Search

Background COPD-associated mortality was examined using a novel approach of phenotyping COPD based on computed tomography (CT)-emphysema index from quantitative CT (QCT) and post-bronchodilator (BD) forced expiratory volume in 1 second (FEV1) in a local Malaysian cohort. Patients and methods Prospectively collected data of 112 eligible COPD subjects (mean age, 67 years; male, 93%; mean post-BD FEV1, 45.7%) was available for mortality analysis. Median follow-up time was 1,000 days (range, 60-1,400). QCT and clinicodemographic data were collected at study entry. Based on CT-emphysema index and post-BD FEV1% predicted, subjects were categorized into "emphysema-dominant," "airway-dominant," "mild mixed airway-emphysema," and "severe mixed airway-emphysema" diseases. Results Sixteen patients (14.2%) died of COPD-associated causes. There were 29 (25.9%) "mild mixed," 23 (20.5%) "airway-dominant," 15 (13.4%) "emphysema-dominant," and 45 (40.2%) "severe mixed" cases. "Mild mixed" disease was proportionately more in Global Initiative for Chronic Obstructive Lung Disease (GOLD) Group A, while "severe mixed" disease was proportionately more in GOLD Groups B and D. Kaplan-Meier survival estimates showed increased mortality risk with "severe mixed" disease (log rank test, p=0.03) but not with GOLD groups (p=0.08). Univariate Cox proportionate hazard analysis showed that age, body mass index, long-term oxygen therapy, FEV1, forced volume capacity, COPD Assessment Test score, modified Medical Research Council score, St Georges' Respiratory Questionnaire score, CT-emphysema index, and "severe mixed" disease (vs "mild mixed" disease) were associated with mortality. Multivariate Cox analysis showed that age, body mass index, and COPD Assessment Test score remain independently associated with mortality. Conclusion "Severe mixed airway-emphysema" disease may predict COPD-associated mortality. Age, body mass index, and COPD Assessment Test score remain as key mortality risk factors in our cohort.

To investigate whether radiomics on iodine overlay maps from dual-energy computed tomography (DECT) can predict survival outcomes in patients with resectable lung cancer. Ninety-three lung cancer patients eligible for curative surgery were examined with DECT at the time of diagnosis. The median follow-up was 60.4 months. Radiomic features of the entire primary tumour were extracted from iodine overlay maps generated by DECT. A Cox proportional hazards regression model was used to determine independent predictors of overall survival (OS) and disease-free survival (DFS), respectively. Forty-two patients (45.2%) had disease recurrence and 39 patients (41.9%) died during the follow-up period. The mean DFS was 49.8 months and OS was 55.2 months. Univariate analysis revealed that significant predictors of both OS and DFS were stage and radiomic parameters, including histogram energy, histogram entropy, grey-level co-occurrence matrix (GLCM) angular second moment, GLCM entropy and homogeneity. The multivariate analysis identified stage and entropy as independent risk factors predicting both OS (stage, hazard ratio (HR) = 2.020 [95% CI 1.014–4.026], p = 0.046; entropy, HR = 1.543 [95% CI 1.069–2.228], p = 0.021) and DFS (stage, HR = 2.132 [95% CI 1.060–4.287], p = 0.034; entropy, HR = 1.497 [95% CI 1.031–2.173], p = 0.034). The C-index showed that adding entropy improved prediction of OS compared to stage only (0.720 and 0.667, respectively; p = 0.048). Radiomic features extracted from iodine overlay map reflecting heterogeneity of tumour perfusion can add prognostic information for patients with resectable lung cancer. • Radiomic feature (histogram entropy) from DECT iodine overlay maps was an independent risk factor predicting both overall survival and disease-free survival. • Adding histogram entropy to clinical stage improved prediction of overall survival compared to stage only (0.720 and 0.667, respectively; p = 0.048). • DECT can be a good option for comprehensive pre-operative evaluation in cases of resectable lung cancer.

Since the clinical introduction of magnetic resonance imaging (MRI), the chest has been one of its most challenging applications, and many physicists and radiologists have tried since the 1980s to use MR for assessment of different lung diseases as well as mediastinal and pleural diseases. Since then, however, technical advances in sequencing, scanners, and coils, adaptation of parallel imaging techniques, utilization of contrast media, and development of postprocessing tools have been reported by many basic and clinical researchers. As a result, state-of-the-art thoracic MRI is now substituted for traditional imaging techniques and/or plays a complementary role in the management of patients with various chest diseases, and especially in the detection of pulmonary nodules and in thoracic oncology. In addition, MRI has continued to be developed to help overcome the limitations of computed tomography (CT) and nuclear medicine examinations. It can currently provide not only morphological, but also functional, physiological, pathophysiological, and molecular information at 1.5T with a gradual shift from 1.5T to 3T MR systems. In this review, we focus on these recent advances in MRI for pulmonary nodule detection and pulmonary nodule and mass evaluation by using noncontrast-enhanced and contrast-enhanced techniques as well as new molecular imaging methods such as chemical exchange saturation transfer imaging for a comparison with other modalities such as single or multidetector row CT, 18F-fluoro-2-deoxyglucose positron emission tomography (FDG-PET), and/or PET/CT. Level of evidence 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1437-1458.

To compare pneumonic-type invasive mucinous adenocarcinoma (pIMA) confined to a single lobe with clinical T2, T3, and T4 stage lung cancer without pathological node metastasis regarding survival after curative surgery and to identify prognostic factors for pIMA.From January 2010 to December 2017, 41 patients (15 male; mean age ± standard deviation, 66.0 ± 9.9 years) who had pIMA confined to a single lobe on computed tomography (CT) and underwent curative surgery were identified in two tertiary hospitals. Three hundred and thirteen patients (222 male; 66.3 ± 9.4 years) who had non-small cell lung cancer (NSCLC) without pathological node metastasis and underwent curative surgery in one participating institution formed a reference group. Relapse-free survival (RFS) and overall survival (OS) were calculated using the Kaplan-Meier method. Cox proportional hazard regression analysis was performed to identify factors associated with the survival of patients with pIMA.The 5-year RFS and OS rates in patients with pIMA were 33.1% and 56.0%, respectively, compared with 74.3% and 91%, 64.3% and 71.8%, and 46.9% and 49.5% for patients with clinical stage T2, T3, and T4 NSCLC in the reference group, respectively. The RFS of patients with pIMA was comparable to that of patients with clinical stage T4 NSCLC and significantly worse than that of patients with clinical stage T3 NSCLC (The RFS of patients with pIMA was comparable to that of patients with clinical stage T4 lung cancer. Separate nodules on CT were associated with poor RFS and OS in patients with pIMA.

