Maya Wiessman, James Wyatt Miller, Ann Marie Navar, Parag Joshi, Yin Xi, Xinhui Duan, Travis Browning, Arzu Canan, Suhny Abbara, Ronald M Peshock, Fernando Kay
{"title":"Optimizing AI-Derived CAC Volume Thresholds on Non-Gated Chest CT for Detection of Actionable Coronary Artery Calcium: A Validation Against Agatston Scoring and Radiologist Reporting.","authors":"Maya Wiessman, James Wyatt Miller, Ann Marie Navar, Parag Joshi, Yin Xi, Xinhui Duan, Travis Browning, Arzu Canan, Suhny Abbara, Ronald M Peshock, Fernando Kay","doi":"10.1097/RTI.0000000000000917","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000917","url":null,"abstract":"<p><strong>Purpose: </strong>Coronary artery calcium (CAC) visually estimated on non-electrocardiogram (ECG)-gated chest CTs is reported inconsistently, limiting identification of high-risk individuals. Although automated AI-derived CAC scoring offers the potential to standardize reporting and improve reliability, this method warrants rigorous validation.</p><p><strong>Materials and methods: </strong>Three hundred thirty-two patients (59% female, median age 62) who underwent a non-gated chest CT within 1-year of a dedicated cardiac CT with Agatston's CAC score (CACscore) were identified between 2016 and 2022. AI-Rad Companion (Siemens) was used to compute CAC volume (AI-CACvol). AI-CACvol performance was compared with radiologists' qualitative CAC reports (H-CACqual) using optimized thresholds for identifying actionable CAC. Model performance was further validated in a postimplementation population.</p><p><strong>Results: </strong>Median AI-CACvol was 20.3 mm³ (IQR 0-188.65), strongly correlated with CACscore (Spearman ρ=0.91, 95% CI: 0.88-0.94); median 31.55 Agatston Units (AU), IQR: 0 to 250). Agreement with CACscore was higher for AI-CACvol versus H-CACqual (weighted kappa 0.88, 95% CI: 0.84, 0.91; vs. 0.85, 95% CI: 0.82, 0.88; P=0.022). At a cutoff of 70 mm³, AI-CACvol demonstrated superior sensitivity compared with H-CACqual for detecting CAC≥100 AU, with greater sensitivity (95% vs. 75%) and comparable specificity (92% vs. 94%). In a validation cohort of 39 patients (64% female, median age 67 y), median CACscore was 43 AU (IQR 0-215) and median AI-CACvol 29.7 mm³ (IQR: 0 to 219.4). The same 70 mm³ cutoff achieved 100% sensitivity and 88% specificity for CAC≥100 AU (n=13).</p><p><strong>Conclusion: </strong>AI-derived CAC volume from non-gated chest CTs correlates strongly with reference CAC scores, showing high sensitivity at actionable thresholds. This supports potential opportunistic screening, though impact on outcomes requires study.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149388430","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}
Georgeann McGuinness, Linda Haramati, Chi Wan Koo, Baskaran Sundaram
{"title":"Response to Letter \"Regarding the Society of Thoracic Radiology Mentorship Program: A Paradigm for Professional Societies\".","authors":"Georgeann McGuinness, Linda Haramati, Chi Wan Koo, Baskaran Sundaram","doi":"10.1097/RTI.0000000000000914","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000914","url":null,"abstract":"","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149344414","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":"CMR Characterization of Hypertrophic Heart Diseases.","authors":"Sandra Quinn, Bradley D Allen","doi":"10.1097/RTI.0000000000000915","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000915","url":null,"abstract":"<p><p>Hypertrophic heart disease comprises a heterogeneous group of myocardial disorders characterized by increased left ventricular wall thickness arising from diverse pathologic processes. Despite differing etiologies, these diseases frequently demonstrate overlapping phenotypic features, which can create significant diagnostic challenges. Accurate differentiation is clinically important, given the prognostic implications associated with each condition, and the application of disease-specific therapeutic strategies. Cardiovascular magnetic resonance (CMR) has become central to the evaluation of hypertrophic heart disease due to its high spatial resolution and unique capability for comprehensive multiparametric tissue characterization. Beyond standardized assessment of ventricular volumes, function, mass, and wall thickness, CMR provides detailed characterization of myocardial fibrosis, edema, and tissue composition through late gadolinium enhancement imaging and parametric mapping techniques, including native T1, T2, and extracellular volume mapping. This review summarizes the contemporary role of CMR in the assessment of hypertrophic heart diseases, with emphasis on imaging features that aid differential diagnosis, and clinically relevant findings that influence management and prognosis.