Volume 45, Issue 8

Breast density impacts cancer detection by masking tumors within fibroglandular tissue and there are disparities in screening outcomes across racial groups. However, it remains unclear whether these differences reflect inherent tissue characteristics or systemic bias. To isolate the effect of breast density on lesion detectability across racial subgroups, we conducted a retrospective case-control study using raw tomosynthesis projections from 902 women (453 cases, 451 matched controls) across BI-RADS density categories and self-reported race. Identical in-silico spiculated masses (8–15 mm) and microcalcification clusters (10–14 mm) were inserted into the projections using a calibrated lesion model. Images were reconstructed in the same manner to avoid proprietary processing in lesion detection. Lesion detectability was assessed with Channelized Hotelling Observers. Regression and causal mediation analyses examined the relationships between race, density, and detectability. As result, detectability decreased with increasing density; for masses, the area under the receiver operating characteristic curve (ROC AUC) reduced significantly from 0.93 to 0.85 (BIRADS A to D), whereas for microcalcifications AUC decreased from 0.85 to 0.78 across the same density range. Discrimination remained higher for masses than calcifications (AUC=0.89 vs. AUC=0.82). Stratified analyses showed slightly higher detectability in Non-Hispanic Black women compared with Non-Hispanic White and Asian American women, largely reflecting differences in density. Mediation analysis revealed that breast density accounted for 38–55% of the observed race-associated detectability differences. Mediation analyses have shown that density is the dominant factor in detectability. These findings support the development of calibrated detection models and personalized screening strategies that account for breast density.

中文摘要翻译待生成

Accurate Cobb angle measurement is essential for scoliosis assessment but remains labor-intensive and observer-dependent. We introduce DGPDT (Detection-Guided Prompt-driven Transformer), a unified transformer-based framework that integrates vertebra detection and foundation-model segmentation for generalizable spinal analysis. A Roboflow Detection Transformer (RF-DETR) with a DINOv2 backbone localizes vertebrae, followed by post-processing to ensure anatomical continuity. The resulting bounding boxes serve as automatic prompts for a fine-tuned Segment Anything Model 2.1 (SAM 2.1), which generates high-resolution vertebral masks. Cobb angles are then computed from vertebral masks, enabling estimation of both main and compensatory curves. Evaluations on the in-house (TVGH-SpineXR) and external (SpineWeb-16) datasets demonstrate encouraging performance on both internal and external datasets, achieving mean Dice coefficients of 0.944 and 0.781, respectively, and mean absolute Cobb angle errors of approximately 2–3° in-domain and 4.93° under cross-domain evaluation. Despite being trained solely on TVGH-SpineXR, DGPDT maintains accuracy comparable to models trained directly on the benchmark dataset. By coupling detection-guided prompting with transformer-based segmentation, DGPDT achieves a clinically acceptable mean absolute error (<5°), suggesting good reproducibility and potential applicability beyond the training dataset.

中文摘要翻译待生成

Accurate segmentation of cardiac MRI is essential for assessment of cardiac function through biomarkers such as the left and right ventricular ejection fraction (LVEF, RVEF). Although AI methods have achieved high average segmentation accuracy, the precision of biomarkers for individual patients – quantified by estimation variance, remains critical for reliable diagnosis. Calibrated biomarkers, whose uncertainty accurately reflects the true variability, are highly desirable. However, existing evaluations predominantly focus on population-level segmentation accuracy, leaving biomarker-level uncertainty and calibration largely underexplored. Intrinsic anatomical ambiguity and annotation variability are major sources of biomarker variability and cannot be fully eliminated, even when training on a single annotation set. To address this, we propose a probabilistic segmentation framework that explicitly models aleatoric uncertainty with the goal of improving calibration in the biomarker space. The framework disentangles two key sources of uncertainty: (1) detection uncertainty , arising from ambiguous inclusion of basal or apical slices in 2D cardiac MRI, modeled via objectness probabilities; and (2) contour uncertainty , reflecting variability in ventricular boundary delineation, modeled through mean–variance regression of elliptic Fourier descriptors, a compact representation of closed contours. By propagating these uncertainties to derived biomarkers, the proposed method produces more informative and better-calibrated confidence estimates for ejection fraction. Compared to conventional pixel-wise approaches, our framework improves biomarker reliability, particularly in realistic settings dominated by annotation ambiguity and limited domain shift.

中文摘要翻译待生成

Limited-angle cone-beam computed tomography (LA-CBCT) enables rapid imaging and reduced radiation exposure, but its severely incomplete projection data lead to ill-posed reconstructions with prominent artifacts, limiting clinical applicability. Recent advances in 3D Gaussian Splatting (3D-GS) have shown promise for efficient tomographic reconstruction, yet its performance remains highly sensitive to initialization. In this work, we present SPARK (Structurally-Informed Projection-Accelerated Reconstruction), a two-stage framework that introduces a generative, structurally informed initialization for 3D-GS. In the first stage, a geometry-conditioned network directly predicts complete 3D Gaussian parameters from a sparse subset of projections, embedding learned anatomical priors to mitigate artifact propagation. In the second stage, the generated scene is refined through physics-based 3D-GS optimization, yielding high-fidelity reconstructions consistent with measured projections. Extensive experiments on public datasets demonstrate that SPARK substantially improves both image quality and convergence speed, achieving superior PSNR/SSIM in severely limited-angle scenarios compared with analytical, iterative, and deep learning baselines. Moreover, SPARK reconstructions provide enhanced inputs for downstream post-processing networks, further boosting image fidelity. These results suggest that SPARK is a promising prior-informed 3D-GS framework for simulated LA-CBCT reconstruction under limited angular coverage, providing an effective bridge between data-driven anatomical priors and physics-based projection-domain refinement.

中文摘要翻译待生成

Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views. Although numerous deep-learning models have been proposed for stenosis detection from a single angiography view, their performance heavily relies on expensive view-level annotations, which are often not readily available in hospital systems. Moreover, these models fail to capture the temporal dynamics and dependencies among multiple views, which are crucial for clinical diagnosis. To address this, we propose SegmentMIL, a transformer-basedmulti-viewmultiple-instance learning framework for patient-level stenosis classification. Trained on a real-world clinical dataset, using patient-level supervision and without any view-level annotations, SegmentMIL jointly predicts the presence of stenosis and localizes the affected anatomical region, distinguishing between the right and left coronary arteries and their respective segments. SegmentMIL obtains high performance on internal and external evaluations and outperforms both view-level models and classical MIL baselines, underscoring its potential as a clinically viable and scalable solution for coronary stenosis diagnosis. Our code is available at https://github.com/NikolaCenic/mil-stenosis.

中文摘要翻译待生成

Contrast-free myocardial infarction (MI) segmentation is essential for mitigating the health risks associated with contrast agents (CAs) in clinical diagnostics. However, existing approaches are limited by their reliance on strictly paired CINE sequences and contrastenhanced images, which are often difficult to obtain because patient conditions and imaging protocols often cause inter-modality slic...

中文摘要翻译待生成