This study aimed to compare the prognostic performance of clinical T staging based on axial, multiplanar, and 3-dimensional measurement on CT with that of pathological T staging in patients with non-small cell lung cancer.Patients with surgically resected lung cancer without pathological node metastasis between June 2010 and December 2017 were retrospectively included. Clinical T stages were determined based on the maximal tumor size on axial, multiplanar (axial, coronal, and sagittal) images and 3-dimensional tumor mask. The prognostic performances of clinical and pathological T staging for disease-free survival (DFS) were compared using the concordance indices (C-indices).A total of 544 patients (64.7 ± 9.7 years, 352 men) were included; 160 patients (29.4%) experienced events including 29 (5.3%) who expired. The median DFS was 44.1 months. The mean tumor size on axial, multiplanar images, 3-dimensional tumor mask, and pathology was 30.8 ± 17.3, 33.9 ± 19.4, 39.2 ± 21.4, and 33.4 ± 18.0 mm, respectively. Clinical staging based on multiplanar measurement showed a higher agreement (67.5% [367/544]) with pathological staging than axial (60.5% [329/544]) and 3-dimensional measurement (50.9% [277/544]) based staging did (p = .0005 and.0001, respectively). The adjusted C-indices of axial, multiplanar, 3-dimensional, and pathological tumor stages were 0.66 (95% confidence interval [CI]: 0.66-0.67), 0.66 (95% CI: 0.66-0.66), 0.67 (95% CI: 0.67-0.67), and 0.67 (95% CI: 0.66-0.67), respectively (p .05).The prognostic performances of tumor staging according to size measurement methods were not significantly different. Multiplanar measurement may be preferable for clinical staging considering its highest agreement with pathological staging.

A biopsy needle with electrical impedance sensor array based on stainless steel microelectrodes (EIS needle) was developed for real-time four electrode measurement and multi-spot sensing of tissues during the biopsy process. The sensor performance was characterized by using saline solutions with various concentrations, which proved accurate, stable and reliable electrical impedance measurement. The capability of impedance-based tissue sensing was verified by the conductivity measurement of agarose hydrogel based phantom mimicking cancer tissue. Furthermore, multi-spot impedance sensing during needle insertion was demonstrated using porcine meat with muscle and fat layers, which exhibited a clear discrimination between different types of tissues. Also, the electrical impedance difference between normal and fatty livers of mouse model was measured by the EIS needle. We could successfully demonstrate that the EIS needle can provide localized and accurate characterization of biological tissues at the needle tip.

This paper describes the accurate deformable registration method for image-guided lung interventions, including lung nodule biopsy and radiofrequency ablation of lung tumours. A level set motion assisted deformable registration method for computed tomography (CT) images was proposed and its accuracy and speed were compared with those of other conventional methods. Fifteen 3D CT images obtained from lung biopsy patients were scanned. Each scan consisted of diagnostic and preoperative CT images. Each deformable registration method was initially evaluated with a landmark-based affine registration algorithm. Various deformable registration methods such as level set motion, demons, diffeomorphic demons, and b-spline were compared. Visual assessment by two expert thoracic radiologists using five scales showed an average visual score of 3.2 for level set motion deformable registration, whereas scores were below 3 for other deformable registration methods. In the qualitative assessment, the level set motion algorithm showed better results than those obtained with other deformable registration methods. A level set motion based deformable registration algorithm was effective for registering diagnostic and preoperative volumetric CT images for image-guided lung intervention.

To assess the volume doubling time (VDT) of lung cancers in IIP compared with COPD. A total of 61 patients (32 with IIP and 29 with COPD) were identified. A radiologist performed three-dimensional manual segmentation for lung cancers. VDTs were calculated and compared between two groups. Logistic regression was performed to identify factors associated with rapid tumour growth (VDT < 90 days). The median VDT of lung cancers in IIP (78.2 days) was significantly shorter than that in COPD (126.1 days; p=0.004). Squamous cell carcinoma (SqCC) was the most frequent subtype, followed by small cell lung cancer (SCLC) in IIP. In COPD, SqCC was the most frequent subtype, followed by adenocarcinoma. Rapid tumour growth was observed in 20 cancers from IIP, and in nine cancers from COPD (p=0.021). SCLC was significantly correlated with rapid tumour growth (p=0.038). Multivariate analysis revealed that the presence of IIP was the single independent predictor of rapid tumour growth (p = 0.016; odds ratio, 3.7). Lung cancers in IIP showed more rapid growth, with median VDT < 90 days. Therefore, a shorter follow-up interval (

To retrospectively investigate whether the baseline extent and 1-year change in regional disease patterns on CT can predict survival of patients with idiopathic pulmonary fibrosis (IPF). A total of 144 IPF patients with CT scans at the time of diagnosis and 1 year later were included. The extents of five regional disease patterns were quantified using an in-house texture-based automated system. The fibrosis score was defined as the sum of the extent of honeycombing and reticular opacity. The Cox proportional hazard model was used to determine the independent predictors of survival. A total of 106 patients (73.6%) died during the follow-up period. Univariate analysis revealed that age, baseline forced vital capacity, total lung capacity, diffusing capacity of the lung for carbon monoxide, six-minute walk distance, desaturation, honeycombing, reticular opacity, fibrosis score, and interval changes in honeycombing and fibrosis score were significantly associated with survival. Multivariate analysis revealed that age, desaturation, fibrosis score and interval change in fibrosis score were significant independent predictors of survival (p = 0.003

Background and objective Matrix degradation is a key feature of chronic obstructive pulmonary disease (COPD). Desmosine and isodesmosine (desmosines) are excreted in urine following matrix degradation. The main purpose of this study was to investigate the association between computed tomography (CT) emphysema indices and urinary desmosines in patients with COPD. Methods A total of 152 subjects were selected from the Korean Obstructive Lung Disease cohort. Their urine samples were assayed for desmosines using liquid chromatography-tandem mass spectrometry (LC-MS/MS) methods. The cohort was divided into emphysema-dominant (n = 80) and non-emphysema dominant- (n = 72) groups according to the CT emphysema index. Results The level of urinary desmosines was significantly higher in the emphysema-dominant group. Significant differences were also observed between the two groups for body mass index and lung function. Multivariate analysis indicated that a high level of urinary desmosines was a significant independent predictor of emphysema (relative risk: 2.6; 95% CI: 1.11–6.09; P = 0.028). The percentage of frequent exacerbators was significantly higher in the high urinary desmosine group in the first year of follow-up (P = 0.041). The mean number of exacerbations was higher in the high urinary desmosine group, although this difference was not statistically significant (P = 0.067). The changes in emphysema index did not differ between the two urinary desmosine groups over 3 years of follow-up. Conclusion This study indicates that the level of urinary desmosines measured by LC-MS/MS methods is associated with the CT emphysema index. Urinary desmosine can be a useful predictor in identifying frequent exacerbators.