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149301724","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 Real-World Clinical Study on Computed Tomography Pulmonary Angiography-Based Artificial Intelligence-Driven Risk Stratification in Pulmonary Embolism.","authors":"Zhujun Li, Jie Zheng, Shutong Yang, Baoping Zhang, Wei Hou, Qian Tian, Shumeng Zhu, Yao Xiao, Wenzhe Zhao, Xin Huang, Chao Jin, Zhijie Jian, Ying Wei, Feng Shi, Jian Yang, Zhe Liu","doi":"10.1097/RTI.0000000000000913","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000913","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the efficacy of a computed tomography pulmonary angiography (CTPA)-based artificial intelligence system for use in the clinical setting to stratify the risk of pulmonary embolism (PE).</p><p><strong>Materials and methods: </strong>This study enrolled 115 patients diagnosed with PE based on positive CTPA reports at our institution between January 1 and October 10, 2023. Cases were classified as relatively high-risk or low-risk according to the 2019 ESC Guidelines. Two radiologists independently and blindly measured risk-related imaging parameters, including main pulmonary artery diameter (MPAD), ascending aortic diameter (AAD), right and left ventricular diameters (RVD, LVD), the right-to-left ventricular diameter ratio (RVD/LVD ratio), pulmonary artery obstruction index (PAOI), and pulmonary embolism volume (PEV). These results were compared with those from the automated artificial intelligence (AI) system to assess consistency.</p><p><strong>Results: </strong>The agreement (intraclass correlation coefficients, ICCs) of MPAD, AAD, RVD, PAOI, LVD, and RVD/LVD ratio between AI system and manual measurements were 0.94, 0.79, 0.78, 0.80, 0.54, and 0.48, respectively. Among the AI-extracted covariates, an RVD/LVD ratio >1.2 showed good performance in identifying relatively high-risk PE cases, with an area under the curve (AUC) of 0.771. The AI model incorporating all covariates achieved an AUC of 0.848 for classifying high-risk PE.</p><p><strong>Conclusions: </strong>The CTPA-based AI system can rapidly extract the key imaging parameters relevant to PE risk stratification in real-world clinical settings, significantly reducing the CTPA interpretation time and improving evaluation efficiency.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149185660","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 Anterior Mediastinal Hodgkin Lymphoma Exhibiting Abundant Intratumoral Vascular Structures on Computed Tomography.","authors":"Ibuki Namihira, Motohiko Yamazaki, Yukari Goto, Yuma Fuzawa, Masaki Tominaga, Takuya Yagi, Yusuke Tani, Shuhei Kondo, Hajime Umezu, Hiroyuki Ishikawa","doi":"10.1097/RTI.0000000000000906","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000906","url":null,"abstract":"<p><p>Hodgkin lymphoma shows a bimodal age distribution, predominantly affecting young adults and individuals in their 50s and 60s, and is the most common type of lymphoma occurring in the mediastinum. Typical computed tomography (CT) imaging findings include a bulky mass arising in the anterior mediastinum (prevascular compartment) with homogeneous soft-tissue attenuation. Herein, we report a case with unusual CT findings characterized by abundant internal vascular structures in an 18-year-old man with nodular sclerosis classic Hodgkin lymphoma who presented with hemoptysis. Histopathologic examination revealed numerous dilated capillaries within the lesion, which were consistent with the CT findings. Reports of mediastinal lymphoma accompanied by such prominent vascular structures are extremely rare.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149129170","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}
Aaron M Pulsipher, Georges Khattar, Robin Patel, Holenarasipur R Vikram, Michael B Gotway, Carlos A Rojas
