Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes.

Rationale: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96-4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66-4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (-88 ml/yr vs. -45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.

Central Role of CT in Management of Pulmonary Fibrosis.

With the approval of antifibrotic medications to treat patients with idiopathic pulmonary fibrosis and progressive pulmonary fibrosis, radiologists have an integral role in diagnosing these entities and guiding treatment decisions. CT features of early pulmonary fibrosis include irregular thickening of interlobular septa, pleura, and intralobular linear structures, with subsequent progression to reticular abnormality, traction bronchiectasis or bronchiolectasis, and honeycombing. CT patterns of fibrotic lung disease can often be reliably classified on the basis of the CT features and distribution of the condition. Accurate identification of usual interstitial pneumonia (UIP) or probable UIP patterns by radiologists can obviate the need for a tissue sample-based diagnosis. Other entities that can appear as a UIP pattern must be excluded in multidisciplinary discussion before a diagnosis of idiopathic pulmonary fibrosis is made. Although the imaging findings of nonspecific interstitial pneumonia and fibrotic hypersensitivity pneumonitis can overlap with those of a radiologic UIP pattern, these entities can often be distinguished by paying careful attention to the radiologic signs. Diagnostic challenges may include misdiagnosis of fibrotic lung disease due to pitfalls such as airspace enlargement with fibrosis, paraseptal emphysema, recurrent aspiration, and postinfectious fibrosis. The radiologist also plays an important role in identifying complications of pulmonary fibrosis-pulmonary hypertension, acute exacerbation, infection, and lung cancer in particular. In cases in which there is uncertainty regarding the clinical and radiologic diagnoses, surgical biopsy is recommended, and a multidisciplinary discussion among clinicians, radiologists, and pathologists can be used to address diagnosis and management strategies. This review is intended to help radiologists diagnose and manage pulmonary fibrosis more accurately, ultimately aiding in the clinical management of affected patients. ©RSNA, 2024 Supplemental material is available for this article.

Long-Term Follow-Up of Interstitial Lung Abnormality: Implication in Follow-Up Strategy and Risk Thresholds.

Rationale: The optimal follow-up computed tomography (CT) interval for detecting the progression of interstitial lung abnormality (ILA) is unknown. Objectives: To identify optimal follow-up strategies and extent thresholds on CT relevant to outcomes. Methods: This retrospective study included self-referred screening participants aged 50 years or older, including nonsmokers, who had imaging findings relevant to ILA on chest CT scans. Consecutive CT scans were evaluated to determine the dates of the initial CT showing ILA and the CT showing progression. Deep learning-based ILA quantification was performed. Cox regression was used to identify risk factors for the time to ILA progression and progression to usual interstitial pneumonia (UIP). Measurements and Main Results: Of the 305 participants with a median follow-up duration of 11.3 years (interquartile range, 8.4-14.3 yr), 239 (78.4%) had ILA on at least one CT scan. In participants with serial follow-up CT studies, ILA progression was observed in 80.5% (161 of 200), and progression to UIP was observed in 17.3% (31 of 179), with median times to progression of 3.2 years (95% confidence interval [CI], 3.0-3.4 yr) and 11.8 years (95% CI, 10.8-13.0 yr), respectively. The extent of fibrosis on CT was an independent risk factor for ILA progression (hazard ratio, 1.12 [95% CI, 1.02-1.23]) and progression to UIP (hazard ratio, 1.39 [95% CI, 1.07-1.80]). Risk groups based on honeycombing and extent of fibrosis (1% in the whole lung or 5% per lung zone) showed significant differences in 10-year overall survival (P = 0.02). Conclusions: For individuals with initially detected ILA, follow-up CT at 3-year intervals may be appropriate to monitor radiologic progression; however, those at high risk of adverse outcomes on the basis of the quantified extent of fibrotic ILA and the presence of honeycombing may benefit from shortening the interval for follow-up scans.

Interstitial Lung Abnormalities at CT in the Korean National Lung Cancer Screening Program: Prevalence and Deep Learning-based Texture Analysis.

