Search

BACKGROUND. CT-guided percutaneous transthoracic needle biopsy (PTNB) is widely used for evaluation of indeterminate pulmonary lesions, although guidelines are lacking regarding the experience need...

Background The solid portion size of lung cancer lesions manifesting as subsolid lesions is key in their management, but the automatic measurement of such lesions by means of a deep learning (DL) algorithm needs evaluation. Purpose To evaluate the performance of a commercially available DL algorithm for automatic measurement of the solid portion of surgically proven lung adenocarcinomas manifesting as subsolid lesions. Materials and Methods Surgically proven lung adenocarcinomas manifesting as subsolid lesions on CT images between January 2018 and December 2018 were retrospectively included. Five radiologists independently measured the maximal axial diameter of the solid portion of lesions. The DL algorithm automatically segmented and measured the maximal axial diameter of the solid portion. Reader measurements, software measurements, and invasive component size at pathologic examination were compared by using intraclass correlation coefficient (ICC) and Bland-Altman plots. Results A total of 448 patients (mean age, 63 years ± 10 [standard deviation]; 264 women) with 448 lesions were evaluated (invasive component size, 3-65 mm). The measurement agreements between each radiologist and the DL algorithm were very good (ICC range, 0.82-0.89). When a radiologist was replaced with the DL algorithm, the ICCs ranged from 0.87 to 0.90, with an ICC of 0.90 among five radiologists. The mean difference between the DL algorithm and each radiologist ranged from -3.7 to 1.5 mm. The widest 95% limit of agreement between the DL algorithm and each radiologist (-15.7 to 8.3 mm) was wider than pairwise comparisons of radiologists (-7.7 to 13.0 mm). The agreement between the DL algorithm and invasive component size at pathologic evaluation was good, with an ICC of 0.67. Measurements by the DL algorithm (mean difference, -6.0 mm) and radiologists (mean difference, -7.5 to -2.3 mm) both underestimated invasive component size. Conclusion Automatic measurements of solid portions of lung cancer manifesting as subsolid lesions by the deep learning algorithm were comparable with manual measurements and showed good agreement with invasive component size at pathologic evaluation. © RSNA, 2021 Online supplemental material is available for this article.

Background Studies on the optimal CT section thickness for detecting subsolid nodules (SSNs) with computer-aided detection (CAD) are lacking. Purpose To assess the effect of CT section thickness on CAD performance in the detection of SSNs and to investigate whether deep learning-based super-resolution algorithms for reducing CT section thickness can improve performance. Materials and Methods CT images obtained with 1-, 3-, and 5-mm-thick sections were obtained in patients who underwent surgery between March 2018 and December 2018. Patients with resected synchronous SSNs and those without SSNs (negative controls) were retrospectively evaluated. The SSNs, which ranged from 6 to 30 mm, were labeled ground-truth lesions. A deep learning-based CAD system was applied to SSN detection on CT images of each section thickness and those converted from 3- and 5-mm section thickness into 1-mm section thickness by using the super-resolution algorithm. The CAD performance on each section thickness was evaluated and compared by using the jackknife alternative free response receiver operating characteristic figure of merit. Results A total of 308 patients (mean age ± standard deviation, 62 years ± 10; 183 women) with 424 SSNs (310 part-solid and 114 nonsolid nodules) and 182 patients without SSNs (mean age, 65 years ± 10; 97 men) were evaluated. The figures of merit differed across the three section thicknesses (0.92, 0.90, and 0.89 for 1, 3, and 5 mm, respectively; P = .04) and between 1- and 5-mm sections (P = .04). The figures of merit varied for nonsolid nodules (0.78, 0.72, and 0.66 for 1, 3, and 5 mm, respectively; P < .001) but not for part-solid nodules (range, 0.93-0.94; P = .76). The super-resolution algorithm improved CAD sensitivity on 3- and 5-mm-thick sections (P = .02 for 3 mm, P < .001 for 5 mm). Conclusion Computer-aided detection (CAD) of subsolid nodules performed better at 1-mm section thickness CT than at 3- and 5-mm section thickness CT, particularly with nonsolid nodules. Application of a super-resolution algorithm improved the sensitivity of CAD at 3- and 5-mm section thickness CT. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Goo in this issue.

Objective. To unify the style of computed tomography (CT) images from multiple sources, we propose a novel multi-domain image translation network to convert CT images from different scan parameters and manufacturers by simply changing a routing vector. Approach. Unlike the existing multi-domain translation techniques, our method is based on a shared encoder and a routable decoder architecture to maximize the expressivity and conditioning power of the network. Main results. Experimental results show that the proposed CT image conversion can minimize the variation of image characteristics caused by imaging parameters, reconstruction algorithms, and hardware designs. Quantitative results and clinical evaluation from radiologists also show that our method can provide accurate translation results. Significance. Quantitative evaluation of CT images from multi-site or longitudinal studies has been a difficult problem due to the image variation depending on CT scan parameters and manufacturers. The proposed method can be utilized to address this for the quantitative analysis of multi-domain CT images.