Objective To retrospectively investigate whether prone CT improves identification of honeycombing and classification of UIP patterns in terms of interobserver agreement and accuracy using pathological results as a reference standard. Materials and methods Institutional review board approval with waiver of patients’ informed consent requirement was obtained. HRCTs of 86 patients with pathologically proven UIP, NSIP and chronic HP between January 2011 and April 2015 were evaluated by 8 observers. Observers were asked to review supine only set and supine and prone combined set and determine the presence of honeycombing and UIP classification (UIP, possible UIP, inconsistent with UIP). The diagnosis was regarded as correct when UIP pattern on CT corresponded to pathological UIP. Results Interobserver agreement of honeycombing identification among radiologists was only fair on the supine and combined set (weighted κ = 0.31 and 0.34). Additional review of prone images demonstrated a significant improvement in interobserver agreement (weighted κ ) of UIP classification from 0.25 to 0.33. Prone CT conferred a significant improvement in interobserver agreement of UIP classification for trainee radiologists (from 0.10 to 0.34) while no improvement was found for board-certified radiologists (from 0.35 to 0.31). There were no significant differences in the accuracy of UIP pattern with reference to pathological results between the supine and combined set (78.8% (145/184) and 81.3% (179/220), P = 0.612). Conclusion Additional review of prone CT can improve overall interobserver agreement of UIP classification among radiologists with variable experiences, particularly for less experienced radiologists, while no improvement was found in honeycombing identification.

[No Abstract Available]

OBJECTIVE To assess the regional ventilation in patients with asthma-chronic obstructive pulmonary disease (COPD) overlap syndrome (ACOS) using xenon-ventilation dual-energy CT (DECT), and to compare it to that in patients with COPD. MATERIALS AND METHODS Twenty-one patients with ACOS and 46 patients with COPD underwent xenon-ventilation DECT. The ventilation abnormalities were visually determined to be 1) peripheral wedge/diffuse defect, 2) diffuse heterogeneous defect, 3) lobar/segmental/subsegmental defect, and 4) no defect on xenon-ventilation maps. Emphysema index (EI), airway wall thickness (Pi10), and mean ventilation values in the whole lung, peripheral lung, and central lung areas were quantified and compared between the two groups using the Student's t test. RESULTS Most patients with ACOS showed the peripheral wedge/diffuse defect (n = 14, 66.7%), whereas patients with COPD commonly showed the diffuse heterogeneous defect and lobar/segmental/subsegmental defect (n = 21, 45.7% and n = 20, 43.5%, respectively). The prevalence of ventilation defect patterns showed significant intergroup differences (p < 0.001). The quantified ventilation values in the peripheral lung areas were significantly lower in patients with ACOS than in patients with COPD (p = 0.045). The quantified Pi10 was significantly higher in patients with ACOS than in patients with COPD (p = 0.041); however, EI was not significantly different between the two groups. CONCLUSION The ventilation abnormalities on the visual and quantitative assessments of xenon-ventilation DECT differed between patients with ACOS and patients with COPD. Xenon-ventilation DECT may demonstrate the different physiologic changes of pulmonary ventilation in patients with ACOS and COPD.

To investigate the reproducibility of computer-aided detection (CAD) for detection of pulmonary nodules and masses for consecutive chest radiographies (CXRs) of the same patient within a short-term period. A total of 944 CXRs (Chest PA) with nodules and masses, recorded between January 2010 and November 2016 at the Asan Medical Center, were obtained. In all, 1092 regions of interest for the nodules and mass were delineated using an in-house software. All CXRs were randomly split into 6:2:2 sets for training, development, and validation. Furthermore, paired follow-up CXRs (n = 121) acquired within one week in the validation set, in which expert thoracic radiologists confirmed no changes, were used to evaluate the reproducibility of CAD by two radiologists (R1 and R2). The reproducibility comparison of four different convolutional neural net algorithms and two chest radiologists (with 13- and 14-years’ experience) was conducted. Model performances were evaluated by figure-of-merit (FOM) analysis of the jackknife free-response receiver operating curve and reproducibility rates were evaluated in terms of percent positive agreement (PPA) and Chamberlain’s percent positive agreement (CPPA). Reproducibility analysis of the four CADs and R1 and R2 showed variations in the PPA and CPPA. Model performance of YOLO (You Only Look Once) v2 based eDenseYOLO showed a higher FOM (0.89; 0.85–0.93) than RetinaNet (0.89; 0.85–0.93) and atrous spatial pyramid pooling U-Net (0.85; 0.80–0.89). eDenseYOLO showed higher PPAs (97.87%) and CPPAs (95.80%) than Mask R-CNN, RetinaNet, ASSP U-Net, R1, and R2 (PPA: 96.52%, 94.23%, 95.04%, 96.55%, and 94.98%; CPPA: 93.18%, 89.09%, 90.57%, 93.33%, and 90.43%). There were moderate variations in the reproducibility of CAD with different algorithms, which likely indicates that measurement of reproducibility is necessary for evaluating CAD performance in actual clinical environments.