Background Interstitial lung abnormalities (ILAs) are associated with worse clinical outcomes, but ILA with lung cancer screening CT has not been quantitatively assessed. Purpose To determine the prevalence of ILA at CT examinations from the Korean National Lung Cancer Screening Program and define an optimal lung area threshold for ILA detection with CT with use of deep learning-based texture analysis. Materials and Methods This retrospective study included participants who underwent chest CT between April 2017 and December 2020 at two medical centers participating in the Korean National Lung Cancer Screening Program. CT findings were classified by three radiologists into three groups: no ILA, equivocal ILA, and ILA (fibrotic and nonfibrotic). Progression was evaluated between baseline and last follow-up CT scan. The extent of ILA was assessed visually and quantitatively with use of deep learning-based texture analysis. The Youden index was used to determine an optimal cutoff value for detecting ILA with use of texture analysis. Demographics and ILA subcategories were compared between participants with progressive and nonprogressive ILA. Results A total of 3118 participants were included in this study, and ILAs were observed with the CT scans of 120 individuals (4%). The median extent of ILA calculated by the quantitative system was 5.8% for the ILA group, 0.7% for the equivocal ILA group, and 0.1% for the no ILA group (P < .001). A 1.8% area threshold in a lung zone for quantitative detection of ILA showed 100% sensitivity and 99% specificity. Progression was observed in 48% of visually assessed fibrotic ILAs (15 of 31), and quantitative extent of ILA increased by 3.1% in subjects with progression. Conclusion ILAs were detected in 4% of the Korean lung cancer screening population. Deep learning-based texture analysis showed high sensitivity and specificity for detecting ILA with use of a 1.8% lung area cutoff value. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Egashira and Nishino in this issue.

Deep Learning-based Approach to Predict Pulmonary Function at Chest CT.

Background Low-dose chest CT screening is recommended for smokers with the potential for lung function abnormality, but its role in predicting lung function remains unclear. Purpose To develop a deep learning algorithm to predict pulmonary function with low-dose CT images in participants using health screening services. Materials and Methods In this retrospective study, participants underwent health screening with same-day low-dose CT and pulmonary function testing with spirometry at a university affiliated tertiary referral general hospital between January 2015 and December 2018. The data set was split into a development set (model training, validation, and internal test sets) and temporally independent test set according to first visit year. A convolutional neural network was trained to predict the forced expiratory volume in the first second of expiration (FEV1) and forced vital capacity (FVC) from low-dose CT. The mean absolute error and concordance correlation coefficient (CCC) were used to evaluate agreement between spirometry as the reference standard and deep-learning prediction as the index test. FVC and FEV1 percent predicted (hereafter, FVC% and FEV1%) values less than 80% and percent of FVC exhaled in first second (hereafter, FEV1/FVC) less than 70% were used to classify participants at high risk. Results A total of 16 148 participants were included (mean age, 55 years ± 10 [SD]; 10 981 men) and divided into a development set (n = 13 428) and temporally independent test set (n = 2720). In the temporally independent test set, the mean absolute error and CCC were 0.22 L and 0.94, respectively, for FVC and 0.22 L and 0.91 for FEV1. For the prediction of the respiratory high-risk group, FVC%, FEV1%, and FEV1/FVC had respective accuracies of 89.6% (2436 of 2720 participants; 95% CI: 88.4, 90.7), 85.9% (2337 of 2720 participants; 95% CI: 84.6, 87.2), and 90.2% (2453 of 2720 participants; 95% CI: 89.1, 91.3) in the same testing data set. The sensitivities were 61.6% (242 of 393 participants; 95% CI: 59.7, 63.4), 46.9% (226 of 482 participants; 95% CI: 45.0, 48.8), and 36.1% (91 of 252 participants; 95% CI: 34.3, 37.9), respectively. Conclusion A deep learning model applied to volumetric chest CT predicted pulmonary function with relatively good performance. © RSNA, 2023 Supplemental material is available for this article.

