Journal of Thoracic Imaging最新文献

{"title":"Chest Computed Tomography-Based Radiomics and Machine Learning for Classifying Mediastinal Lymphadenopathy Caused By Hematologic Malignancies and Metastatic Abdominopelvic Solid Cancers.","authors":"Haoru Wang, Qian Hu, Yingxue Tong, Huiru Zhu, Ling He, Jinhua Cai","doi":"10.1097/RTI.0000000000000860","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000860","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the role of chest CT radiomics in classifying mediastinal lymphadenopathy caused by hematologic malignancies and abdominopelvic solid cancers.</p><p><strong>Materials and methods: </strong>A total of 231 patients with mediastinal lymphadenopathy were selected from the Mediastinal-Lymph-Node-SEG collection in The Cancer Imaging Archive, including 145 patients with hematologic malignancies (74 with chronic lymphocytic leukemia and 71 with lymphoma) and 86 with abdominopelvic solid cancers. Patients were randomly stratified into train and test sets in a 7:3 ratio. Radiomics features were extracted from enhanced CT images of mediastinal lymph nodes, followed by feature selection using univariate analysis and least absolute shrinkage and selection operator regression. A support vector machine algorithm was used to develop classification models, with performance evaluated using the area under the receiver operating characteristic curve (AUC-ROC), accuracy, and 95% CI.</p><p><strong>Results: </strong>For differentiating mediastinal lymphadenopathy between hematologic malignancies and abdominopelvic solid cancers, the model incorporated 23 features and achieved an AUC-ROC of 0.931 (95% CI: 0.891-0.971) and an accuracy of 0.866 in the train set, and an AUC-ROC of 0.830 (95% CI: 0.730-0.929) and an accuracy of 0.759 in the test set. For distinguishing chronic lymphocytic leukemia from lymphoma, the model utilized 4 features, achieving an AUC-ROC of 0.880 (95% CI: 0.813-0.947) and an accuracy of 0.752 in the train set, and an AUC-ROC of 0.872 (95% CI: 0.763-0.982) and an accuracy of 0.836 in the test set.</p><p><strong>Conclusions: </strong>Chest CT radiomics shows promise for classifying mediastinal lymphadenopathy in patients with hematologic malignancies and abdominopelvic solid cancers.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Case of Incidentally Discovered Primary Pulmonary Vein Stenosis in an Adult.","authors":"Hyunjin Kim, Takeshi Kubo, Akihiro Ikeda, Yoshihiro Yamasaki, Kango Kawase, Sumire Haga, Yuri Nakamura, Naoki Yamashita, Mizue Suzuki, Shunsuke Yuge, Rie Ota, Yusuke Yokota, Masaki Imaeda, Ayako Saito, Gosuke Okubo, Shotaro Kanao, Takanori Taniguchi, Satoshi Noma","doi":"10.1097/RTI.0000000000000857","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000857","url":null,"abstract":"<p><p>Primary pulmonary vein stenosis (PPVS) in adults is rare and often incidentally detected on imaging. A 60-year-old man underwent chest CT for respiratory symptoms, revealing a localized reticulonodular opacity in the right upper lung field near the pulmonary hilum. Coronal and sagittal reconstructions demonstrated tortuous collateral veins bridging the right superior and inferior pulmonary veins. Mediastinal-window images confirmed severe stenosis of the proximal right superior pulmonary vein without evidence of external compression or congenital anomaly. As symptoms resolved spontaneously, conservative management was chosen. This case demonstrates that axial reticulonodular opacities can raise suspicion of PPVS, with multiplanar and mediastinal-window imaging enabling accurate diagnosis of this rare condition.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence in Low-Dose Computed Tomography Screening of the Chest: Past, Present, and Future.","authors":"Rowena Yip, Artit Jirapatnakul, Ricardo Avila, Jessica Gonzalez Gutierrez, Morteza Naghavi, David F Yankelevitz, Claudia I Henschke","doi":"10.1097/RTI.0000000000000854","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000854","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) with low-dose computed tomography (LDCT) has the potential to transform lung cancer screening into a comprehensive approach to early detection of multiple diseases. Building on over 3 decades of research and global implementation by the International Early Lung Cancer Action Program (I-ELCAP), this paper reviews the development and clinical integration of AI for interpreting LDCT scans. We describe the historical milestones in AI-assisted lung nodule detection, emphysema quantification, and cardiovascular risk assessment using visual and quantitative imaging features. We