Purpose Computed tomography (CT) volume sets reconstructed with different kernels are helping to increase diagnostic accuracy. However, several CT volumes reconstructed with different kernels are difficult to sustain, due to limited storage and maintenance issues. A CT kernel conversion method is proposed using convolutional neural networks (CNN). Methods A total of 3289 CT images from ten patients (five men and five women; mean age, 63.0 ± 8.6 years) were obtained in May 2016 (Somatom Sensation 16, Siemens Medical Systems, Forchheim, Germany). These CT images were reconstructed with various kernels, including B10f (very smooth), B30f (medium smooth), B50f (medium sharp), and B70f (very sharp) kernels. Smooth kernel images were converted into sharp kernel images using super-resolution (SR) network with Squeeze-and-Excitation (SE) blocks and auxiliary losses, and vice versa. In this study, the single-conversion model and multi-conversion model were presented. In case of the single-conversion model, for the one corresponding output image (e.g., B10f to B70), SE-Residual blocks were stacked. For the multi-conversion model, to convert an image into several output images (e.g., B10f to B30f, B50f, and B70f, and vice versa), progressive learning (PL) was employed by calculating auxiliary losses in every four SE-Residual blocks. Through auxiliary losses, the model could learn mutual relationships between different kernel types. The conversion quality was evaluated by the root-mean-square-error (RMSE), structural similarity (SSIM) index and mutual information (MI) between original and converted images. Results The RMSE (SSIM index , MI) of the multi-conversion model was 4.541 ± 0.688 (0.998 ± 0.001 , 2.587 ± 0.137), 27.555 ± 5.876 (0.944 ± 0.021 , 1.735 ± 0.137), 72.327 ± 17.387 (0.815 ± 0.053 , 1.176 ± 0.096), 8.748 ± 1.798 (0.996 ± 0.002 , 2.464 ± 0.121), 9.470 ± 1.772 (0.994 ± 0.003 , 2.336 ± 0.133), and 9.184 ± 1.605 (0.994 ± 0.002 , 2.342 ± 0.138) in conversion between B10f–B30f, B10f–B50f, B10f–B70f, B70f–B50f, B70f–B30f, and B70f–B10f, respectively, which showed significantly better image quality than the conventional model. Conclusions We proposed deep learning-based CT kernel conversion using SR network. By introducing simplified SE blocks and PL, the model performance was significantly improved.

To develop a model for differentiating the predominant subtype-based prognostic groups of lung adenocarcinoma using CT radiomic features, and to validate its performance in comparison with radiologists’ assessments. A total of 993 patients presenting with invasive lung adenocarcinoma between March 2010 and June 2016 were identified. Predominant histologic subtypes were categorized into three groups according to their prognosis (group 0: lepidic; group 1: acinar/papillary; group 2: solid/micropapillary). Seven hundred eighteen radiomic features were extracted from segmented lung cancers on contrast-enhanced CT. A model-development set was formed from the images of 893 patients, while 100 image sets were reserved for testing. A least absolute shrinkage and selection operator method was used for feature selection. Performance of the radiomic model was evaluated using receiver operating characteristic curve analysis, and accuracy on the test set was compared with that of three radiologists with varying experiences (6, 7, and 19 years in chest CT). Our model differentiated the three groups with areas under the curve (AUCs) of 0.892 and 0.895 on the development and test sets, respectively. In pairwise discrimination, the AUC was highest for group 0 vs. 2 (0.984). The accuracy of the model on the test set was higher than the averaged accuracy of the three radiologists without statistical significance (73.0% vs. 61.7%, p = 0.059). For group 2, the model achieved higher PPV than the observers (85.7% vs. 35.0–48.4%). Predominant subtype-based prognostic groups of lung adenocarcinoma were classified by a CT-based radiomic model with comparable performance to radiologists. • A CT-based radiomic model differentiated three prognosis-based subtype groups of lung adenocarcinoma with areas under the curve (AUCs) of 0.892 and 0.895 on development and test sets, respectively. • The CT-based radiomic model showed near perfect discrimination between group 0 and group 2 (AUCs, 0.984–1.000). • The accuracy of the CT-based radiomic model was comparable to the averaged accuracy of the three radiologists with 6, 7, and 19 years of clinical experience in chest CT (73.0% vs. 61.7%, p = 0.059), achieving a higher positive predictive value for group 2 than the observers (85.7% vs. 35.0–48.4%).

Magnetic resonance imaging (MRI) is the most accurate technique for evaluating residual tumor after neoadjuvant chemotherapy. However, precise determination of the extent of dispersed residual tumor in the breast following treatment remains a difficult task. We hereby introduce three-dimensional (3D)-printed surgical guides for use in breast cancer patients undergoing breast-conserving surgery after receiving neoadjuvant chemotherapy. We prospectively applied the 3D-printed surgical guides on breast cancer patients who underwent partial breast resection after receiving neoadjuvant chemotherapy. Breasts and tumors were modeled in 3D by using pretreatment magnetic resonance images, and surgical guides were created by using a 3D printer to mark the primary tumor. Out of the five patients who participated in the study, all patients had clear resection margins, and two patients experienced complete pathological remission. There were no recurrences during the median follow-up period of 21.9 months. Thus, our newly-developed 3D-printed surgical guides were useful for accurately marking the extent of breast tumor based on pretreatment magnetic resonance images, which is important for designating the extent of surgery needed in patients who have received neoadjuvant chemotherapy.

A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1–2-mm slices, 5–10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18 mm, and 25.47 ± 13.63 mm, respectively. Our deep-learning method showed significantly better segmentation performance (p

Background Intratumor heterogeneity in lung cancer may influence outcomes. CT radiomics seeks to assess tumor features to provide detailed imaging features. However, CT radiomic features vary according to the reconstruction kernel used for image generation. Purpose To investigate the effect of different reconstruction kernels on radiomic features and assess whether image conversion using a convolutional neural network (CNN) could improve reproducibility of radiomic features between different kernels. Materials and Methods In this retrospective analysis, patients underwent non-contrast material-enhanced and contrast material-enhanced axial chest CT with soft kernel (B30f) and sharp kernel (B50f) reconstruction using a single CT scanner from April to June 2017. To convert different kernels without sinogram, the CNN model was developed using residual learning and an end-to-end way. Kernel-converted images were generated, from B30f to B50f and from B50f to B30f. Pulmonary nodules or masses were semiautomatically segmented and 702 radiomic features (tumor intensity, texture, and wavelet features) were extracted. Measurement variability in radiomic features was evaluated using the concordance correlation coefficient (CCC). Results A total of 104 patients were studied, including 54 women and 50 men, with pulmonary nodules or masses (mean age, 63.2 years ± 10.5). The CCC between two readers using the same kernel was 0.92, and 592 of 702 (84.3%) of the radiomic features were reproducible (CCC ≥ 0.85); using different kernels, the CCC was 0.38 and only 107 of 702 (15.2%) of the radiomic features were reliable. Texture features and wavelet features were predominantly affected by reconstruction kernel (CCC, from 0.88 to 0.61 for texture features and from 0.92 to 0.35 for wavelet features). After applying image conversion, CCC improved to 0.84 and 403 of 702 (57.4%) radiomic features were reproducible (CCC, 0.85 for texture features and 0.84 for wavelet features). Conclusion Chest CT image conversion using a convolutional neural network effectively reduced the effect of two different reconstruction kernels and may improve the reproducibility of radiomic features in pulmonary nodules or masses. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Park in this issue.