OBJECTIVE Patients with chronic obstructive pulmonary disease (COPD) are known to be at risk of osteoporosis. The purpose of this study was to evaluate the association between thoracic vertebral bone density measured on chest CT (DThorax) and clinical variables, including survival, in patients with COPD. MATERIALS AND METHODS A total of 322 patients with COPD were selected from the Korean Obstructive Lung Disease (KOLD) cohort. DThorax was measured by averaging the CT values of three consecutive vertebral bodies at the level of the left main coronary artery with a round region of interest as large as possible within the anterior column of each vertebral body using an in-house software. Associations between DThorax and clinical variables, including survival, pulmonary function test (PFT) results, and CT densitometry, were evaluated. RESULTS The median follow-up time was 7.3 years (range: 0.1-12.4 years). Fifty-six patients (17.4%) died. DThorax differed significantly between the different Global Initiative for Chronic Obstructive Lung Disease stages. DThorax correlated positively with body mass index (BMI), some PFT results, and the six-minute walk distance, and correlated negatively with the emphysema index (EI) (all p < 0.05). In the univariate Cox analysis, older age (hazard ratio [HR], 3.617; 95% confidence interval [CI], 2.119-6.173, p < 0.001), lower BMI (HR, 3.589; 95% CI, 2.122-6.071, p < 0.001), lower forced expiratory volume in one second (FEV₁) (HR, 2.975; 95% CI, 1.682-5.262, p < 0.001), lower diffusing capacity of the lung for carbon monoxide corrected with hemoglobin (DLCO) (HR, 4.595; 95% CI, 2.665-7.924, p < 0.001), higher EI (HR, 3.722; 95% CI, 2.192-6.319, p < 0.001), presence of vertebral fractures (HR, 2.062; 95% CI, 1.154-3.683, p = 0.015), and lower DThorax (HR, 2.773; 95% CI, 1.620-4.746, p < 0.001) were significantly associated with all-cause mortality and lung-related mortality. In the multivariate Cox analysis, lower DThorax (HR, 1.957; 95% CI, 1.075-3.563, p = 0.028) along with older age, lower BMI, lower FEV₁, and lower DLCO were independent predictors of all-cause mortality. CONCLUSION The thoracic vertebral bone density measured on chest CT demonstrated significant associations with the patients' mortality and clinical variables of disease severity in the COPD patients included in KOLD cohort.

Lung adenocarcinoma shows broad spectrum of prognosis and histologic heterogeneity. This study was to investigate the prognostic value of CT radiomics in resectable lung adenocarcinoma patients and assess its incremental value over clinical-pathologic risk factors. This retrospective analysis evaluated 1058 patients who underwent curative surgery for lung adenocarcinoma (training cohort: N = 754; temporal validation cohort: N = 304). Radiomics features were extracted from preoperative contrast-enhanced CT. Radiomics signature to predict disease-free survival (DFS) and overall survival (OS) was generated. Association between the radiomics signature and prognosis were evaluated using univariable and multivariable Cox proportional hazards regression analyses. Incremental value of the radiomics signature beyond clinical-pathologic risk factors was assessed using concordance index (C-index). The radiomics signatures were independently associated with DFS (hazard ratio [HR], 1.920; p

To assess whether pulmonary vein injury is detectable on CT and associated with air embolism after percutaneous transthoracic needle biopsy (PTNB) in a tertiary referral hospital.Between January 2012 and November 2021, 11,691 consecutive CT-guided PTNBs in 10,685 patients were retrospectively evaluated. Air embolism was identified by reviewing radiologic reports. Pulmonary vein injury was defined as the presence of the pulmonary vein in the needle pathway or shooting range of the cutting needle with the presence of parenchymal hemorrhage. The association between pulmonary vein injury and air embolism was assessed using logistic regression analysis in matched patients with and without air embolism with a ratio of 1:4.A total of 27 cases of air embolism (median age, 67 years; range, 48-80 years; 24 men) were found with an incidence of 0.23% (27/11,691). Pulmonary vein injury during the procedures was identifiable on CT in 24 of 27 patients (88.9%), whereas it was 1.9% (2/108) for matched patients without air embolism The veins beyond the target lesion (70.8% [17/24]) were injured more frequently than the veins in the needle pathway before the target lesion (29.2% [7/24]). In univariable and multivariable analyses, pulmonary vein injury was associated with air embolism (odds ratio, 485.19; 95% confidence interval, 68.67-3428.19, p.001).Pulmonary vein injury was detected on CT and was associated with air embolism. Avoiding pulmonary vein injury with careful planning of the needle pathway on CT may reduce air embolism risk.• Pulmonary vein injury during CT-guided biopsy was identifiable on CT in most of the patients (88.9% [24/27]). • The veins beyond the target lesion (70.8% [17/24]) were injured more frequently than the veins in the needle pathway before the target lesion (29.2% [7/24]). • Avoiding the distinguishable pulmonary vein along the pathway or shooting range of the needle on CT may reduce the air embolism risk.