Content-based Image Retrieval by Using Deep Learning for Interstitial Lung Disease Diagnosis with Chest CT.

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]; P < .001). In terms of disease category, the diagnostic accuracy improved after applying CBIR in UIP (before vs after CBIR, 52.4% vs 72.8%, respectively; P < .001) and NSIP cases (before vs after CBIR, 42.9% vs 61.6%, respectively; P < .001). Interreader agreement improved after CBIR (before vs after CBIR Fleiss κ, 0.32 vs 0.47, respectively; P = .005). Conclusion The proposed content-based image retrieval system for chest CT images with deep learning improved the diagnostic accuracy of interstitial lung disease and interreader agreement in readers with different levels of experience. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Wielpütz in this issue.

Artificial Intelligence in Lung Imaging.

Recently, interest and advances in artificial intelligence (AI) including deep learning for medical images have surged. As imaging plays a major role in the assessment of pulmonary diseases, various AI algorithms have been developed for chest imaging. Some of these have been approved by governments and are now commercially available in the marketplace. In the field of chest radiology, there are various tasks and purposes that are suitable for AI: initial evaluation/triage of certain diseases, detection and diagnosis, quantitative assessment of disease severity and monitoring, and prediction for decision support. While AI is a powerful technology that can be applied to medical imaging and is expected to improve our current clinical practice, some obstacles must be addressed for the successful implementation of AI in workflows. Understanding and becoming familiar with the current status and potential clinical applications of AI in chest imaging, as well as remaining challenges, would be essential for radiologists and clinicians in the era of AI. This review introduces the potential clinical applications of AI in chest imaging and also discusses the challenges for the implementation of AI in daily clinical practice and future directions in chest imaging.

Lobar Ventilation in Patients with COPD Assessed with the Full-Scale Airway Network Flow Model and Xenon-enhanced Dual-Energy CT.

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. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Parraga and Eddy in this issue.

Invasive Pulmonary Aspergillosis in Patients With Severe Fever With Thrombocytopenia Syndrome.

Sixteen of 45 patients with severe fever with thrombocytopenia (36%) were admitted to an intensive care unit; 9 (56%) developed invasive pulmonary aspergillosis (IPA) within a median of 8 days (range, 2-11). Mortality was higher in the IPA vs non-IPA patients and in those without vs with antifungal therapy.

Differentiation of predominant subtypes of lung adenocarcinoma using a quantitative radiomics approach on CT.

OBJECTIVES: 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. METHODS: 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). RESULTS: 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%). CONCLUSIONS: Predominant subtype-based prognostic groups of lung adenocarcinoma were classified by a CT-based radiomic model with comparable performance to radiologists. KEY POINTS: • 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%).

Assessment of regional emphysema, air-trapping and Xenon-ventilation using dual-energy computed tomography in chronic obstructive pulmonary disease patients.

OBJECTIVES: To compare the parenchymal attenuation change between inspiration/expiration CTs with dynamic ventilation change between xenon wash-in (WI) inspiration and wash-out (WO) expiration CTs. METHODS: 52 prospectively enrolled COPD patients underwent xenon ventilation dual-energy CT during WI and WO periods and pulmonary function tests (PFTs). The parenchymal attenuation parameters (emphysema index (EI), gas-trapping index (GTI) and air-trapping index (ATI)) and xenon ventilation parameters (xenon in WI (Xe-WI), xenon in WO (Xe-WO) and xenon dynamic (Xe-Dyna)) of whole lung and three divided areas (emphysema, hyperinflation and normal) were calculated on virtual non-contrast images and ventilation images. Pearson correlation, linear regression analysis and one-way ANOVA were performed. RESULTS: EI, GTI and ATI showed a significant correlation with Xe-WI, Xe-WO and Xe-Dyna (EI R = -.744, -.562, -.737; GTI R = -.621, -.442, -.629; ATI R = -.600, -.421, -.610, respectively, p < 0.01). All CT parameters showed significant correlation with PFTs except forced vital capacity (FVC). There was a significant difference in GTI, ATI and Xe-Dyna in each lung area (p < 0.01). CONCLUSIONS: The parenchymal attenuation change between inspiration/expiration CTs and xenon dynamic change between xenon WI- and WO-CTs correlate significantly. There are alterations in the dynamics of xenon ventilation between areas of emphysema. KEY POINTS: • The xenon ventilation change correlates with the parenchymal attenuation change. • The xenon ventilation change shows the difference between three lung areas. • The combination of attenuation and xenon can predict more accurate PFTs.