also discuss challenges related to image acquisition variability, ground truth curation, and clinical integration, with a particular focus on the design and implementation of the open-source IELCAP-AIRS system and the ScreeningPLUS infrastructure, which enable AI training, validation, and deployment in real-world screening environments. AI algorithms for rule-out decisions, nodule tracking, and disease quantification have the potential to reduce radiologist workload and advance precision screening. With the ability to evaluate multiple diseases from a single LDCT scan, AI-enabled screening offers a powerful, scalable tool for improving population health. Ongoing collaboration, standardized protocols, and large annotated datasets are critical to advancing the future of integrated, AI-driven preventive care.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145193695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Empowering Radiologists With ChatGPT-4o: Comparative Evaluation of Large Language Models and Radiologists in Cardiac Cases.","authors":"Turay Cesur, Yasin Celal Gunes, Eren Camur, Mustafa Dağli","doi":"10.1097/RTI.0000000000000846","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000846","url":null,"abstract":"<p><strong>Purpose: </strong>This study evaluated the diagnostic accuracy and differential diagnostic capabilities of 12 Large Language Models (LLMs), one cardiac radiologist, and 3 general radiologists in cardiac radiology. The impact of the ChatGPT-4o assistance on radiologist performance was also investigated.</p><p><strong>Materials and methods: </strong>We collected publicly available 80 \"Cardiac Case of the Month\" from the Society of Thoracic Radiology website. LLMs and Radiologist-III were provided with text-based information, whereas other radiologists visually assessed the cases with and without the ChatGPT-4o assistance. Diagnostic accuracy and differential diagnosis scores (DDx scores) were analyzed using the χ2, Kruskal-Wallis, Wilcoxon, McNemar, and Mann-Whitney U tests.</p><p><strong>Results: </strong>The unassisted diagnostic accuracy of the cardiac radiologist was 72.5%, general radiologist-I was 53.8%, and general radiologist-II was 51.3%. With ChatGPT-4o, the accuracy improved to 78.8%, 70.0%, and 63.8%, respectively. The improvements for general radiologists-I and II were statistically significant (P≤0.006). All radiologists' DDx scores improved significantly with ChatGPT-4o assistance (P≤0.05). Remarkably, Radiologist-I's GPT-4o-assisted diagnostic accuracy and DDx score were not significantly different from the Cardiac Radiologist's unassisted performance (P>0.05).Among the LLMs, Claude 3 Opus and Claude 3.5 Sonnet had the highest accuracy (81.3%), followed by Claude 3 Sonnet (70.0%). Regarding the DDx score, Claude 3 Opus outperformed all models and radiologist-III (P<0.05). The accuracy of the general radiologist-III significantly improved from 48.8% to 63.8% with GPT4o assistance (P<0.001).</p><p><strong>Conclusions: </strong>ChatGPT-4o may enhance the diagnostic performance of general radiologists in cardiac imaging, suggesting its potential as a diagnostic support tool. Further studies are required to assess the clinical integration.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incidental Cardiovascular Findings in Lung Cancer Screening and Noncontrast Chest Computed Tomography.","authors":"Matthew D Cham, Joseph Shemesh","doi":"10.1097/RTI.0000000000000853","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000853","url":null,"abstract":"<p><p>While the primary goal of lung cancer screening CT is to detect early-stage lung cancer in high-risk populations, it often reveals asymptomatic cardiovascular abnormalities that can be clinically significant. These findings include coronary artery calcifications (CACs), myocardial pathologies, cardiac chamber enlargement, valvular lesions, and vascular disease. CAC, a marker of subclinical atherosclerosis, is particularly emphasized due to its strong predictive value for cardiovascular events and mortality. Guidelines recommend qualitative or quantitative CAC scoring on all noncontrast chest CTs. Other actionable findings include aortic aneurysms, pericardial disease, and myocardial pathology, some of which may indicate past or impending cardiac events. This article explores the wide range of incidental cardiovascular findings detectable during low-dose CT (LDCT) scans for lung cancer screening, as well as noncontrast chest CT scans. Distinguishing which findings warrant further evaluation is essential to avoid overdiagnosis, unnecessary anxiety, and resource misuse. The article advocates for a structured approach to follow-up based on the clinical significance of each finding and the patient's overall risk profile. It also notes the rising role of artificial intelligence in automatically detecting and quantifying these abnormalities, potentiating early behavioral modification or medical and surgical interventions. Ultimately, this piece highlights the opportunity to reframe LDCT as a comprehensive cardiothoracic screening tool.