We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 patients at AMC and 1035 healthy subjects and 4404 patients at SNUBH were obtained. Our approach involved two steps. First, the regional patterns of thoracic abnormalities were identified by initial learning of patch images around abnormal lesions. Second, Resnet-50 was fine-tuned using the entire images. The network was weakly trained and modified to detect various disease patterns. Finally, class activation maps (CAM) were extracted to localise and visualise the abnormal patterns. For average disease, the sensitivity, specificity, and area under the curve (AUC) were 85.4%, 99.8%, and 0.947, respectively, in the AMC dataset and 97.9%, 100.0%, and 0.983, respectively, in the SNUBH dataset. This curriculum learning and weak labelling with high-scale CXR images requires less preparation to train the system and could be easily extended to include various diseases in actual clinical environments. This algorithm performed well for the detection and classification of five disease patterns in CXR images and could be helpful in image interpretation.

To investigate the feasibility of a deep learning–based detection (DLD) system for multiclass lesions on chest radiograph, in comparison with observers. A total of 15,809 chest radiographs were collected from two tertiary hospitals (7204 normal and 8605 abnormal with nodule/mass, interstitial opacity, pleural effusion, or pneumothorax). Except for the test set (100 normal and 100 abnormal (nodule/mass, 70; interstitial opacity, 10; pleural effusion, 10; pneumothorax, 10)), radiographs were used to develop a DLD system for detecting multiclass lesions. The diagnostic performance of the developed model and that of nine observers with varying experiences were evaluated and compared using area under the receiver operating characteristic curve (AUROC), on a per-image basis, and jackknife alternative free-response receiver operating characteristic figure of merit (FOM) on a per-lesion basis. The false-positive fraction was also calculated. Compared with the group-averaged observations, the DLD system demonstrated significantly higher performances on image-wise normal/abnormal classification and lesion-wise detection with pattern classification (AUROC, 0.985 vs. 0.958; p = 0.001; FOM, 0.962 vs. 0.886; p < 0.001). In lesion-wise detection, the DLD system outperformed all nine observers. In the subgroup analysis, the DLD system exhibited consistently better performance for both nodule/mass (FOM, 0.913 vs. 0.847; p < 0.001) and the other three abnormal classes (FOM, 0.995 vs. 0.843; p < 0.001). The false-positive fraction of all abnormalities was 0.11 for the DLD system and 0.19 for the observers. The DLD system showed the potential for detection of lesions and pattern classification on chest radiographs, performing normal/abnormal classifications and achieving high diagnostic performance. • The DLD system was feasible for detection with pattern classification of multiclass lesions on chest radiograph. • The DLD system had high performance of image-wise classification as normal or abnormal chest radiographs (AUROC, 0.985) and showed especially high specificity (99.0%). • In lesion-wise detection of multiclass lesions, the DLD system outperformed all 9 observers (FOM, 0.962 vs. 0.886; p < 0.001).

Deep learning is a genre of machine learning that allows computational models to learn representations of data with multiple levels of abstraction using numerous processing layers. A distinctive feature of deep learning, compared with conventional machine learning methods, is that it can generate appropriate models for tasks directly from the raw data, removing the need for human-led feature extraction. Medical images are particularly suited for deep learning applications. Deep learning techniques have already demonstrated high performance in the detection of diabetic retinopathy on fundoscopic images and metastatic breast cancer cells on pathologic images. In radiology, deep learning has the opportunity to provide improved accuracy of image interpretation and diagnosis. Many groups are exploring the possibility of using deep learning-based applications to solve unmet clinical needs. In chest imaging, there has been a large effort to develop and apply computer-aided detection systems for the detection of lung nodules on chest radiographs and chest computed tomography. The essential limitation to computer-aided detection is an inability to learn from new information. To overcome these deficiencies, many groups have turned to deep learning approaches with promising results. In addition to nodule detection, interstitial lung disease recognition, lesion segmentation, diagnosis and patient outcomes have been addressed by deep learning approaches. The purpose of this review article was to cover the current state of the art for deep learning approaches and its limitations, and some of the potential impact on the field of radiology, with specific reference to chest imaging.

Background: The full-scale airway network (FAN) flow model shows excellent agreement with limited functional imaging data but requires further validation prior to clinical use. Purpose: To validate the ventilation distributions computed with the FAN flow model with xenon ventilation from xenon-enhanced dual-energy (DE) CT in participants with chronic obstructive pulmonary disease (COPD). Materials and Methods: in this prospective study, the FAN model extracted structural data from xenon-enhanced DE CT images of men with COPD scanned between June 2012 and July 2013 to compute gas ventilation dynamics. The ventilation distributions on the middle cross-section plane, percentage lobar ventilation, and ventilation heterogeneity quantified by the coefficient of variation (CV) were compared between xenon-enhanced DE CT imaging and the FAN model. The relationship between the ventilation parameters with the densitometry and pulmonary function test results was demonstrated. The agreements and correlations between the parameters were measured using the concordance correlation coefficient and the Pearson correlation coefficient. Results: Twenty-two men with COPD (mean age, 67 years +/- 7 [standard deviation]) were evaluated. The percentage lobar ventilation computed with FAN showed a strong positive correlation with xenon-enhanced DE CT data (r = 0.7, P < .001). Ninety-five percent of lobar ventilation CV differences lay within 95% confidence intervals. Correlations of the percentage lobar ventilation were negative for percentage emphysema (xenon-enhanced DE CT: r = -0.38, P < .001; FAN: r = -0.23, P = .02) but were positive for percentage normal tissue volume (xenon-enhanced DE CT: r = 0.78, P < .001; FAN: r = 0.45, P < .001). Lung CVs of FAN revealed negative correlations with the spirometry results (CVFAN vs percentage predicted forced expiratory volume in 1 second: r = -0.75, P < .001; CVFAN vs ratio of forced expiratory volume in 1 second to forced vital capacity: r = -0.67, P < .001). Conclusion: The full-scale airway network modeled lobar ventilation in patients with chronic obstructive pulmonary disease correlated with the xenon-enhanced dual-energy CT imaging data. (C) RSNA, 2020, Cancer Research UKCancer Research UK [C5255]; Engineering and Physical Sciences Research CouncilUK Research & Innovation (UKRI)Engineering & Physical Sciences Research Council (EPSRC) [A16466]; NIHR Oxford Biomedical Research CentreNational Institute for Health Research (NIHR), Supported by the Cancer Research UK (grant C5255), Engineering and Physical Sciences Research Council (grant A16466), and NIHR Oxford Biomedical Research Centre.