Advanced adenocarcinoma of the lung: comparison of CT characteristics of patients with anaplastic lymphoma kinase gene rearrangement and those with epidermal growth factor receptor mutation.

PURPOSE: To study the differences in computed tomographic (CT) characteristics between patients with advanced lung adenocarcinoma who have anaplastic lymphoma kinase (ALK) gene rearrangement and those who have epidermal growth factor receptor (EGFR) mutations. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board. Informed consent was waived. Patients with stage IV adenocarcinoma (n = 198) were enrolled from November 2004 to December 2013, including 68 patients with ALK rearrangement and 130 with EGFR mutation. Two independent radiologists evaluated the main tumor in each patient and determined its size, type, margins, lymph node metastasis, and intrathoracic metastasis (lung, pleural or pericardial, or bone). A multiple logistic regression model was applied to discriminate clinical and CT characteristics between the types of mutation. RESULTS: The κ index for assessment of tumor and node stage between radiologists was 0.8530 to 0.9388. Most of the main tumors in patients with both types of mutation appeared as solid masses. In univariate analysis, patients with an ALK rearrangement were younger (P < .001) and were more likely to be men (P = .001), to have never smoked (P = .002), and to have pleural or pericardial metastases (P < .05) compared with those with EGFR mutations. In multivariate analysis, lobulated margins (odds ratio, 4.815; 95% confidence interval [CI]: 1.789, 12.961; P = .002), N2 or N3 lymph node involvement (odds ratio, 2.445; 95% CI: 1.005, 5.950; P = .049), and lymphangitic lung metastasis (odds ratio, 8.485; 95% CI: 2.238, 32.170; P = .002) were more common in patients with ALK rearrangement than in those with EGFR mutation. The area under the receiver operating characteristic curve was 0.855. CONCLUSION: Adenocarcinomas with ALK rearrangement appeared as solid masses with lobulated margins at CT and were more likely to be associated with lymphangitic metastasis, advanced lymph node metastasis, and pleural or pericardial metastasis than were tumors with EGFR mutations.

Detailed analysis of the density change on chest CT of COPD using non-rigid registration of inspiration/expiration CT scans.

OBJECTIVES: One objective was to evaluate the air trapping index (ATI), measured by inspiration/expiration CT, in COPD patients and nonsmokers. Another objective was to assess the association between the pulmonary function test (PFT) and CT parameters such as ATI or other indices, separately in the whole lung, in emphysema, and in hyperinflated and normal lung areas. METHODS: One hundred and thirty-eight COPD patients and 29 nonsmokers were included in our study. The ATI, the emphysema index (EI), the gas trapping index (Exp -856) and expiration/inspiration ratio of mean lung density (E/Iratio of MLD) were measured on CT. The values of the whole lung, of emphysema, and of hyperinflated and normal lung areas were compared and then correlated with various PFT parameters. RESULTS: Compared with nonsmokers, COPD patients showed a higher ATI in the whole lung and in each lung lesion (all P < 0.05). The ATI showed a higher correlation than EI with FEF25-75%, RV and RV/TLC, and was comparable to Exp -856 and the E/I ratio of MLD. The ATI of emphysema and hyperinflated areas on CT showed better correlation than the normal lung area with PFT parameters. CONCLUSIONS: Detailed analysis of density change at inspiration and expiration CT of COPD can provide new insights into pulmonary functional impairment in each lung area. KEY POINTS: • COPD patients show significant air trapping in the lung. • The air trapping index is a comparable parameter to other CT indices. • Air trapping of emphysema and hyperinflated lung areas relates to functional loss. • The emphysema area changes more, with less air trapping than other areas.