{"title":"Chest Computed Tomography Manifestations of Legionella Pneumonia in a Large Multihospital Cohort of Immunocompromised and Immunocompetent Patients.","authors":"Aaron M Pulsipher, Georges Khattar, Robin Patel, Holenarasipur R Vikram, Michael B Gotway, Carlos A Rojas","doi":"10.1097/RTI.0000000000000911","DOIUrl":"10.1097/RTI.0000000000000911","url":null,"abstract":"<p><strong>Purpose: </strong>To assess chest computed tomography (CT) manifestations of Legionella pneumonia (LP) in a large, well-characterized immunocompetent and immunocompromised patient cohort.</p><p><strong>Materials and methods: </strong>This retrospective study identified LP patients across a multicenter hospital system over 84-months. Chest CTs were reviewed for presence and distibution of ground-glass opacity (GGO), consolidation, and numerous other findings. CT findings were categorized into lobar, bronchopneumonia, atypical, and mixed patterns. Evolution on follow-up CT was assessed.</p><p><strong>Results: </strong>311/346 patients (median age 66.6 y [IQR: 55.9, 74.8]; 178 [57.2%] male) had CT examinations available. GGO (98.1%, 305/311) and consolidation (92%, 286/311) were the most prevalent findings, commonly coexisting. The segmental pattern occurred most frequently. The GGO and reverse halo signs occurred in 6.1% (19/311) and 3.5% (11/311), respectively. Follow-up CT occurred in 58.5% (182/311) (median=47.5 d), demonstrating improvement in 84.1% (153/182), worsening in 10.4% (19/182), stability in 5.5% (10/182), and new CT patterns in 12.6% (23/182). Respiratory co-infection occurred in 27.0% (84/311), commonly bacterial. Cavitation occurred in 7.1% (22/311), more frequently among co-infected patients (14.3%, 12/84) than isolated LP (4.4%, 10/227, P =0.005), even more common among immunocompromised patients (12.0% [18/150] vs. 2.5% [4/161], P =0.001), the highest prevalence among co-infected immunocompromised patients (21.3%, 10/47). Co-infection (odds ratio [OR]=3.26, 95% CI=1.33-8.00; P =0.01) and immunocompromise (OR=4.93, 95% CI=1.61-15.1; P =0.005) were independently associated with cavitation.</p><p><strong>Conclusions: </strong>LP presents nonspecifically with a multilobar segmental pattern of GGO and consolidation. Respiratory co-infection was common, often heralded by cavitation. CT findings improve after LP diagnosis.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149117564","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":"Intrathoracic Mesenchymal Tumors on Computed Tomography: Imaging Spectrum and Predictors of Malignancy.","authors":"Anuradha Singh, Zafar Neyaz, Mansi Gupta, Aanchal Bajpai, Neha Nigam","doi":"10.1097/RTI.0000000000000907","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000907","url":null,"abstract":"<p><strong>Purpose: </strong>To characterize computed tomography (CT) features of primary intrathoracic mesenchymal tumors and identify imaging findings that differentiate benign from malignant lesions.</p><p><strong>Materials and methods: </strong>This retrospective study included 81 histopathologically confirmed intrathoracic mesenchymal tumors that were evaluated using pretreatment contrast-enhanced CT between January 2010 and January 2025. The tumor location, morphology, attenuation, invasive behavior, and associated findings were assessed and compared between the benign and malignant groups.</p><p><strong>Results: </strong>Tumors most commonly arose in the mediastinum (32%) and the lungs (32%). Benign tumors (n = 39) were significantly smaller and exhibited a round or oval shape with smooth or lobulated margins (77%). Malignant tumors (n = 42) were larger (mean, 11.2 vs. 6.7 cm), more frequently demonstrated irregular or ill-defined margins, and commonly showed heterogeneous hypoenhancement with extensive low-attenuation areas. On multivariable analysis, tumor necrosis, irregular or spiculated margins, and increasing tumor size were independent predictors of malignancy, whereas calcification showed an inverse association and favored benign pathology.</p><p><strong>Conclusion: </strong>Intrathoracic mesenchymal tumors demonstrate distinctive CT features that aid in differentiation. Malignant tumors characteristically present as large lesions with necrosis and irregular margins, whereas benign tumors are typically well circumscribed and may demonstrate calcification. Recognition of these patterns supports the early identification of mesenchymal etiology, guides biopsy planning, and informs multidisciplinary management.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149117575","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}