We aimed to evaluate the performance of a fully automated quantitative software in detecting interstitial lung abnormalities (ILA) according to the Fleischner Society guidelines on routine chest CT compared with radiologists' visual analysis.This retrospective single-centre study included participants with ILA findings and 1:2 matched controls who underwent routine chest CT using various CT protocols for health screening. Two thoracic radiologists independently reviewed the CT images using the Fleischner Society guidelines. We developed a fully automated quantitative tool for detecting ILA by modifying deep learning-based quantification of interstitial lung disease and evaluated its performance using the radiologists' consensus for ILA as a reference standard.A total of 336 participants (mean age, 70.5 ± 6.1 years; M:F = 282:54) were included. Inter-reader agreements were substantial for the presence of ILA (weighted κ, 0.74) and fair for its subtypes (weighted κ, 0.38). The quantification system for identifying ILA using a threshold of 5 % in at least one zone showed 67.6 % sensitivity, 93.3 % specificity, and 90.5 % accuracy. Eight of 20 (40 %) false positives identified by the system were underestimated by readers for ILA extent. Contrast-enhancement in a certain vendor and suboptimal inspiration caused a true false-positive on the system (all P 0.05). The best cut-off value of abnormality extent detecting ILA on the system was 3.6 % (sensitivity, 84.8 %; specificity 92.4 %).Inter-reader agreement was substantial for ILA but only fair for its subtypes. Applying an automated quantification system in routine clinical practice may aid the objective identification of ILA.

Background Evaluation of interstitial lung disease (ILD) at CT is a challenging task that requires experience and is subject to substantial interreader variability. Purpose To investigate whether a proposed content-based image retrieval (CBIR) of similar chest CT images by using deep learning can aid in the diagnosis of ILD by readers with different levels of experience. Materials and Methods This retrospective study included patients with confirmed ILD after multidisciplinary discussion and available CT images identified between January 2000 and December 2015. Database was composed of four disease classes: usual interstitial pneumonia (UIP), nonspecific interstitial pneumonia (NSIP), cryptogenic organizing pneumonia, and chronic hypersensitivity pneumonitis. Eighty patients were selected as queries from the database. The proposed CBIR retrieved the top three similar CT images with diagnosis from the database by comparing the extent and distribution of different regional disease patterns quantified by a deep learning algorithm. Eight readers with varying experience interpreted the query CT images and provided their most probable diagnosis in two reading sessions 2 weeks apart, before and after applying CBIR. Diagnostic accuracy was analyzed by using McNemar test and generalized estimating equation, and interreader agreement was analyzed by using Fleiss κ. Results A total of 288 patients were included (mean age, 58 years ± 11 [standard deviation]; 145 women). After applying CBIR, the overall diagnostic accuracy improved in all readers (before CBIR, 46.1% [95% CI: 37.1, 55.3]; after CBIR, 60.9% [95% CI: 51.8, 69.3]

Lung lobe segmentation in chest CT has been used for the analysis of lung functions and surgical planning. However, accurate lobe segmentation is difficult as 80% of patients have incomplete and/or fake fissures. Furthermore, lung diseases such as chronic obstructive pulmonary disease (COPD) can increase the difficulty of differentiating the lobar fissures. Lobar fissures have similar intensities to those of the vessels and airway wall, which could lead to segmentation error in automated segmentation. In this study, a fully automated lung lobe segmentation method with 3D U-Net was developed and validated with internal and external datasets. The volumetric chest CT scans of 196 normal and mild-to-moderate COPD patients from three centers were obtained. Each scan was segmented using a conventional image processing method and manually corrected by an expert thoracic radiologist to create gold standards. The lobe regions in the CT images were then segmented using a 3D U-Net architecture with a deep convolutional neural network (CNN) using separate training, validation, and test datasets. In addition, 40 independent external CT images were used to evaluate the model. The segmentation results for both the conventional and deep learning methods were compared quantitatively to the gold standards using four accuracy metrics including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). In internal validation, the segmentation method achieved high accuracy for the DSC, JSC, MSD, and HSD (0.97 ± 0.02, 0.94 ± 0.03, 0.69 ± 0.36, and 17.12 ± 11.07, respectively). In external validation, high accuracy was also obtained for the DSC, JSC, MSD, and HSD (0.96 ± 0.02, 0.92 ± 0.04, 1.31 ± 0.56, and 27.89 ± 7.50, respectively). This method took 6.49 ± 1.19 s and 8.61 ± 1.08 s for lobe segmentation of the left and right lungs, respectively. Although various automatic lung lobe segmentation methods have been developed, it is difficult to develop a robust segmentation method. However, the deep learning–based 3D U-Net method showed reasonable segmentation accuracy and computational time. In addition, this method could be adapted and applied to severe lung diseases in a clinical workflow.

