a sensitivity of 93.8% and a specificity of 31.2%, and the high specificity cutoff (0.448) resulted in a sensitivity of 47.9% and a specificity of 86.0%. Two of the three radiologists provided highly sensitive (93.8% and 97.9%) but not specific (48.4% and 40.9%) diagnoses. The model showed good calibration (p 0.05), and its output was an independent predictor for VPI (adjusted odds ratio, 1.07; 95% CI, 1.03-1.11; p 0.001).The deep learning model demonstrated a radiologist-level performance. The model could achieve either highly sensitive or highly specific diagnoses depending on clinical needs.• The preoperative CT-based deep learning model demonstrated an expert-level diagnostic performance for the presence of visceral pleural invasion in early-stage lung cancer. • Radiologists had a tendency toward highly sensitive, but not specific diagnoses for the visceral pleural invasion.
- Published
- 2020
47. Meteorin-like protein (METRNL)/IL-41 improves LPS-induced inflammatory responses via AMPK or PPARδ-mediated signaling pathways
- Author
-
Do Hyeon Pyun, A. M. Abd El-Aty, Ji Hoon Jeong, Eui Jin Hwang, Yong Kyoo Shin, Tae Woo Jung, Eon Sub Park, Tae Jin Kim, and Hyunjung Lee
- Subjects
Lipopolysaccharides ,Lipopolysaccharide ,Inflammation ,Apoptosis ,AMP-Activated Protein Kinases ,Monocytes ,03 medical and health sciences ,chemistry.chemical_compound ,0302 clinical medicine ,Adipokines ,medicine ,Human Umbilical Vein Endothelial Cells ,Humans ,030212 general & internal medicine ,PPAR delta ,Phosphorylation ,Cell adhesion ,Chemokine CCL2 ,Cell adhesion molecule ,business.industry ,Tumor Necrosis Factor-alpha ,AMPK ,General Medicine ,Cell biology ,chemistry ,030220 oncology & carcinogenesis ,Tumor necrosis factor alpha ,medicine.symptom ,Signal transduction ,business - Abstract
Purpose Meteorin-like protein (METRNL) (also known as IL-41), recently identified as a myokine, is released in response to muscle contraction. It improves the skeletal muscle insulin sensitivity through exerting a beneficial anti-inflammatory effect. However, no independent studies have been published to verify the effects of METRNL on human umbilical vein endothelial cells (HUVECs) and THP-1 human monocytes. Materials and methods The levels of NFκB and IκB phosphorylation as well as the expression of adhesion molecules were assessed by Western blotting analysis. Cell adhesion assay demonstrated the interactions between HUVEC and THP-1 cells. We used enzyme-linked immunosorbent assay (ELISA) to measure the levels of TNFα and MCP-1 in culture medium. Results Treatment with METRNL suppressed the secretion of TNFα and MCP-1 as well as NFκB and IκB phosphorylation and inflammatory markers in lipopolysaccharide (LPS)-treated HUVECs and THP-1 cells. Furthermore, treatment with METRNL ameliorated LPS-induced attachment of THP-1 monocytes to HUVECs via inhibition of adhesion molecule expression and apoptosis. Treatment of HUVEC and THP-1 cells with METRNL enhanced AMPK phosphorylation and PPARδ expression in a dose-dependent manner. Small interference (si) RNA-mediated suppression of AMPK or PPARδ restored all these changes. Conclusions It has therefore been shown that METRNL ameliorates inflammatory responses through AMPK and PPARδ-dependent pathways in LPS-treated HUVEC. In sum, the current study may suggest the suppressive potential of METRNL against endothelial inflammation.
- Published
- 2020
48. Variability in interpretation of low-dose chest CT using computerized assessment in a nationwide lung cancer screening program: comparison of prospective reading at individual institutions and retrospective central reading
- Author
-
Eui Jin, Hwang, Jin Mo, Goo, Hyae Young, Kim, Soon Ho, Yoon, Gong Yong, Jin, Jaeyoun, Yi, and Yeol, Kim
- Subjects
Lung Neoplasms ,Belgium ,Reading ,Humans ,Radiographic Image Interpretation, Computer-Assisted ,Prospective Studies ,Tomography, X-Ray Computed ,Early Detection of Cancer ,Retrospective Studies - Abstract
To evaluate the degree of variability in computer-assisted interpretation of low-dose chest CTs (LDCTs) among radiologists in a nationwide lung cancer screening (LCS) program, through comparison with a retrospective interpretation from a central laboratory.Consecutive baseline LDCTs (n = 3353) from a nationwide LCS program were investigated. In the institutional reading, 20 radiologists in 14 institutions interpreted LDCTs using computer-aided detection and semi-automated segmentation systems for lung nodules. In the retrospective central review, a single radiologist re-interpreted all LDCTs using the same system, recording any non-calcified nodules ≥ 3 mm without arbitrary rejection of semi-automated segmentation to minimize the intervention of radiologist's discretion. Positive results (requiring additional follow-up LDCTs or diagnostic procedures) were initially classified by the lung CT screening reporting and data system (Lung-RADS) during the interpretation, while the classifications based on the volumetric criteria from the Dutch-Belgian lung cancer screening trial (NELSON) were retrospectively applied. Variabilities in positive rates were assessed with coefficients of variation (CVs).In the institutional reading, positive rates by the Lung-RADS ranged from 7.5 to 43.3%, and those by the NELSON ranged from 11.4 to 45.0% across radiologists. The central review exhibited higher positive rates by Lung-RADS (20.0% vs. 27.3%; p .001) and the NELSON (23.1% vs. 37.0%; p .001), and lower inter-institution variability (CV, 0.30 vs. 0.12, p = .003 by Lung-RADS; CV, 0.25 vs. 0.12, p = .014 by the NELSON) compared to the institutional reading.Considerable inter-institution variability in the interpretation of LCS results is caused by different usage of the computer-assisted system.• Considerable variability existed in the interpretation of screening LDCT among radiologists partly from the different usage of the computerized system. • A retrospective reading of low-dose chest CTs in the central laboratory resulted in reduced variability but an increased positive rate.