Comparison of a New Integral-Based Half-Band Method for CT Measurement of Peripheral Airways in COPD With a Conventional Full-Width Half-Maximum Method Using Both Phantom and Clinical CT Images.

OBJECTIVES: To compare a new integral-based half-band method (IBHB) and a conventional full-width half-maximum (FWHM) method in measuring peripheral airway dimensions at airway phantoms and thin-section computed tomography of chronic obstructive pulmonary disease (COPD). METHODS: The IBHB was validated and compared using airway phantoms and 50 patients with COPD. Airway parameters (wall area percentage [WA%], mean lumen radius, and mean wall thickness) were measured at fourth to sixth generations of the right apical bronchus. Matched results from 2 methods were compared and correlated with forced expiratory volume (FEV) in 1 second (FEV1), FEV1 / forced vital capacity (FVC), and global initiative for chronic obstructive lung disease (GOLD) stage. Linear regression analysis was performed using airway dimensions and emphysema index. RESULTS: The IBHB generated more accurate measurements at phantom study. Measured airway parameters by both methods at thin-section computed tomography study were significantly different (all P < 0.05, paired t test). The IBHB method-measured WA% and wall thickness were significantly smaller. Mean WA% with IBHB also showed better correlation than that with FWHM (FEV1, r = -0.52 vs -0.28; FEV1 / FVC, r = -0.41 vs r = -0.20; GOLD, 0.52 vs 0.33, respectively). Linear regression analysis revealed fifth-generation WA% measured by IBHB was an independent variable, and addition to emphysema index increased predictability (FEV1, r = 0.63; FEV1 / FVC, r = 0.61; GOLD, r = 0.70). CONCLUSIONS: The new IBHB measured peripheral airway dimensions differently than FWHM and showed better correlations with functional parameters in COPD.

Nontuberculous mycobacterial pulmonary infection in patients with idiopathic interstitial pneumonias: comparison with patients without idiopathic interstitial pneumonias.

OBJECTIVE: The aim of this study was to describe computed tomography (CT) findings of nontuberculous mycobacterial (NTM) pulmonary infection in patients with idiopathic interstitial pneumonias (IIP) in comparison with those in patients without IIP. METHODS: From November 2001 to October 2012, 810 patients in the NTM registry were retrospectively reviewed. Among them, 42 patients (mean age, 69.7 years; 32 men and 10 women) who were diagnosed as having IIP by either histological or radioclinical criteria were included in our study. Eighty-two age- and sex-matched immunocompetent patients with NTM pulmonary infection and without IIP were selected as the control group. Medical records and CT scans were reviewed. Formal radiologic reports obtained before diagnosis of NTM infection were also reviewed. RESULTS: Lobar/segmental consolidation (85.7%) was the most common CT finding in the IIP group, whereas branching centrilobular nodules (95.1%), traction bronchiectasis (79.3%), and volume decrease (58.5%) were common in the control group. Frequencies of these findings were significantly different between the 2 groups (P < 0.001). Most of consolidations were associated with cavity (83.3%) without dominant zonal distribution. Pneumonia or fungal infection (n = 20) was the most common radiologic diagnosis in the IIP group. CONCLUSIONS: The NTM pulmonary infection in IIP patients is characterized as lobar/segmental consolidation with/without cavity, different to immunocompetent patients without IIP, and can mimic other diseases especially bacterial/fungal infection.

The textures of sarcoidosis: quantifying lung disease through variograms.

Objective: Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis. Approach: For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline. Main results: We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC ≈ 0.9, p ≪ 0.0001 in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner. Significance: Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.

Evaluation of retrieval accuracy and visual similarity in content-based image retrieval of chest CT for obstructive lung disease.

