Search

Artificial intelligence (AI) technology is actively being applied for the interpretation of medical imaging, such as chest X-rays. AI-based software medical devices, which automatically detect various types of abnormal findings in chest X-ray images to assist physicians in their interpretation, are actively being commercialized and clinically implemented in Korea. Several important issues need to be considered for AI-based detection assistant tools to be applied in clinical practice: the evaluation of performance and efficacy prior to implementation; the determination of the target application, range, and method of delivering results; and monitoring after implementation and legal liability issues. Appropriate decision making regarding these devices based on the situation in each institution is necessary. Radiologists must be engaged as medical assessment experts using the software for these devices as well as in medical image interpretation to ensure the safe and efficient implementation and operation of AIbased detection assistant tools.

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.

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

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.

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.

ObjectiveTo determine the optimum definition of growth for indeterminate pulmonary nodules detected in lung cancer screening.Materials and methodsIndividuals 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.ResultsAltogether, 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.ConclusionGrowth evaluation of screening-detected indeterminate nodules with volumetric measurement exhibited higher sensitivity but lower specificity compared to diametric measurements.

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.

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.

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.

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