Seung Min Yoo, Min Ji Son, Dawon Park, Charles S White
{"title":"Uncommon but Critical Cardiac Abnormalities on Routine Chest Computed Tomography.","authors":"Seung Min Yoo, Min Ji Son, Dawon Park, Charles S White","doi":"10.1097/RTI.0000000000000912","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000912","url":null,"abstract":"<p><p>Uncommon but critical cardiac abnormalities may be missed on routine chest computed tomography (CT) due to misinterpretation as motion artifact. The examples include paradoxical embolism through the patent foramen ovale, right ventricular lead perforation, patent ductus arteriosus with endarteritis, infective endocarditis, acute mitral regurgitation secondary to chordal rupture, acute myocardial infarction, left atrial or ventricular thrombus, and paracardiac fat necrosis. Such overlooked diagnoses may lead to an unfavorable outcome. This review provides important tips to discriminate true abnormalities from cardiac motion artifact, and discusses specific CT findings that permit identification of subtle but critical cardiac findings on routine chest CT.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082538","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":"Prevalence of the Direct Bronchus Sign in Primary Versus Metastatic Peripheral Pulmonary Lesions: A 10-Year Retrospective Cohort Study.","authors":"Sze Shyang Kho, Larry Ellee Nyanti","doi":"10.1097/RTI.0000000000000910","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000910","url":null,"abstract":"","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149070489","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}
Ariadne K DeSimone, Kathryn A Schulz, Suzanne C Byrne, Mark M Hammer
{"title":"Real-world Performance of Computer-aided Pulmonary Nodule Detection for Lung Cancer.","authors":"Ariadne K DeSimone, Kathryn A Schulz, Suzanne C Byrne, Mark M Hammer","doi":"10.1097/RTI.0000000000000909","DOIUrl":"https://doi.org/10.1097/RTI.0000000000000909","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the real-world sensitivity of an artificial intelligence-based pulmonary vessel suppression and computer-aided detection system (ClearRead VIS/CADe) for lung cancer detection and to characterize nodule features associated with detection and nondetection.</p><p><strong>Materials and methods: </strong>This retrospective study included patients diagnosed with lung cancer within a lung cancer screening program in the authors' health care network after deployment of ClearRead VIS/CADe (August 2023 to June 2025). A fellowship-trained cardiothoracic radiologist reviewed the diagnosis, CT examination, and the most recent prior chest CT examination for each patient. Malignant nodules were characterized by size, type, location, and relationship to major vessels. For each examination, whether the malignant nodule was identified in the radiology report, annotated by CADe, and visible on vessel-suppressed images was recorded. Sensitivity was assessed overall and by nodule characteristics. Multivariable logistic regression was performed for nodules <30 mm to identify factors associated with CADe annotation.</p><p><strong>Results: </strong>A total of 129 patients were included. Overall sensitivity of CADe annotation on diagnosis CT examinations was 72% (93/129), whereas vessel-suppressed images demonstrated higher sensitivity (92%, 119/129). CADe sensitivity varied significantly by nodule size (P<0.001), was highest for solid nodules (80%) and lower for part-solid (75%), ground-glass (38%), and cystic nodules (13%) (P<0.001). Vessel-suppressed images demonstrated high sensitivity across nodule sizes and morphology. After exclusion of masses, subpleural and paramediastinal locations remained independently associated with reduced sensitivity (P<0.05).</p><p><strong>Conclusion: </strong>Vessel-suppressed images demonstrated high sensitivity for malignant pulmonary nodules, whereas CADe performance varied by nodule type and location.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148913537","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}