The aim of our study was to assess the performance of content-based image retrieval (CBIR) for similar chest computed tomography (CT) in obstructive lung disease. This retrospective study included patients with obstructive lung disease who underwent volumetric chest CT scans. The CBIR database included 600 chest CT scans from 541 patients. To assess the system performance, follow-up chest CT scans of 50 patients were evaluated as query cases, which showed the stability of the CT findings between baseline and follow-up chest CT, as confirmed by thoracic radiologists. The CBIR system retrieved the top five similar CT scans for each query case from the database by quantifying and comparing emphysema extent and size, airway wall thickness, and peripheral pulmonary vasculatures in descending order from the database. The rates of retrieval of the same pairs of query CT scans in the top 1-5 retrievals were assessed. Two expert chest radiologists evaluated the visual similarities between the query and retrieved CT scans using a five-point scale grading system. The rates of retrieving the same pairs of query CTs were 60.0% (30/50) and 68.0% (34/50) for top-three and top-five retrievals. Radiologists rated 64.8% (95% confidence interval 58.8-70.4) of the retrieved CT scans with a visual similarity score of four or five and at least one case scored five points in 74% (74/100) of all query cases. The proposed CBIR system for obstructive lung disease integrating quantitative CT measures demonstrated potential for retrieving chest CT scans with similar imaging phenotypes. Further refinement and validation in this field would be valuable.

Percutaneous CT-guided aspiration and core biopsy of pulmonary nodules smaller than 1 cm: analysis of outcomes of 305 procedures from a tertiary referral center.

OBJECTIVE: We conducted a retrospective analysis to evaluate the diagnostic outcomes of CT-guided aspiration and core biopsy of 305 pulmonary nodules measuring less than 1 cm. MATERIALS AND METHODS: We determined the diagnostic yield of using CT-guided aspiration and core biopsy to analyze 305 lesions in 290 patients. Diagnostic performance was evaluated according to the biopsy method, including aspiration alone, core biopsy alone, and combination use, and the consistency of the nodule, including solid, partly solid ground-glass opacity (GGO), and pure GGO. Final diagnoses were established in 268 of the 305 lesions (87.9%). Nondiagnostic biopsy results were obtained for 27 of the 268 lesions (10.1%). RESULTS: The overall sensitivity, specificity, positive predictive value, and negative predictive value for the diagnosis of malignancy were 93.1% (148 of 159 lesions), 98.8% (81/82), 99.3% (148/149), and 88.0% (81/92), respectively; diagnostic accuracy was 95.0% (229/241). Using multivariate logistic regression analysis, we found that aspiration alone was a significant independent risk factor associated with diagnostic failure (odds ratio, 3.199; p = 0.001). CONCLUSION: The use of CT-guided aspiration and core biopsy resulted in a high diagnostic yield for pulmonary nodules smaller than 1 cm. The use of the aspiration method alone was an independent risk factor associated with diagnostic failure.

Low-dose chest computed tomography with sinogram-affirmed iterative reconstruction, iterative reconstruction in image space, and filtered back projection: studies on image quality.

OBJECTIVE: This study aimed to determine optimal strength of sinogram-affirmed iterative reconstruction (SAFIRE) and to evaluate image quality (IQ) of low-dose chest computed tomography (LDCT) using SAFIRE compared with iterative reconstruction in image space (IRIS) and filtered back projection (FBP). METHODS: Thirty patients underwent LDCT. Computed tomography (CT) was reconstructed using 5 strengths of SAFIRE (S1-S5), IRIS, and FBP. Objective noise of CT was measured. Two radiologists evaluated CT for subjective IQ, beam-hardening artifacts, and overall IQ. RESULTS: Measured noise was highest in FBP, followed by S1, S2, S3, IRIS, S4, and S5. S2 and S3 demonstrated significantly higher overall IQ scores than the other strengths (P < 0.05). Overall IQ and beam-hardening artifacts of S2 and S3 were significantly better than those in FBP and IRIS (P < 0.001). CONCLUSIONS: S2 or S3 strengths of SAFIRE can be used practically in clinical routines and may have more potential than IRIS and FBP for LDCT with improved IQ.