Heterogeneous clinical manifestations and progression of chronic obstructive pulmonary disease (COPD) affect patient health risk assessment, stratification, and management. Pulmonary function tests are used to diagnose and classify the severity of COPD, but they cannot fully represent the type or range of pathophysiologic abnormalities of the disease. To evaluate whether deep radiomics from chest computed tomography (CT) images can predict mortality in patients with COPD, we designed a convolutional neural network (CNN) model for extracting representative features from CT images and then performed random survival forest to predict survival in COPD patients. We trained CNN-based binary classifier based on six-minute walk distance results (> 440 m or not) and extracted high-throughput image features (i.e., deep radiomics) directly from the last fully connected layer of it. The various sizes of fully connected layers and combinations of deep features were experimented using a discovery cohort with 344 patients from the Korean Obstructive Lung Disease cohort and an external validation cohort with 102 patients from Penang General Hospital in Malaysia. In the integrative analysis of discovery and external validation cohorts, with combining 256 deep features from the coronal slice of the vertebral body and two sagittal slices of the left/right lung, deep radiomics for survival prediction achieved concordance indices of 0.8008 (95% CI, 0.7642–0.8373) and 0.7156 (95% CI, 0.7024–0.7288), respectively. Deep radiomics from CT images could be used to predict mortality in COPD patients.

To evaluate the effects of computer-aided diagnosis (CAD) on inter-reader agreement in Lung Imaging Reporting and Data System (Lung-RADS) categorization.Two hundred baseline CT scans covering all Lung-RADS categories were randomly selected from the National Lung Cancer Screening Trial. Five radiologists independently reviewed the CT scans and assigned Lung-RADS categories without CAD and with CAD. The CAD system presented up to five of the most risk-dominant nodules with measurements and predicted Lung-RADS category. Inter-reader agreement was analyzed using multirater Fleiss κ statistics.The five readers reported 139-151 negative screening results without CAD and 126-142 with CAD. With CAD, readers tended to upstage (average, 12.3%) rather than downstage Lung-RADS category (average, 4.4%). Inter-reader agreement of five readers for Lung-RADS categorization was moderate (Fleiss kappa, 0.60 [95% confidence interval, 0.57, 0.63]) without CAD, and slightly improved to substantial (Fleiss kappa, 0.65 [95% CI, 0.63, 0.68]) with CAD. The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% [201/371] vs. 63.6% [232/365]). The proportion of disagreement in nodule size measurement was reduced from 5.1% (102/2000) to 3.1% (62/2000) with the use of CAD (p0.001). In 31 cancer-positive cases, substantial management discrepancies (category 1/2 vs. 4A/B) between reader pairs decreased with application of CAD (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).Application of CAD demonstrated a minor improvement in inter-reader agreement of Lung-RADS category, while showing the potential to reduce measurement variability and substantial management change in cancer-positive cases.• Inter-reader agreement of five readers for Lung-RADS categorization was minimally improved by application of CAD, with a Fleiss kappa value of 0.60 to 0.65. • The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% vs. 63.6%). • In 31 cancer-positive cases, substantial management discrepancies between reader pairs, referring to a difference in follow-up interval of at least 9 months (category 1/2 vs. 4A/B), were reduced in half by application of CAD (32/310 to 16/310) (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).

Over the past few decades, pulmonary imaging technologies have advanced from chest radiography and nuclear medicine methods to high-spatial-resolution or low-dose chest CT and MRI. It is currently possible to identify and measure pulmonary pathologic changes before these are obvious even to patients or depicted on conventional morphologic images. Here, key technological advances are described, including multiparametric CT image processing methods, inhaled hyperpolarized and fluorinated gas MRI, and four-dimensional free-breathing CT and MRI methods to measure regional ventilation, perfusion, gas exchange, and biomechanics. The basic anatomic and physiologic underpinnings of these pulmonary functional imaging techniques are explained. In addition, advances in image analysis and computational and artificial intelligence (machine learning) methods pertinent to functional lung imaging are discussed. The clinical applications of pulmonary functional imaging, including both the opportunities and challenges for clinical translation and deployment, will be discussed in part 2 of this review. Given the technical advances in these sophisticated imaging methods and the wealth of information they can provide, it is anticipated that pulmonary functional imaging will be increasingly used in the care of patients with lung disease. © RSNA, 2021 Online supplemental material is available for this article.

