Recent advances in deep learning have led to robust automated tools for segmentation of abdominal computed tomography (CT). Meanwhile, segmentation of magnetic resonance imaging (MRI) is substantially more challenging due to the inherent signal variability and the increased effort required for annotating training datasets. Hence, existing approaches are trained on limited sets of MRI sequences, which might limit their generalizability. To characterize the landscape of MRI abdominal segmentation tools, we present here a comprehensive benchmarking of the three state-of-the-art and open-source models: MRSegmentator, MRISegmentator-Abdomen, and TotalSegmentator MRI. Since these models are trained using labor-intensive manual annotation cycles, we also introduce and evaluate ABDSynth, a SynthSeg-based model purely trained on widely available CT segmentations (no real images). More generally, we assess accuracy and generalizability by leveraging three public datasets (not seen by any of the evaluated methods during their training), which span all major manufacturers, five MRI sequences, as well as a variety of subject conditions, voxel resolutions, and fields-of-view. Our results reveal that MRSegmentator achieves the best performance and is most generalizable. In contrast, ABDSynth yields slightly less accurate results, but its relaxed requirements in training data make it an alternative when the annotation budget is limited. The evaluation code and datasets are given for future benchmarking at https://github.com/deepakri201/AbdoBench, along with inference code and weights for ABDSynth.

Diagnosis of carotid plaques from head and neck CT angiography (CTA) scans is typically time-consuming and labor-intensive, leading to limited studies and unpleasant results in this area. The objective of this study is to develop a deep-learning-based model for detection and segmentation of carotid plaques using CTA images. CTA images from 1061 patients (765 male; 296 female) with 4048 carotid plaques were included and split into a 75% training-validation set and a 25% independent test set. We built a workflow involving three modified deep learning networks: a plain U-Net for coarse artery segmentation, an Attention U-Net for fine artery segmentation, a dual-channel-input ConvNeXt-based U-Net architecture for plaque segmentation, and post-processing to refine predictions and eliminate false positives. The models were trained on the training-validation set using five-fold cross-validation and further evaluated on the independent test set using comprehensive metrics for segmentation and plaque detection. The proposed workflow was evaluated in the independent test set (261 patients with 902 carotid plaques) and achieved a mean dice similarity coefficient (DSC) of 0.91±0.04 in artery segmentation, and 0.75±0.14/0.67±0.15 in plaque segmentation per artery/patient. The model detected 95.5% (861/902) plaques, including 96.6% (423/438), 95.3% (307/322), and 92.3% (131/142) of calcified, mixed, and soft plaques, with less than one (0.63±0.93) false positive plaque per patient on average. This study developed an automatic detection and segmentation deep learning-based CAP-Net for carotid plaques using CTA, which yielded promising results in identifying and delineating plaques.

Recent advances in deep learning have led to robust automated tools for segmentation of abdominal computed tomography (CT). Meanwhile, segmentation of magnetic resonance imaging (MRI) is substantially more challenging due to the inherent signal variability and the increased effort required for annotating training datasets. Hence, existing approaches are trained on limited sets of MRI sequences, which might limit their generalizability. To characterize the landscape of MRI abdominal segmentation tools, we present here a comprehensive benchmarking of the three state-of-the-art and open-source models: MRSegmentator, MRISegmentator-Abdomen, and TotalSegmentator MRI. Since these models are trained using labor-intensive manual annotation cycles, we also introduce and evaluate ABDSynth, a SynthSeg-based model purely trained on widely available CT segmentations (no real images). More generally, we assess accuracy and generalizability by leveraging three public datasets (not seen by any of the evaluated methods during their training), which span all major manufacturers, five MRI sequences, as well as a variety of subject conditions, voxel resolutions, and fields-of-view. Our results reveal that MRSegmentator achieves the best performance and is most generalizable. In contrast, ABDSynth yields slightly less accurate results, but its relaxed requirements in training data make it an alternative when the annotation budget is limited. The evaluation code and datasets are given for future benchmarking at https://github.com/deepakri201/AbdoBench, along with inference code and weights for ABDSynth.

To develop and assess the performance of an anatomically based multitask deep learning radiomics nomogram (AMDRN) system to predict implant failure risk before maxillary sinus floor elevation (MSFE) while incorporating automated segmentation of key anatomical structures. We retrospectively collected patients' preoperative cone beam computed tomography (CBCT) images and electronic medical records (EMRs). First, the nn-UNet v2 model was optimized to segment the maxillary sinus (MS), Schneiderian membrane (SM), and residual alveolar bone (RAB). Based on the segmentation mask, a deep learning model (3D-Attention-ResNet) and a radiomics model were developed to extract 3D features from CBCT scans, generating the DL Score, and Rad Score. Significant clinical features were also extracted from EMRs to build a clinical model. These components were then integrated using logistic regression (LR) to create the AMDRN model, which includes a visualization module to support clinical decision-making. Segmentation results for MS, RAB, and SM achieved high DICE coefficients on the test set, with values of 99.50% ± 0.84%, 92.53% ± 3.78%, and 91.58% ± 7.16%, respectively. On an independent test set, the Clinical model, Radiomics model, 3D-DL model, and AMDRN model achieved prediction accuracies of 60%, 76%, 82%, and 90%, respectively, with AMDRN achieving the highest AUC of 93%. The AMDRN system enables efficient preoperative prediction of implant failure risk in MSFE and accurate segmentation of critical anatomical structures, supporting personalized treatment planning and clinical risk management.