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Dose Computed Tomography Screening for Lung Cancer in Asia, Including Never-Smokers.","authors":"Natthaya Triphuridet","doi":"10.1097/RTI.0000000000000850","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000850","url":null,"abstract":"<p><p>Lung cancer in never-smokers (LCINS) presents a distinct epidemiological profile in Asia, with a higher proportion of cases occurring in never-smoking women. This review examines the evidence for lung cancer screening in this population, synthesizing data on risk factors, LDCT screening, and current guidelines across Asian countries. Challenges such as overdiagnosis and economic limitations to screening implementation are discussed, and future research directions, including risk prediction and tailored screening, are highlighted.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality, Standards, and Optimal Training of Radiologists for Lung Cancer Screening.","authors":"Dorith Shaham, Ella A Kazerooni","doi":"10.1097/RTI.0000000000000844","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000844","url":null,"abstract":"<p><p>Lung cancer screening (LCS) with low-dose computed tomography (LDCT) has been shown to detect lung cancer at an earlier stage and to reduce mortality among high-risk populations, as demonstrated by major trials including I-ELCAP, NLST, and NELSON. These findings have led to the implementation of national screening programs worldwide. This article outlines the critical components required for the successful implementation of high-quality LCS programs, with a particular focus on quality assurance (QA) mechanisms and radiologist training. Structured radiologist training is essential to ensure the accuracy and effectiveness of LDCT screening. As these requirements are universal, online initiatives such as the I-ELCAP Teaching File, ESTI Lung Cancer Certification Project, and the UK's PERFECTS EQA platform provide scalable models for enhancing radiologic performance in LCS. The success of lung cancer screening programs depends not only on access and infrastructure but also on rigorous training and quality oversight. International collaboration and the adoption of validated educational and QA tools are key to optimizing outcomes and maintaining diagnostic excellence in LDCT-based screening.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145071000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable Machine Learning for Estimating the Contrast Material Arrival Time in Computed Tomography Pulmonary Angiography.","authors":"Xiang-Pan Meng, Haomei Yu, Changjie Pan, Fang-Ming Chen, Xiaofeng Li, Jianliang Wang, Chunhong Hu, Xiangming Fang","doi":"10.1097/RTI.0000000000000848","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000848","url":null,"abstract":"<p><strong>Purpose: </strong>To establish an explainable machine learning (ML) approach using patient-related and noncontrast chest CT-derived features to predict the contrast material arrival time (TARR) in CT pulmonary angiography (CTPA).</p><p><strong>Materials and methods: </strong>This retrospective study included consecutive patients referred for CTPA between September 2023 to October 2024. Sixteen clinical and 17 chest CT-derived parameters were used as inputs for the ML approach, which employed recursive feature elimination for feature selection and XGBoost with SHapley Additive exPlanations (SHAP) for explainable modeling. The prediction target was abnormal TARR of the pulmonary artery (ie, TARR <7 seconds or >10 s), determined by the time to peak enhancement in the test bolus, with 2 models distinguishing these cases. External validation was conducted. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>A total of 666 patients (mean age, 70 [IQR, 59.3 to 78.0]; 46.8% female participants) were split into training (n = 353), testing (n = 151), and external validation (n = 162) sets. 86 cases (12.9%) had TARR <7 seconds, and 138 cases (20.7%) had TARR >10 seconds. The ML models exhibited good performance in their respective testing and external validation sets (AUC: 0.911 and 0.878 for TARR <7 s; 0.834 and 0.897 for TARR >10 s). SHAP analysis identified the measurements of the vena cava and pulmonary artery as key features for distinguishing abnormal TARR.