OBJECTIVE Emphysema and small-airway disease are the two major components of chronic obstructive pulmonary disease (COPD). We propose a novel method of quantitative computed tomography (CT) emphysema air-trapping composite (EAtC) mapping to assess each COPD component. We analyzed the potential use of this method for assessing lung function in patients with COPD. MATERIALS AND METHODS A total of 584 patients with COPD underwent inspiration and expiration CTs. Using pairwise analysis of inspiration and expiration CTs with non-rigid registration, EAtC mapping classified lung parenchyma into three areas: Normal, functional air trapping (fAT), and emphysema (Emph). We defined fAT as the area with a density change of less than 60 Hounsfield units (HU) between inspiration and expiration CTs among areas with a density less than -856 HU on inspiration CT. The volume fraction of each area was compared with clinical parameters and pulmonary function tests (PFTs). The results were compared with those of parametric response mapping (PRM) analysis. RESULTS The relative volumes of the EAtC classes differed according to the Global Initiative for Chronic Obstructive Lung Disease stages (p < 0.001). Each class showed moderate correlations with forced expiratory volume in 1 second (FEV1) and FEV1/forced vital capacity (FVC) (r = -0.659-0.674, p < 0.001). Both fAT and Emph were significant predictors of FEV1 and FEV1/FVC (R² = 0.352 and 0.488, respectively; p < 0.001). fAT was a significant predictor of mean forced expiratory flow between 25% and 75% and residual volume/total vital capacity (R² = 0.264 and 0.233, respectively; p < 0.001), while Emph and age were significant predictors of carbon monoxide diffusing capacity (R² = 0.303; p < 0.001). fAT showed better correlations with PFTs than with small-airway disease on PRM. CONCLUSION The proposed quantitative CT EAtC mapping provides comprehensive lung functional information on each disease component of COPD, which may serve as an imaging biomarker of lung function.

In recent years, artificial intelligence (AI) technologies have greatly advanced and become a reality in many areas of our daily lives. In the health care field, numerous efforts are being made to implement the AI technology for practical medical treatments. With the rapid developments in machine learning algorithms and improvements in hardware performances, the AI technology is expected to play an important role in effectively analyzing and utilizing extensive amounts of health and medical data. However, the AI technology has various unique characteristics that are different from the existing health care technologies. Subsequently, there are a number of areas that need to be supplemented within the current health care system for the AI to be utilized more effectively and frequently in health care. In addition, the number of medical practitioners and public that accept AI in the health care is still low; moreover, there are various concerns regarding the safety and reliability of AI technology implementations. Therefore, this paper aims to introduce the current research and application status of AI technology in health care and discuss the issues that need to be resolved., Graphical Abstract

To develop and validate a CT-based radiomic model to simultaneously diagnose anaplastic lymphoma kinase (ALK) rearrangements and epidermal growth factor receptor (EGFR) mutation status of lung adenocarcinoma and to assess whether peritumoural radiomic features add value in the prediction of mutation status.503 patients with pathologically proven lung adenocarcinoma containing information on the mutation status were retrospectively included. Intratumoural and peritumoural radiomic features of the primary lesion were extracted from CT. We proposed two-level stepwise binary radiomics-based classification models to diagnose ALK (step1) and EGFR mutation status (step2). The performance of proposed models and added value of peritumoural radiomic features were evaluated by using the areas under receiver operating characteristic curves (AUC) and Obuchowski index in the development and validation sets.Regarding the prediction of ALK rearrangement, the diagnostic performance of the intratumoural radiomic model showed the AUC of 0.77 and 0.68 for the development and validation sets, respectively. As for EGFR mutation, the diagnostic performance of the intratumoural radiomic model showed the AUCs of 0.64 and 0.62 for the development and validation sets, respectively. The radiomics added value to the model based on clinical features (development set [radiomics + clinical model vs. clinical model]: Obuchowski index, 0.76 vs. 0.66, p0.001; validation set: 0.69 vs. 0.61, p = 0.075). Adding peritumoural features resulted in no improvement in terms of model performance.The CT radiomics-based model allowed the simultaneous prediction of the presence of ALK and EGFR mutations while adding value to the clinical features.

To evaluate a deep learning–based model using model-generated segmentation masks to differentiate invasive pulmonary adenocarcinoma (IPA) from preinvasive lesions or minimally invasive adenocarcinoma (MIA) on CT, making comparisons with radiologist-derived measurements of solid portion size. Four hundred eleven subsolid nodules (SSNs) (120 preinvasive lesions or MIAs and 291 IPAs) in 333 patients who underwent surgery between June 2010 and August 2016 were retrospectively included to develop the model (370 SSNs in 293 patients for training and 41 SSNs in 40 patients for tuning). Ninety SSNs of 2 cm or smaller (45 preinvasive lesions or MIAs and 45 IPAs) resected in 2018 formed a validation set. Six radiologists measured the solid portion of each nodule. Performances of the model and radiologists were assessed using receiver operating characteristics curve analysis. The deep learning model differentiated IPA from preinvasive lesions or MIA with areas under the curve (AUCs) of 0.914, 0.956, and 0.833 for the training, tuning, and validation sets, respectively. The mean AUC of the radiologists was 0.835 in the validation set, without significant differences between radiologists and the model (p = 0.97). The sensitivity, specificity, and accuracy of the model were 71% (32/45), 87% (39/45), and 79% (71/90), respectively, whereas the corresponding values of the radiologists were 75.2% (203/270), 76.7% (207/270), and 75.9% (410/540) with a 5-mm threshold for the solid portion size. The performance of the model for differentiating IPA from preinvasive lesions or MIA was comparable to that of the radiologists’ measurements of solid portion size. • A deep learning–based model differentiated IPA from preinvasive lesions or MIA with AUCs of 0.914 and 0.956 for the training and tuning sets, respectively. • In the validation set including subsolid nodules of 2 cm or smaller, the model showed an AUC of 0.833, being on par with the performance of the solid portion size measurements made by the radiologists (AUC, 0.835; p = 0.97). • SSNs with a solid portion measuring > 10 mm on CT showed a high probability of being IPA (positive predictive value, 93.5–100.0%).