<b>BACKGROUND</b>. Coronary artery calcium (CAC) scoring is used to stratify acute coronary syndrome (ACS) risk. Nonetheless, patients with a CAC score of zero (CAC₀) remain at risk from noncalcified plaque components. <b>OBJECTIVE</b>. The purpose of this study was to explore CTA-derived coronary artery plaque characteristics in symptomatic patients with CAC₀ who subsequently have ACS through comparisons with patients with a CAC score greater than 0 (CAC_{> 0}) who subsequently have ACS as well as with patients with CAC₀ who do not subsequently have ACS. <b>METHODS</b>. This study entailed a secondary retrospective analysis of prior prospective registry data. The international multicenter CONFIRM (Coronary CT Angiography Evaluation for Clinical Outcomes: An International Multicenter) registry collected longitudinal observational data on symptomatic patients who underwent clinically indicated coronary CTA from January 2004 to May 2010. ICONIC (Incident Coronary Syndromes Identified by CT) was a nested cohort study conducted within CONFIRM that identified patients without known coronary artery disease (CAD) at the time of CTA who did and did not subsequently have ACS (i.e., the ACS and control groups, respectively) and who were propensity matched in a 1:1 ratio on the basis of CAD risk factors and CAD severity on CTA. The present ICONIC substudy selected matched patients in the ACS and control groups who both had documented CAC scores. CTA examinations were analyzed using artificial intelligence software for automated quantitative plaque assessment. In the ACS group, invasive angiography findings were used to identify culprit lesions. <b>RESULTS</b>. The present study included 216 patients (mean age, 55.6 years; 91 women and 125 men), with 108 patients in each of the ACS and control groups. In the ACS group, 23% (<i>n</i> = 25) of patients had CAC₀. In the ACS group, culprit lesions in the subsets of patients with CAC₀ and CAC_{> 0} showed no significant differences in fibrous, fibrofatty, or necrotic-core plaque volumes (<i>p</i> > .05). In the CAC₀ subset, patients with ACS, compared with control patients, had greater mean (± SD) fibrous plaque volume (29.4 ± 42.0 vs 5.5 ± 15.2 mm³, <i>p</i> < .001), fibrofatty plaque volume (27.3 ± 52.2 vs 1.3 ± 3.7 mm³, <i>p</i> < .001), and necrotic-core plaque volume (2.8 ± 6.4 vs 0.0 ± 0.1 mm³, <i>p</i> < .001). <b>CONCLUSION</b>. After propensity-score matching, 23% of patients with ACS had CAC₀. Patients with CAC₀ in the ACS and control groups showed significant differences in volumes of noncalcified plaque components. <b>CLINICAL IMPACT</b>. Methods that identify and quantify noncalcified plaque forms may help characterize ACS risk in symptomatic patients with CAC₀.

To develop a deep learning (DL) pipeline for accurate slice selection, temporal muscle (TM) segmentation, TM thickness (TMT) and area (TMA) quantification, and assessment of the prognostic role of TMT and TMA in acute ischemic stroke (AIS) patients. A total of 1020 AIS patients were enrolled. Participants were divided into three datasets: Dataset 1 (n = 295) for slice selection using ResNet50 model, Dataset 2 (n = 258) for TM segmentation employing TransUNet-based algorithm, and Dataset 3 (n = 467) for evaluating DL-based quantification of TMT and TMA as prognostic factors in AIS. The ability of the DL system to select slices was assessed using accuracy, ±1 slice accuracy and mean absolute error. The Dice similarity coefficient (DSC) is used to assess the performance of the DL system on TM segmentation. The association between automatic quantification of TMT and TMA and 6-month outcomes was determined. Automatic slice selection achieved a mean accuracy of 72.91 %, 97.94 % ± 1 slice accuracy with a mean absolute error of 1.54 mm, while TM segmentation on T1WI achieved a mean DSC of 0.858. Automatically extracted TMT and TMA were each independently associated with 6-month poor outcomes in AIS patients after adjusting for age, sex, onodera nutritional prognosis index, systemic immune-inflammation index, albumin levels, and smoking/drinking history (TMT: hazard ratio 0.736, 95 % confidence interval 0.528-0.931; TMA: hazard ratio 0.702, 95 % confidence interval 0.541-0.910). TMT and TMA are robust prognostic markers in AIS patients, and our end-to-end DL pipeline enables rapid, automated quantification that integrates seamlessly into clinical workflows, supporting scalable risk stratification and personalized rehabilitation planning.