The increase in the radiation exposure from CT examinations prompted the investigation on the various dose-reduction techniques. Significant dose reduction has been achieved and the level of radiation exposure of thoracic CT is expected to reach the level equivalent to several chest X-ray examinations. With more scanners with advanced dose reduction capability deployed, knowledge on the radiation dose reduction methods has become essential to clinical practice as well as academic research. This article reviews the history of dose reduction techniques, ongoing changes brought by newer technologies and areas of further investigation.

The assessment of pulmonary function, including ventilation and perfusion status, is important in addition to the evaluation of structural changes of the lung parenchyma in various pulmonary diseases. The dual-energy computed tomography (DECT) technique can provide the pulmonary functional information and high resolution anatomic information simultaneously. The application of DECT for the evaluation of pulmonary function has been investigated in various pulmonary diseases, such as pulmonary embolism, asthma and chronic obstructive lung disease and so on. In this review article, we will present principles and technical aspects of DECT, along with clinical applications for the assessment pulmonary function in various lung diseases.

The aim of our study was to retrospectively determine predictive factors for a decline in forced vital capacity (FVC) on initial CT using texture-based automated quantification in patients with idiopathic pulmonary fibrosis (IPF).For our study, 193 patients with IPF and 1-year follow-up pulmonary function tests were enrolled in our study. A texture-based automated system used in-house software to quantify six regional CT patterns: normal, ground-glass opacity (GGO), reticular opacity (RO), honeycombing, emphysema, and consolidation. A decline of FVC was defined as a decrease in the initial FVC of more than 10%.A decline of FVC occurred in 32 patients: The mean volume of the decline in FVC was 0.43 ± 0.18 (SD) L. The mean extents of GGO, RO, honeycombing, emphysema, and consolidation in all 193 patients were as follows: 12.3% ± 11.9%, 16.8% ± 9.8%, 7.1% ± 6.7%, 3.9% ± 5.5%, and 2.8% ± 0.8%, respectively. A multivariate analysis revealed that RO was the sole independent predictor for a decline in FVC (p = 0.012; adjusted odds ratio, 1.047). ROC analysis showed that the AUC of RO was 0.641 and that the optimal RO cutoff value was 22.05% (sensitivity, 50.0%; specificity, 81.4%; negative predictive value, 89.1%).RO of less than 22.05% in extent can accurately predict stable IPF at 1-year follow-up in terms of FVC.

Purpose: In patients with chronic obstructive pulmonary disease (COPD), diaphragm function may deteriorate due to reduced muscle fiber length. Quantitative analysis of the morphology of the diaphragm is therefore important. In the authors current study, they propose a diaphragm segmentation method for COPD patients that uses volumetric chest computed tomography (CT) data, and they provide a quantitative analysis of the diaphragmatic dimensions. Methods: Volumetric CT data were obtained from 30 COPD patients and 10 normal control patients using a 16-row multidetector CT scanner (Siemens Sensation 16) with 0.75-mm collimation. Diaphragm segmentation using 3D ray projections on the lower surface of the lungs was performed to identify the draft diaphragmatic lung surface, which was modeled using quadratic 3D surface fitting and robust regression in order to minimize the effects of segmentation error and parameterize diaphragm morphology. This result was visually evaluated by an expert thoracic radiologist. To take into consideration the shape features of the diaphragm, several quantification parameters—including the shape index on the apex (SIA) (which was computed using gradient set to 0), principal curvatures on the apex on the fitted diaphragm surface (CA), the height between the apex and the base plane (H), the diaphragm lengths along the x-, y-, and z-axes (XL, YL, ZL), quadratic-fitted diaphragm lengths on the z-axis (FZL), average curvature (C), and surface area (SA)—were measured using in-house software and compared with the pulmonary function test (PFT) results. Results: The overall accuracy of the combined segmentation method was 97.22% ± 4.44% while the visual accuracy of the models for the segmented diaphragms was 95.28% ± 2.52% (mean ± SD). The quantitative parameters, including SIA, CA, H, XL, YL, ZL, FZL, C, and SA were 0.85 ± 0.05 (mm−1), 0.01 ± 0.00 (mm−1), 17.93 ± 10.78 (mm), 129.80 ± 11.66 (mm), 163.19 ± 13.45 (mm), 71.27 ± 17.52 (mm), 61.59 ± 16.98 (mm), 0.01 ± 0.00 (mm−1), and 34 380.75 ± 6680.06 (mm2), respectively. Several parameters were correlated with the PFT parameters. Conclusions: The authors propose an automatic method for quantitatively evaluating the morphological parameters of the diaphragm on volumetric chest CT in COPD patients. By measuring not only the conventional length and surface area but also the shape features of the diaphragm using quadratic 3D surface modeling, the proposed method is especially useful for quantifying diaphragm characteristics. Their method may be useful for assessing morphological diaphragmatic changes in COPD patients.

OBJECTIVES The aim of this study was to assess the feasibility of combined xenon-enhanced ventilation (V) and iodine-enhanced perfusion (Q) dual-energy computed tomography (DECT) to evaluate regional V and Q status in patients with chronic obstructive pulmonary disease (COPD). MATERIALS AND METHODS Combined V and Q DECT imaging was performed in 52 prospectively enrolled male COPD patients. Virtual noncontrast images, V maps, and Q maps were anatomically coregistered with deformable registration and evaluated using in-house software. After normalization of the V and Q values of each pixel, normalized V and Q, V/Qratio, and VQmin (ie, the smaller of the V and Q in each pixel) maps were generated. For visual analysis, the V/Qratio pattern was determined to be matched, mismatched, or reversed mismatched and compared with the regional disease patterns--emphysema with/without bronchial wall thickening, bronchial wall thickening, or normal parenchyma--in each segment. The mean V, Q, V/Qratio, and VQmin values and the standard deviation of the V/Qratio (V/QSD) of each patient were quantified and compared with pulmonary function test (PFT) parameters using the Pearson correlation test. RESULTS Segments with normal parenchyma showed a matched V/Qratio pattern, whereas segments with bronchial wall thickening commonly showed a reversed mismatched V/Qratio pattern. In the emphysema areas, the matched, mismatched, and reversed mismatched patterns were mixed without a dominant pattern. In quantitative analysis, the mean V, Q, VQmin, and V/Qratio values were significantly and positively correlated with PFT parameters (r = 0.290-0.819; P < 0.05). The V/QSD was significantly and negatively correlated with PFT parameters (r = -0.439 to -0.736; P < 0.001). VQmin values showed the best correlation with PFT parameters (r = 0.483-0.819; P < 0.001). CONCLUSIONS Visual and quantitative assessment of the regional V, Q, V/Qratio, and VQmin is feasible with combined V and Q DECT imaging and significantly correlate with PFT results in COPD patients. Assessing disease patterns using conventional computed tomography images may not provide correct evaluation of regional V and Q in COPD patients with emphysema.