To investigate whether CT slice thickness influences the performance of radiomics prognostic models in non-small-cell lung cancer (NSCLC) patients. CT images including 1-, 3-, and 5-mm slice thicknesses acquired from 311 patients who underwent surgical resection for NSCLC between May 2014 and December 2015 were evaluated. Tumor segmentation was performed on CT of each slice thickness and total 94 radiomics features (shape, tumor intensity, and texture) were extracted. The study population was temporally split into development (n = 185) and validation sets (n = 126) for prediction of disease-free survival (DFS). Three radiomics models were built from three different slice thickness datasets (Rad-1, Rad-3, and Rad-5), respectively. Model performance was assessed and compared in three slice thickness datasets and mixed slice thickness dataset using C-indices. In corresponding slice thickness datasets, the C-indices of Rad-1, Rad-3, and Rad-5 for prediction of DFS were 0.68, 0.70, and 0.68 in the development set, and 0.73, 0.73, and 0.76 in the validation set (p = 0.40–0.89 and 0.27–0.90, respectively). Performance of the models was not significantly changed when they were applied to different slice thicknesses data in the validation set (C-index, 0.73–0.76, 0.72–0.73, 0.75–0.76; p = 0.07–0.92). In the mixed slice thickness dataset, performances of the models were similar to or slightly lower than their performances in the corresponding slice thickness datasets (C-index, 0.72–0.75 vs. 0.73–0.76) in the validation set. The performance of radiomics models for predicting DFS in NSCLC patients was not significantly affected by CT slice thickness. • Three radiomics models based on 1-, 3-, and 5-mm CT datasets showed C-indices for predicting disease-free survival of 0.68–0.70 in the development set and 0.73–0.76 in the validation set, without statistical differences (p = 0.27–0.90). • Application of the radiomics models to different slice thickness datasets showed no significant differences in performance between the values in the prediction of disease-free survival (p = 0.07–0.99). • Three radiomics models based on 1-, 3-, and 5-mm CT datasets performed well in mixed slice thickness datasets, showing similar or slightly lower performances.

We propose a novel airway segmentation method in volumetric chest computed tomography (CT) and evaluate its performance on multiple datasets. The segmentation is performed voxel-by-voxel by a 2.5D convolutional neural net (2.5D CNN) trained in a supervised manner. To enhance the accuracy of the segmented airway tree, we simultaneously took three adjacent slices in each of the orthogonal directions including axial, sagittal, and coronal and fine-tuned the parameters that influence the tree length and the number of leakage. The gold standard of airway segmentation was generated by a semi-automated method using AVIEW™. The 2.5D CNN was trained and evaluated on a subset of inspiratory thoracic CT scans taken from the Korean obstructive lung disease study, which includes normal subjects and chronic obstructive pulmonary disease patients. The reliability and further practicality of our proposed method was demonstrated in multiple datasets. In eight test datasets collected by the same imaging protocol, the percentage detected tree length, false positive rate, and Dice similarity coefficient of our method were 92.16%, 7.74%, and 0.8997 ± 0.0892, respectively. In 20 test datasets of the EXACT’09 challenge, the percentage detected tree length was 60.1% and the false positive rate was 4.56%. Our fully automated (end-to-end) segmentation method could be applied in radiologic practice.

The term interstitial lung abnormalities refers to specific CT findings that are potentially compatible with interstitial lung disease in patients without clinical suspicion of the disease. Interstitial lung abnormalities are increasingly recognised as a common feature on CT of the lung in older individuals, occurring in 4-9% of smokers and 2-7% of non-smokers. Identification of interstitial lung abnormalities will increase with implementation of lung cancer screening, along with increased use of CT for other diagnostic purposes. These abnormalities are associated with radiological progression, increased mortality, and the risk of complications from medical interventions, such as chemotherapy and surgery. Management requires distinguishing interstitial lung abnormalities that represent clinically significant interstitial lung disease from those that are subclinical. In particular, it is important to identify the subpleural fibrotic subtype, which is more likely to progress and to be associated with mortality. This multidisciplinary Position Paper by the Fleischner Society addresses important issues regarding interstitial lung abnormalities, including standardisation of the definition and terminology; predisposing risk factors; clinical outcomes; options for initial evaluation, monitoring, and management; the role of quantitative evaluation; and future research needs.