Accurate and efficient medical image segmentation is crucial but challenging due to anatomical variability and high computational demands on volumetric data. Recent hybrid CNN-Transformer architectures achieve state-of-the-art results but add significant complexity. In this paper, we propose MLRU++, a Multiscale Lightweight Residual UNETR++ architecture designed to balance segmentation accuracy and computational efficiency. It introduces two key innovations: a Lightweight Channel and Bottleneck Attention Module (LCBAM) that enhances contextual feature encoding with minimal overhead, and a Multiscale Bottleneck Block (M2B) in the decoder that captures fine-grained details via multi-resolution feature aggregation. Experiments on four publicly available benchmark datasets (Synapse, BTCV, ACDC, and Decathlon Lung) demonstrate that MLRU++ achieves state-of-the-art performance, with average Dice scores of 87.57% (Synapse), 93.00% (ACDC), and 81.12% (Lung). Compared to existing leading models, MLRU++ improves Dice scores by 5.38% and 2.12% on Synapse and ACDC, respectively, while significantly reducing parameter count and computational cost. Ablation studies evaluating LCBAM and M2B further confirm the effectiveness of the proposed architectural components. Results suggest that MLRU++ offers a practical and high-performing solution for 3D medical image segmentation tasks. Source code is available at: https://github.com/1027865/MLRUPP

Accurate and efficient medical image segmentation is crucial but challenging due to anatomical variability and high computational demands on volumetric data. Recent hybrid CNN-Transformer architectures achieve state-of-the-art results but add significant complexity. In this paper, we propose MLRU++, a Multiscale Lightweight Residual UNETR++ architecture designed to balance segmentation accuracy and computational efficiency. It introduces two key innovations: a Lightweight Channel and Bottleneck Attention Module (LCBAM) that enhances contextual feature encoding with minimal overhead, and a Multiscale Bottleneck Block (M2B) in the decoder that captures fine-grained details via multi-resolution feature aggregation. Experiments on four publicly available benchmark datasets (Synapse, BTCV, ACDC, and Decathlon Lung) demonstrate that MLRU++ achieves state-of-the-art performance, with average Dice scores of 87.57% (Synapse), 93.00% (ACDC), and 81.12% (Lung). Compared to existing leading models, MLRU++ improves Dice scores by 5.38% and 2.12% on Synapse and ACDC, respectively, while significantly reducing parameter count and computational cost. Ablation studies evaluating LCBAM and M2B further confirm the effectiveness of the proposed architectural components. Results suggest that MLRU++ offers a practical and high-performing solution for 3D medical image segmentation tasks. Source code is available at: https://github.com/1027865/MLRUPP

Precise segmentation of papillary thyroid microcarcinoma (PTMC) during ultrasound-guided radiofrequency ablation (RFA) is critical for effective treatment but remains challenging due to acoustic artifacts, small lesion size, and anatomical variability. In this study, we propose DualSwinUnet++, a dual-decoder transformer-based architecture designed to enhance PTMC segmentation by incorporating thyroid gland context. DualSwinUnet++ employs independent linear projection heads for each decoder and a residual information flow mechanism that passes intermediate features from the first (thyroid) decoder to the second (PTMC) decoder via concatenation and transformation. These design choices allow the model to condition tumor prediction explicitly on gland morphology without shared gradient interference. Trained on a clinical ultrasound dataset with 691 annotated RFA images and evaluated against state-of-the-art models, DualSwinUnet++ achieves superior Dice and Jaccard scores while maintaining sub-200ms inference latency. The results demonstrate the model's suitability for near real-time surgical assistance and its effectiveness in improving segmentation accuracy in challenging PTMC cases.

Deep learning models for medical image segmentation often struggle with task-specific characteristics, limiting their generalization to unseen tasks with new anatomies, labels, or modalities. Retraining or fine-tuning these models requires substantial human effort and computational resources. To address this, in-context learning (ICL) has emerged as a promising paradigm, enabling query image segmentation by conditioning on example image-mask pairs provided as prompts. Unlike previous approaches that rely on implicit modeling or non-end-to-end pipelines, we redefine the core interaction mechanism in ICL as an explicit retrieval process, termed E-ICL, benefiting from the emergence of vision foundation models (VFMs). E-ICL captures dense correspondences between queries and prompts at minimal learning cost and leverages them to dynamically weight multi-class prompt masks. Built upon E-ICL, we propose EICSeg, the first end-to-end ICL framework that integrates complementary VFMs for universal medical image segmentation. Specifically, we introduce a lightweight SD-Adapter to bridge the distinct functionalities of the VFMs, enabling more accurate segmentation predictions. To fully exploit the potential of EICSeg, we further design a scalable self-prompt training strategy and an adaptive token-to-image prompt selection mechanism, facilitating both efficient training and inference. EICSeg is trained on 47 datasets covering diverse modalities and segmentation targets. Experiments on nine unseen datasets demonstrate its strong few-shot generalization ability, achieving an average Dice score of 74.0%, outperforming existing in-context and few-shot methods by 4.5%, and reducing the gap to task-specific models to 10.8%. Even with a single prompt, EICSeg achieves a competitive average Dice score of 60.1%. Notably, it performs automatic segmentation without manual prompt engineering, delivering results comparable to interactive models while requiring minimal labeled data. Source code will be available at https://github.com/ zerone-fg/EICSeg.