- Published
- 2020
49. Implementation of the cloud-based computerized interpretation system in a nationwide lung cancer screening with low-dose CT: comparison with the conventional reading system
- Author
-
Eui Jin, Hwang, Jin Mo, Goo, Hyae Young, Kim, Jaeyoun, Yi, Soon Ho, Yoon, and Yeol, Kim
- Subjects
Lung Neoplasms ,Reading ,Humans ,Radiographic Image Interpretation, Computer-Assisted ,Solitary Pulmonary Nodule ,Cloud Computing ,Middle Aged ,Tomography, X-Ray Computed ,Sensitivity and Specificity ,Early Detection of Cancer - Abstract
We aimed to compare the CT interpretation before and after the implementation of a computerized system for lung nodule detection and measurements in a nationwide lung cancer screening program.Our screening program started in April 2017, with 14 participating institutions. Initially, all CTs were interpreted using interpretation systems in each institution and manual nodule measurement (conventional system). A cloud-based CT interpretation system, equipped with semi-automated measurement and CAD (computer-aided detection) for lung nodules (cloud-based system), was implemented during the project. Positive rates and performances for lung cancer diagnosis based on the Lung-RADS version 1.0 were compared between the conventional and cloud-based systems.A total of 1821 (M:F = 1782:39, mean age 62.7 years, 16 confirmed lung cancers) and 4666 participants (M:F = 4560:106, mean age 62.8 years, 31 confirmed lung cancers) were included in the conventional and cloud-based systems, respectively. Significantly more nodules were detected in the cloud-based system (0.76 vs. 1.07 nodule/participant, p .001). Positive rate did not differ significantly between the two systems (9.9% vs. 11.0%, p = .211), while their variability across institutions was significantly lower in the cloud-based system (coefficients of variability, 0.519 vs. 0.311, p = .018). The Lung-RADS-based sensitivity (93.8% vs. 93.5%, p = .979) and specificity (90.9% vs. 89.6%, p = .132) did not differ significantly between the two systems.Implementation of CAD and semi-automated measurement for lung nodules in a nationwide lung cancer screening program resulted in increased number of detected nodules and reduced variability in positive rates across institutions.• Computer-aided CT reading detected more lung nodules than radiologists alone in lung cancer screening. • Positive rate in lung cancer screening did not change with computer-aided reading. • Computer-aided CT reading reduced inter-institutional variability in lung cancer screening.
- Published
- 2020
50. Growth and Clinical Impact of 6-mm or Larger Subsolid Nodules after 5 Years of Stability at Chest CT
- Author
-
Woo Hyeon Lim, Jin Mo Goo, Jung Hee Hong, Hyungjin Kim, Ju Gang Nam, Eui Jin Hwang, Jong Hyuk Lee, and Chang Min Park
- Subjects
Male ,Lung Neoplasms ,Radiography ,Chest ct ,030218 nuclear medicine & medical imaging ,Metastasis ,03 medical and health sciences ,0302 clinical medicine ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,Stage (cooking) ,Lung cancer ,Neoplasm Staging ,Retrospective Studies ,Lung ,business.industry ,Incidence (epidemiology) ,Retrospective cohort study ,Middle Aged ,medicine.disease ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,Multiple Pulmonary Nodules ,Female ,Radiography, Thoracic ,business ,Nuclear medicine ,Tomography, X-Ray Computed ,Precancerous Conditions - Abstract
Background It remains unclear whether 5 years of stability is sufficient to establish the benign behavior of subsolid nodules (SSNs) of the lung. There are no guidelines for the length of follow-up needed for these SSNs. Purpose To investigate the incidence of interval growth of pulmonary SSNs 6 mm or greater in diameter after 5 years of stability and their clinical outcome. Materials and Methods This retrospective study assessed SSNs 6 mm or greater that were stable for 5 years after detection (January 2002 to December 2018). The incidence of interval growth after 5 years of stability and the clinical and radiologic features of these SSNs were investigated. Clinical stage shifts of growing SSNs, presence of metastasis, and overall survival were assessed during the follow-up period. Subgroup analysis was performed in patients with nonenhanced thin-section (section thickness ≤1.5 mm) CT for interval growth after 5 years of stability. Results A total of 235 SSNs in 235 patients (mean age, 64 years ± 10 [standard deviation]; 132 women) were evaluated. There were 212 pure ground-glass nodules and 24 part-solid nodules. During follow-up (median, 112 months; range, 84-208 months), five of the 235 SSNs (2%; three primary ground-glass nodules and two part-solid nodules) showed interval growth. Three of these five growing SSNs were 10 mm or greater. Three of the five SSNs with interval growth had clinical stage shifts after growth (from Tis [in situ] to T1mi [minimally invasive] in one lesion; from T1mi to T1a in two lesions). There were no deaths or metastases from lung cancer during follow-up. Of 160 SSNs imaged with section thickness of 1.5 mm or less, two (1%) grew; both lesions were 10 mm or greater. Conclusion Only 2% of subsolid pulmonary nodules greater than or equal to 6 mm that had been stable for 5 years showed subsequent growth. At median follow-up of 9 years (after the initial 5-year period of stability), growth of those lung nodules had no clinical effect. © RSNA, 2020 See also the editorial by Naidich and Azour in this issue.
- Published
- 2020
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.