To apply radiomics analysis for overall survival prediction in chronic obstructive pulmonary disease (COPD), and evaluate the performance of the radiomics signature (RS).This study included 344 patients from the Korean Obstructive Lung Disease (KOLD) cohort. External validation was performed on a cohort of 112 patients. In total, 525 chest CT-based radiomics features were semi-automatically extracted. The five most useful features for survival prediction were selected by least absolute shrinkage and selection operation (LASSO) Cox regression analysis and used to generate a RS. The ability of the RS for classifying COPD patients into high or low mortality risk groups was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis.The five features remaining after the LASSO analysis were %LAAA radiomics approach for survival prediction and risk stratification in COPD patients is feasible, and the constructed radiomics model demonstrated acceptable performance. The RS derived from chest CT data of COPD patients was able to effectively identify those at increased risk of mortality.• A total of 525 chest CT-based radiomics features were extracted and the five radiomics features of %LAA

Purpose Despite the high prevalence of pulmonary vascular alterations and their substantial impact on chronic obstructive pulmonary disease (COPD), tools for the direct in vivo assessment of pulmonary vascular alterations remain limited. Thus, the purpose of this study was to automatically extract pulmonary vessels from volumetric chest CT and evaluate the associations between the derived quantitative pulmonary vessel features and clinical parameters, including survival, in COPD patients. Methods This study included 344 adult COPD patients. Pulmonary vessels were automatically extracted from volumetric chest CT data. Quantitative pulmonary vessel features were obtained from various lung surface areas (LSAs), which are theoretical surface areas drawn at different depths from the pleural borders. The total number of vessels (Ntotal) and number of vessels with vessel area (VA) less than 5 mm2 (N Results The pulmonary vessels were automatically extracted with 100% technical success. Cox regression analysis showed Ntotal/LSA, N Conclusions The automated extraction of pulmonary vessels and their quantitative assessment are technically feasible. Various quantitative pulmonary vessel features demonstrated significant relationships with survival and PFT in COPD patients. Of the various quantitative features, the percentage of total VA measured at 18 mm depth from the pleural surface (%VA18mm) and the number of small vessels counted per 10 cm2 of LSA at 9 mm depth from the pleural surface (N

BACKGROUND AND OBJECTIVE Combined pulmonary fibrosis and emphysema (CPFE) is characterized by preserved lung volume and slower lung function decline. However, it is unclear at what extent emphysema begins to impact respiratory physiology and prognostic characteristics in idiopathic pulmonary fibrosis (IPF). We estimated the extent of emphysema that could be used to define CPFE in IPF. METHODS The extent of emphysema was observed on high-resolution computed tomography scans and measured by a texture-based automated quantification system in 209 IPF patients. We analysed the impact of differences in the extent of emphysema on the annual decline rate and prognostic significance of lung function parameters. RESULTS The extent of emphysema was ≥5% in 53 patients (25%), ≥10% in 23 patients (11%) and ≥15% in 12 patients (6%). Patients with emphysema to an extent of ≥5% were more frequently men and ever-smokers; they had more preserved lung volume and lower forced vital capacity (FVC) decline rates than those with no or trivial emphysema. The FVC decline rate was a significant predictor of mortality in patients with no or trivial emphysema (hazard ratio (HR): 0.933, P

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.

This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6–9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

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 (

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.

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%).

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.

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.

We propose the use of ensemble classifiers to overcome inter-scanner variations in the differentiation of regional disease patterns in high-resolution computed tomography (HRCT) images of diffuse interstitial lung disease patients obtained from different scanners. A total of 600 rectangular 20 × 20-pixel regions of interest (ROIs) on HRCT images obtained from two different scanners (GE and Siemens) and the whole lung area of 92 HRCT images were classified as one of six regional pulmonary disease patterns by two expert radiologists. Textual and shape features were extracted from each ROI and the whole lung parenchyma. For automatic classification, individual and ensemble classifiers were trained and tested with the ROI dataset. We designed the following three experimental sets: an intra-scanner study in which the training and test sets were from the same scanner, an integrated scanner study in which the data from the two scanners were merged, and an inter-scanner study in which the training and test sets were acquired from different scanners. In the ROI-based classification, the ensemble classifiers showed better (p

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.

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.

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 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.

