Radiology最新文献

Background Individuals eligible for lung cancer screening with low-dose CT face a higher cardiovascular mortality risk. Purpose To investigate the association between changes in epicardial adipose tissue (EAT) at the 2-year interval and mortality in individuals undergoing serial low-dose CT lung cancer screening. Materials and Methods This secondary analysis of the National Lung Screening Trial obtained EAT volume and density from serial low-dose CT scans using a validated automated deep learning algorithm. EAT volume and density changes over 2 years were categorized into typical (decrease of 7% to increase of 11% and decrease of 3% to increase of 2%, respectively) and atypical (increase or decrease beyond typical) changes, which were associated with all-cause, cardiovascular, and lung cancer mortality. Uni- and multivariable Cox proportional hazard regression models-adjusted for baseline EAT values, age, sex, race, ethnicity, smoking, pack-years, heart disease or myocardial infarction, stroke, hypertension, diabetes, education status, body mass index, and coronary artery calcium-were performed. Results Among 20 661 participants (mean age, 61.4 years ± 5.0 [SD]; 12 237 male [59.2%]), 3483 (16.9%) died over a median follow-up of 10.4 years (IQR, 9.9-10.8 years) (cardiovascular related: 816 [23.4%]; lung cancer related: 705 [20.2%]). Mean EAT volume increased (2.5 cm³/m² ± 11.0) and density decreased (decrease of 0.5 HU ± 3.0) over 2 years. Atypical changes in EAT volume were independent predictors of all-cause mortality (atypical increase: hazard ratio [HR], 1.15 [95% CI: 1.06, 1.25] [P < .001]; atypical decrease: HR, 1.34 [95% CI: 1.23, 1.46] [P < .001]). An atypical decrease in EAT volume was associated with cardiovascular mortality (HR, 1.27 [95% CI: 1.06, 1.51]; P = .009). EAT density increase was associated with all-cause, cardiovascular, and lung cancer mortality (HR, 1.29 [95% CI: 1.18, 1.40] [P < .001]; HR, 1.29 [95% CI: 1.08, 1.54] [P = .005]; HR, 1.30 [95% CI: 1.07, 1.57] [P = .007], respectively). Conclusion EAT volume increase and decrease and EAT density increase beyond typical on subsequent chest CT scans were associated with all-cause mortality in participants screened for lung cancer. EAT volume decrease and EAT density increase were associated with elevated risk of cardiovascular mortality after adjustment for baseline EAT values. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Fuss in this issue.

Background Prognostic value of radiologic features in interstitial lung disease (ILD) has been predominantly studied in idiopathic pulmonary fibrosis, but findings vary. The relative importance of features versus guideline-defined patterns in predicting outcomes is unknown. Purpose To identify radiologic features that are independently associated with transplant-free survival beyond clinical predictive factors across all ILD subtypes, and to identify whether individual features versus patterns are more important for prognostication. Materials and Methods This is a secondary analysis of the prospective Canadian Registry for Pulmonary Fibrosis. Consecutive patients with ILD were evaluated in standardized multidisciplinary discussions between January 2021 and March 2022. Radiologic features on thin-section CT images were quantified, and guideline-defined usual interstitial pneumonia (UIP) and fibrotic hypersensitivity pneumonitis (fHP) patterns were assigned. Multivariable Cox analysis was used to assess the associations of radiologic features with transplant-free survival, and nested models were used to test the relative importance of features compared with patterns. Results A total of 1593 patients (mean age, 66 years ± 12 [SD]; 800 male) were included. The following four features were associated with transplant-free survival: extent of honeycombing (hazard ratio, 1.20; 95% CI; 1.06, 1.36 per 10% increase in lung involvement; P = .005), extent of traction bronchiectasis (hazard ratio, 1.18; 95% CI: 1.10, 1.26 per 10% increase; P < .001), pulmonary artery diameter (hazard ratio, 1.03; 95% CI: 1.01; 1.04 per 1-mm increase; P = .002), and presence of subpleural sparing (hazard ratio, 0.76; 95% CI: 0.56, 0.96; P = .03). Guideline-defined patterns were not independently associated with survival in a model that included these four radiologic features, each of which retained its prognostic value. Conclusion The extent of fibrosis was predictive of worse outcomes across all ILD subtypes in a dose-dependent fashion and independent of well-recognized clinical prognostic factors. Guideline-defined UIP and fHP patterns each helped risk-stratify patients in isolation but lost prognostic value when accounting for the extent of fibrosis, suggesting that their previous association with mortality is based on these patterns acting as surrogates for a greater extent of fibrosis. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Wells in this issue.