Objective To assess the performance of content-based image retrieval (CBIR) of chest CT for diffuse interstitial lung disease (DILD). Materials and methods The database was comprised by 246 pairs of chest CTs (initial and follow-up CTs within two years) from 246 patients with usual interstitial pneumonia (UIP, n = 100), nonspecific interstitial pneumonia (NSIP, n = 101), and cryptogenic organic pneumonia (COP, n = 45). Sixty cases (30-UIP, 20-NSIP, and 10-COP) were selected as the queries. The CBIR retrieved five similar CTs as a query from the database by comparing six image patterns (honeycombing, reticular opacity, emphysema, ground-glass opacity, consolidation and normal lung) of DILD, which were automatically quantified and classified by a convolutional neural network. We assessed the rates of retrieving the same pairs of query CTs, and the number of CTs with the same disease class as query CTs in top 1-5 retrievals. Chest radiologists evaluated the similarity between retrieved CTs and queries using a 5-scale grading system (5-almost identical; 4-same disease; 3-likelihood of same disease is half; 2-likely different; and 1-different disease). Results The rate of retrieving the same pairs of query CTs in top 1 retrieval was 61.7% (37/60) and in top 1-5 retrievals was 81.7% (49/60). The CBIR retrieved the same pairs of query CTs more in UIP compared to NSIP and COP (p = 0.008 and 0.002). On average, it retrieved 4.17 of five similar CTs from the same disease class. Radiologists rated 71.3% to 73.0% of the retrieved CTs with a similarity score of 4 or 5. Conclusion The proposed CBIR system showed good performance for retrieving chest CTs showing similar patterns for DILD.

Korean Society of Thoracic Radiology (KSTR) launched a web-based learning program called the “KSTR Weekly Chest Cases” in November 1997 (http://kstr.radiology.or.kr/weekly/). This program aimed to provide easily accessible, high-quality thoracic radiology education through a case-based approach to a worldwide audience. The website contains over 1000 cases with high-quality images, including cases from KSTR imaging conferences. Currently, the “KSTR Weekly Chest Cases” website has over 2700 members from 90 countries. KSTR members and website editors continue to facilitate communication and provide educationally relevant thoracic imaging worldwide through the “KSTR Weekly Chest Cases,” now also available as an app.

In this chapter, we present six case scenarios uncovering many common questions and issues that we may frequently face in the field of 3D printing in medicine where the radiologists will bring added value through their expertise. 3D printing in medicine is a relatively new emerging field. Therefore, these scenarios could be some examples of applications to find use in everyday medicine. Scenarios including several simulators and surgical guides, which are actually used in a real clinical environment where one can possibly improve the physician’s satisfaction and patients’ outcomes, are detailed. In addition, the added values for physician’s satisfaction and patient outcomes regarding 3D printed simulators and surgical guides are also highlighted. For example, a 3D printed rehearsal simulator of congenital heart anomalies of which surgical correction or treatment, particularly in infant or childhood, is difficult due to small size, its complexity, and individual variation could be very useful for an inexperienced surgeon.

Background Patients with chronic obstructive pulmonary disease (COPD) have an increased risk of vitamin D deficiency. Vitamin D levels also correlate with lung function in patients with COPD. However, there are few reports on vitamin D deficiency and emphysema severity in COPD. This study aimed to investigate the effects of plasma 25-hydroxyvitamin D (25-OHD) level on emphysema severity in male COPD patients. Methods A total of 151 male subjects were selected from the Korean Obstructive Lung Disease (KOLD) cohort. Subjects were subdivided into four subgroups according to their baseline plasma 25-OHD level: sufficiency (≥20 ng/ml), mild deficiency (15–20 ng/ml), moderate deficiency (10–15 ng/ml), and severe deficiency ( Results Baseline computed tomography (CT) emphysema indices revealed significant differences among the subgroups (p = 0.034). A statistically significant difference was also observed among the subgroups regarding change in the CT emphysema index over 3 years (p = 0.047). The annual increase in emphysema index was more prominent in the severe deficiency group (1.34% per year) than in the other groups (0.41% per year) (p = 0.003). Conclusions This study demonstrates that CT emphysema indices were different among the four subgroups and supports that severe vitamin D deficiency is associated with rapid progression of emphysema in male patients with COPD.

Deep learning is now widely used as an efficient tool for medical image classification and segmentation. However, conventional machine learning techniques are still more accurate than deep learning when only a small dataset is available. In this study, we present a general data augmentation strategy using Perlin noise, applying it to pixel-by-pixel image classification and quantification of various kinds of image patterns of diffuse interstitial lung disease (DILD). Using retrospectively obtained high-resolution computed tomography (HRCT) images from 106 patients, 100 regions-of-interest (ROIs) for each of six classes of image patterns (normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation) were selected for deep learning classification by experienced thoracic radiologists. For extra-validation, the deep learning quantification of the six classification patterns was evaluated for 92 HRCT whole lung images for which hand-labeled segmentation masks created by two experienced radiologists were available. FusionNet, a convolutional neural network (CNN), was used for training, test, and extra-validation on classifications of DILD image patterns. The accuracy of FusionNet with data augmentation using Perlin noise (89.5%, 49.8%, and 55.0% for ROI-based classification and whole lung quantifications by two radiologists, respectively) was significantly higher than that with conventional data augmentation (82.1%, 45.7%, and 49.9%, respectively). This data augmentation strategy using Perlin noise could be widely applied to deep learning studies for image classification and segmentation, especially in cases with relatively small datasets.