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 investigate whether morphometric complexity in the lung can predict survival and act as a new prognostic marker in patients with chronic obstructive pulmonary disease (COPD). COPD (n = 302) patients were retrospectively reviewed. All patients underwent volumetric computed tomography and pulmonary function tests at enrollment (2005–2015). For complexity analysis, we applied power law exponent of the emphysema size distribution (Dsize) as well as box-counting fractal dimension (Dbox3D) analysis. Patients’ survival at February 2017 was ascertained. Univariate and multivariate Cox proportional hazards analyses were performed, and prediction performances of various combinatorial models were compared. Patients were 66 ± 6 years old, had 41 ± 28 pack-years’ smoking history and variable GOLD stages (n = 20, 153, 108 and 21 in stages I−IV). The median follow-up time was 6.1 years (range: 0.2−11.6 years). Sixty-three patients (20.9%) died, of whom 35 died of lung-related causes. In univariate Cox analysis, lower Dsize and Dbox3D were significantly associated with both all-cause and lung-related mortality (both p < 0.001). In multivariate analysis, the backward elimination method demonstrated that Dbox3D, along with age and the BODE index, was an independent predictor of survival (p = 0.014; HR, 2.08; 95% CI, 1.16–3.71). The contributions of Dsize and Dbox3D to the combinatorial survival model were comparable with those of the emphysema index and lung-diffusing capacity. Low morphometric complexity in the lung is a predictor of survival in patients with COPD. • A newly suggested method for quantifying lung morphometric complexity is feasible. • Morphometric complexity measured on chest CT images predicts COPD patients’ survival. • Complexity, diffusing capacity and emphysema index contribute similarly to the survival model.

A computer-aided differential diagnosis (CADD) system that distinguishes between usual interstitial pneumonia (UIP) and non-specific interstitial pneumonia (NSIP) using high-resolution computed tomography (HRCT) images was developed, and its results compared against the decision of a radiologist. Six local interstitial lung disease patterns in the images were determined, and 900 typical regions of interest were marked by an experienced radiologist. A support vector machine classifier was used to train and label the regions of interest of the lung parenchyma based on the texture and shape characteristics. Based on the regional classifications of the entire lung using HRCT, the distributions and extents of the six regional patterns were characterized through their CADD features. The disease division index of every area fraction combination and the asymmetric index between the left and right lungs were also evaluated. A second SVM classifier was employed to classify the UIP and NSIP, and features were selected through sequential-forward floating feature selection. For the evaluation, 54 HRCT images of UIP (n = 26) and NSIP (n = 28) patients clinically diagnosed by a pulmonologist were included and evaluated. The classification accuracy was measured based on a fivefold cross-validation with 20 repetitions using random shuffling. For comparison, thoracic radiologists assessed each case using HRCT images without clinical information or diagnosis. The accuracies of the radiologists’ decisions were 75 and 87%. The accuracies of the CADD system using different features ranged from 70 to 81%. Finally, the accuracy of the proposed CADD system after sequential-forward feature selection was 91%.

Background Computed tomography (CT)-guided percutaneous transthoracic core needle biopsy (PTNB) is typically performed at 120 kVp tube voltage. However, there is no study that has demonstrated diagnostic performance including ground-glass nodules and radiation dose reduction at lower tube voltage in large population. Purpose To retrospectively compare the diagnostic performance and radiation dose between 100 kVp and 120 kVp during CT-guided PTNB. Material and Methods This study included 393 PTNBs performed in 385 patients (Group I; 120 kVp) from March 2011 to September 2011 and 1368 PTNBs performed in 1318 patients (Group II; 100 kVp) from October 2011 to December 2013. The patients underwent CT-guided PTNB with the coaxial technique. Diagnostic performance, complication rate, and radiation dose were compared between two groups. Results Technical success was achieved in 391 of 393 PTNBs (99.5%) in Group I and in 1344 of 1368 PTNBs (98.2%) in Group II ( P = 0.09). The diagnostic accuracies for pulmonary lesions were not significantly different between two groups (97.1% [362/373] versus 96.2% [1202/1249], P = 0.458). Complication rate showed no significant differences between two groups in terms of pneumothorax (19.7% [77/391] versus 19.4% [261/1344], P = 0.904) and hemoptysis (2.3% [9/391] versus 3.2% [43/1344], P = 0.360). Among patients who developed pneumothorax, three patients (3.9%, 3/77) in Group I and eight patients (3.1%, 8/261) in Group II required treatment with drainage catheter. Nobody needed further treatment for hemoptysis in the two groups. The mean radiation dose was 1.5 ± 1.9 mSv in Group I and 0.7 ± 0.3 mSv in Group II ( P Conclusion The 100-kVp protocol for CT-guided PTNB showed significant benefit of radiation dose reduction while maintaining high diagnostic accuracy and safety.

Purpose To evaluate whether bronchoscopic lung volume reduction (BLVR) increases ventilation and therefore improves ventilation-perfusion (V/Q) mismatch. Materials and Methods All patients provided written informed consent to be included in this study, which was approved by the Institutional Review Board (2013-0368) of Asan Medical Center. The physiologic changes that occurred after BLVR were measured by using xenon-enhanced ventilation and iodine-enhanced perfusion dual-energy computed tomography (CT). Patients with severe emphysema plus hyperinflation who did not respond to usual treatments were eligible. Pulmonary function tests, the 6-minute walking distance (6MWD) test, quality of life assessment, and dual-energy CT were performed at baseline and 3 months after BLVR. The effect of BLVR was assessed with repeated-measures analysis of variance. Results Twenty-one patients were enrolled in this study (median age, 68 years; mean forced expiratory volume in 1 second [FEV