</p><p><strong>Conclusion: </strong>The explainable ML algorithm accurately identified normal and abnormal TARR of the pulmonary artery, facilitating personalized CTPA scans.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145016592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pulmonary Embolism Survival Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data.","authors":"Zhusi Zhong, Helen Zhang, Fayez H Fayad, Andrew C Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collins, Colin F Greineder, Sun H Ahn, Harrison X Bai, Zhicheng Jiao, Michael K Atalay","doi":"10.1097/RTI.0000000000000831","DOIUrl":"10.1097/RTI.0000000000000831","url":null,"abstract":"<p><strong>Purpose: </strong>Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using computed tomography pulmonary angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE survival.</p><p><strong>Materials and methods: </strong>In total, 918 patients (median age 64 y, range 13 to 99 y, 48% male) with 3978 CTPAs were identified via retrospective review across 3 institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and clinical variables were then incorporated into independent DL models to predict survival outcomes. Cross-modal fusion CoxPH models were used to develop multimodal models from combinations of DL models and calculated PESI scores. Five multimodal models were developed as follows: (1) using CTPA imaging features only, (2) using clinical variables only, (3) using both CTPA and clinical variables, (4) using CTPA and PESI score, and (5) using CTPA, clinical variables, and PESI score. Performance was evaluated using the concordance index (c-index). Kaplan-Meier analysis was performed to stratify patients into high-risk and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction.</p><p><strong>Results: </strong>For both data sets, the multimodal models incorporating CTPA features, clinical variables, and PESI score achieved higher c-indices than PESI alone. Following the stratification of patients into high-risk and low-risk groups by models, survival outcomes differed significantly (both P <0.001). A strong correlation was found between high-risk grouping and RV dysfunction.</p><p><strong>Conclusions: </strong>Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143812346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-world Evaluation of Computer-aided Pulmonary Nodule Detection Software Sensitivity and False Positive Rate.","authors":"Raquelle El Alam, Khushboo Jhala, Mark M Hammer","doi":"10.1097/RTI.0000000000000835","DOIUrl":"10.1097/RTI.0000000000000835","url":null,"abstract":"<p><strong>Purpose: </strong>Evaluate the false positive rate (FPR) of nodule detection software in real-world use.</p><p><strong>Materials and methods: </strong>A total of 250 nonenhanced chest computed tomography (CT) examinations were randomly selected from an academic institution and submitted to the ClearRead nodule detection system (Riverain Technologies). Detected findings were reviewed by a thoracic imaging fellow. Nodules were classified as true nodules, lymph nodes, or other findings (branching opacity, vessel, mucus plug, etc.), and FPR was recorded. FPR was compared with the initial published FPR in the literature. True diagnosis was based on pathology or follow-up stability. For cases with malignant nodules, we recorded whether malignancy was detected by clinical radiology report (which was performed without software assistance) and/or ClearRead.</p><p><strong>Results: </strong>Twenty-one CTs were excluded due to a lack of thin-slice images, and 229 CTs were included. A total of 594 findings were reported by ClearRead, of which 362 (61%) were true nodules and 232 (39%) were other findings. Of the true nodules, 297 were solid nodules, of which 79 (27%) were intrapulmonary lymph nodes. The mean findings identified by ClearRead per scan was 2.59. ClearRead mean FPR was 1.36, greater than the published rate of 0.58 ( P <0.0001). If we consider true lung nodules <6 mm as false positive, FPR is 2.19. A malignant nodule was present in 30 scans; ClearRead identified it in 26 (87%), and the clinical report identified it in 28 (93%) ( P =0.32).</p><p><strong>Conclusion: </strong>In real-world use, ClearRead had a much higher FPR than initially reported but a similar sensitivity for malignant nodule detection compared with unassisted radiologists.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144044902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}