OBJECTIVE To retrospectively investigate whether tumor size assessment on multiplanar reconstruction (MPR) CT images better reflects pathologic T-stage than evaluation on axial images and evaluate the additional value of measurement in three-dimensional (3D) space. MATERIALS AND METHODS From 1661 patients who had undergone surgical resection for primary lung cancer between June 2013 and November 2016, 210 patients (145 men; mean age, 64.4 years) were randomly selected and 30 were assigned to each pathologic T-stage. Two readers independently measured the maximal lesion diameters on MPR CT. The longest diameters on 3D were obtained using volume segmentation. T-stages determined on CT images were compared with pathologic T-stages (overall and subgroup-Group 1, T1a/b; Group 2, T1c or higher), with differences in accuracy evaluated using McNemar's test. Agreement between readers was evaluated with intraclass correlation coefficients (ICC). RESULTS The diagnostic accuracy of MPR measurements for determining T-stage was significantly higher than that of axial measurement alone for both reader 1 (74.3% [156/210] vs. 63.8% [134/210]; p = 0.001) and reader 2 (68.1% [143/210] vs. 61.9% [130/210]; p = 0.049). In the subgroup analysis, diagnostic accuracy with MPR diameter was significantly higher than that with axial diameter in only Group 2 (p < 0.05). Inter-reader agreements for the ICCs on axial and MPR measurements were 0.98 and 0.98. The longest diameter on 3D images showed a significantly lower performance than MPR, with an accuracy of 54.8% (115/210) (p < 0.05). CONCLUSION Size measurement on MPR CT better reflected the pathological T-stage, specifically for T1c or higher stage lung cancer. Measurements in a 3D plane showed no added value.

Airway diseases are frequently related to morphological changes that may influence lung physiology. Accurate airway region segmentation may be useful for quantitative evaluation of disease prognosis and therapy efficacy. The information can also be applied to understand the fundamental mechanisms of various lung diseases. We present a hybrid method to automatically segment the airway regions on 3D volume chest computed tomography (CT) scans. This method uses multi-scale filtering and support vector machine (SVM) classification. The proposed scheme is comprised of two hybrid steps. First, a tubular structure-based multi-scale filter is applied to find the initial candidate airway regions. Second, for identifying candidate airway regions using the fuzzy connectedness technique, the small and disconnected branches of airway regions are detected using SVM classification trained to differentiate between airway and non-airway regions through texture analysis of user-defined landmark points. For development and evaluation of the method, two datasets were incorporated: (1) 55 lung-CT volumes from the Korean Obstructive Lung Disease (KOLD) Cohort Study and (2) 20 cases from the publicly open database (EXACT′09). The average tree-length detection rates of EXACT′09 and KOLD were 56.9 ± 11.0 and 70.5 ± 8.98, respectively. Comparison of the results for the EXACT′09 data set between the presented method and other methods revealed that our approach was a high performer. The method limitations were higher false-positive rates than those of the other methods and risk of leakage. In future studies, application of a convolutional neural network will help overcome these shortcomings.

Objective The absence of collateral ventilation (CV) is crucial for effective bronchoscopic lung volume reduction (BLVR) with an endobronchial valve. Here, we assessed whether CT can predict the Chartis™ results. Materials and methods This study included 69 patients (mean age: 70.9 ± 6.6 years; 66 [95.7%] males) who had undergone CT to assess BLVR eligibility. The Chartis™ system (Pulmonox Inc.) was used to check CV. Experienced thoracic radiologists independently determined the completeness of fissures on volumetric CT images. Results The comparison between the visual and quantitative analyses revealed that 5% defect criterion showed good agreement. The Chartis™ assessment was performed for 129 lobes; 11 (19.6%) of 56 lobes with complete fissures on CT showed positive CV, while this rate was significantly higher (40 of 49 lobes, i.e., 81.6%) for lobes with incomplete fissures. The size of the fissure defect did not affect the rate of CV. Of the patients who underwent BLVR, 22 of 24 patients (91.7%) with complete fissures and three of four patients with incomplete fissures (75%) achieved target lobe volume reduction (TLVR). Conclusion The quantitative analysis of fissure shows that incomplete fissures increased the probability of CV on Chartis™, while the defect size did not affect the overall rates. TLVR could be achieved even in some patients with relatively large fissure defect, if they showed negative CV on Chartis™.

To retrospectively evaluate the diagnostic performance of a convolutional neural network (CNN) model in detecting pneumothorax on chest radiographs obtained after percutaneous transthoracic needle biopsy (PTNB) for pulmonary lesions. A CNN system for computer-aided diagnosis on chest radiographs was developed using the full 26-layer You Only Look Once model. A total of 1596 chest radiographs with pneumothorax were used for training. To validate the clinical feasibility of this model, follow-up chest radiographs obtained after PTNB for 1333 pulmonary lesions in 1319 patients in 2016 were prepared as an independent test set. Two experienced radiologists determined the presence of pneumothorax by consensus. The diagnostic performance of the CNN model was assessed using the jackknife free-response receiver operating characteristic method. The incidence of pneumothorax was 17.9% (247/1379) on 3-h follow-up chest radiographs and 23.3% (309/1329) on 1-day follow-up chest radiographs. Twenty-three (1.7% of all PTNBs) cases required drainage catheter insertion. Our approach had a sensitivity, a specificity, and an area under the curve (AUC), respectively, of 61.1% (151/247), 93.0% (1053/1132), and 0.898 for 3-h follow-up chest radiographs and 63.4% (196/309), 93.5% (954/1020), and 0.905 for 1-day follow-up chest radiographs. The overall accuracy was 87.3% (1204/1379) for 3-h follow-up radiographs and 86.5% (1150/1329) for 1-day follow-up radiographs. The CNN model found all 23 cases of pneumothorax requiring drainage. Our CNN model had good performance for detection of pneumothorax on chest radiographs after PTNB, especially for those requiring further procedures. It can be used as a screening tool prior to radiologist interpretation. • The CNN model had good performance for detection of pneumothorax on chest radiographs after PTNB and showed high specificity and negative predictive value. • The CNN model found all cases of pneumothorax requiring drainage after PTNB. • The CNN model can be used as a screening tool prior to radiologist interpretation.

Background Chronic obstructive pulmonary disease (COPD) is a heterogeneous condition that can differ in its clinical manifestation, structural changes and response to treatment. Objective To identify subgroups of COPD with distinct phenotypes, evaluate the distribution of phenotypes in four related regions and calculate the 1-year change in lung function and quality of life according to subgroup. Methods Using clinical characteristics, we performed factor analysis and hierarchical cluster analysis in a cohort of 1676 COPD patients from 13 Asian cities. We compared the 1-year change in forced expiratory volume in one second (FEV1), modified Medical Research Council dyspnoea scale score, St George's Respiratory Questionnaire (SGRQ) score and exacerbations according to subgroup derived from cluster analysis. Results Factor analysis revealed that body mass index, Charlson comorbidity index, SGRQ total score and FEV1 were principal factors. Using these four factors, cluster analysis identified three distinct subgroups with differing disease severity and symptoms. Among the three subgroups, patients in subgroup 2 (severe disease and more symptoms) had the most frequent exacerbations, most rapid FEV1 decline and greatest decline in SGRQ total score. Conclusion Three subgroups with differing severities and symptoms were identified in Asian COPD subjects.