Recent advances in artificial intelligence have witnessed the emergence of large-scale deep learning models capable of interpreting and generating both textual and imaging data. Such models, typically referred to as foundation models (FMs), are trained on extensive corpora of unlabeled data and demonstrate high performance across various tasks. FMs have recently received extensive attention from academic, industry, and regulatory bodies. Given the potentially transformative impact that FMs can have on the field of radiology, radiologists must be aware of potential pathways to train these radiology-specific FMs, including understanding both the benefits and challenges. Thus, this review aims to explain the fundamental concepts and terms of FMs in radiology, with a specific focus on the requirements of training data, model training paradigms, model capabilities, and evaluation strategies. Overall, the goal of this review is to unify technical advances and clinical needs for safe and responsible training of FMs in radiology to ultimately benefit patients, providers, and radiologists.

Background Combined mammography and MRI screening is not universally accessible for women with intermediate breast cancer risk due to limited MRI resources. Selecting women for MRI by assessing their mammogram may enable more resource-effective screening. Purpose To explore the feasibility of using a commercial artificial intelligence (AI) system at mammography to stratify women with intermediate risk for supplemental MRI or no MRI. Materials and Methods This retrospective study included consecutive women with intermediate risk screened with mammography and MRI between January 2003 and January 2020 at a Dutch university medical center. An AI system was used to independently evaluate all mammograms, providing a case-based score that ranked the likelihood of a malignancy on a scale of 1-10. Different AI thresholds for supplemental MRI screening were tested, balancing cancer detection against the number of women needing to undergo MRI. Univariate analyses were used to explore associations between personal factors (age, breast density, and duration of screening participation) and AI results. Results In 760 women (mean age, 48.9 years ± 10.5 [SD]), 2819 combined screening examinations were performed, and 37 breast cancers were detected. Use of AI at mammography achieved an area under the receiver operating characteristic curve of 0.72 (95% CI: 0.63, 0.81) for the entire intermediate-risk population and 0.81 (95% CI: 0.69, 0.93) for women with prior breast cancer. Using a threshold score of 5, 31 of 37 (84%) breast cancers were detected, including 13 of 19 (68%) mammographically occult cancers, at a supplemental breast MRI rate of 50% (1409 of 2819 examinations). No significant association between breast density or age and the probability of a false-negative AI result was found. Conclusion Using AI at mammography to select women for supplemental MRI effectively identified women with higher breast cancer risk in an intermediate-risk population, including women with mammographically occult cancers. AI selection of women with intermediate risk for supplemental MRI screening has the potential to reduce screening burden and costs, while maintaining a high cancer detection rate. © RSNA, 2025.

Background Diagnostic imaging and biopsy are used to evaluate abnormal screening mammography. Differences in on-site availability and receipt of these diagnostic services may contribute to disparities in breast cancer outcomes across sociodemographic groups. Purpose To identify multilevel factors associated with on-site availability and receipt of diagnostic imaging and biopsy after screening mammography. Materials and Methods This retrospective study included female patients (age range, 40-89 years) who underwent screening mammography at 136 facilities in the United States from January 2010 to December 2020. The primary exposure variables were race and ethnicity and neighborhood-level educational attainment, household income, and rurality. The adjustment variables were age, breast density, breast biopsy history, personal and family history of breast cancer, time from prior mammographic examination to screening mammography, screening modality, facility academic affiliation, and screening examination year. The relative risk (RR) of factors for on-site availability at screening facilities and undergoing standard-of-care imaging (ie, mammography and/or US) and advanced diagnostic imaging (ie, digital breast tomosynthesis, MRI) and biopsy, and undergoing any same-day diagnostic service and biopsy were estimated using modified Poisson regression. Results In total, 1 123 177 female patients (median age, 59 years; IQR, 51-67 years) underwent 3 519 502 screening mammographic examinations: 10.3% Asian patients (362 440 of 3 519 502), 12.7% Black patients (447 777 of 3 519 502), 6.5% Hispanic patients (227 177 of 3 519 502), 68.3% White patients (2 403 159 of 3 519 502), and 2.2% all other races and ethnicities (78 949 of 3 519 502). In most fully adjusted models, race or ethnicity and neighborhood-level socioeconomic status were not associated with on-site diagnostic service availability. However, compared with White patients, patients belonging to racial and ethnic minority groups were less likely to undergo same-day diagnostic services after abnormal screening mammography (Asian patients: RR, 0.74 [95% CI: 0.64, 0.85]; Black patients: RR, 0.56 [95% CI: 0.49, 0.63]; Hispanic patients: RR, 0.61 [95% CI: 0.52, 0.71]). Black patients were less likely to undergo same-day biopsies after an abnormal diagnostic workup (RR, 0.46; 95% CI: 0.33, 0.65). Conclusion Although no evidence existed that on-site diagnostic service availability varied by race and ethnicity in most models, patients in racial and ethnic minority groups were less likely to be provided same-day diagnostic services and Black patients were less likely to undergo same-day biopsy. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Mullen in this issue.