Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation predictions often fail to capture these annotator biases. Although recent studies have explored multi-rater segmentation, existing methods typically focus on a single perspective -- either generating a probabilistic ``gold standard'' consensus or preserving expert-specific preferences -- thus struggling to provide a more omni view. In this study, we propose DiffOSeg, a two-stage diffusion-based framework, which aims to simultaneously achieve both consensus-driven (combining all experts' opinions) and preference-driven (reflecting experts' individual assessments) segmentation. Stage I establishes population consensus through a probabilistic consensus strategy, while Stage II captures expert-specific preference via adaptive prompts. Demonstrated on two public datasets (LIDC-IDRI and NPC-170), our model outperforms existing state-of-the-art methods across all evaluated metrics. Source code is available at https://github.com/string-ellipses/DiffOSeg .

Precise liver segmentation is critical for accurate diagnosis and effective treatment planning, serving as a foundation for medical image analysis. However, existing methods struggle with limited labeled data, poor generalizability, and insufficient integration of anatomical and clinical features. To address these limitations, we propose a novel Few-Shot Segmentation model with Unified Liver Representation (FSS-ULivR), which employs a ResNet-based encoder enhanced with Squeeze-and-Excitation modules to improve feature learning, an enhanced prototype module that utilizes a transformer block and channel attention for dynamic feature refinement, and a decoder with improved attention gates and residual refinement strategies to recover spatial details from encoder skip connections. Through extensive experiments, our FSS-ULivR model achieved an outstanding Dice coefficient of 98.94%, Intersection over Union (IoU) of 97.44% and a specificity of 93.78% on the Liver Tumor Segmentation Challenge dataset. Cross-dataset evaluations further demonstrated its generalizability, with Dice scores of 95.43%, 92.98%, 90.72%, and 94.05% on 3DIRCADB01, Colorectal Liver Metastases, Computed Tomography Organs (CT-ORG), and Medical Segmentation Decathlon Task 3: Liver datasets, respectively. In multi-organ segmentation on CT-ORG, it delivered Dice scores ranging from 85.93% to 94.26% across bladder, bones, kidneys, and lungs. For brain tumor segmentation on BraTS 2019 and 2020 datasets, average Dice scores were 90.64% and 89.36% across whole tumor, tumor core, and enhancing tumor regions. These results emphasize the clinical importance of our model by demonstrating its ability to deliver precise and reliable segmentation through artificial intelligence techniques and engineering solutions, even in scenarios with scarce annotated data.

Accurate X-ray Computed tomography (CT) image segmentation of the abdominal organs is fundamental for diagnosing abdominal diseases, planning cancer treatment, and formulating radiotherapy strategies. However, the existing deep learning based models for three-dimensional (3D) CT image abdominal multi-organ segmentation face challenges, including complex organ distribution, scarcity of labeled data, and diversity of organ structures, leading to difficulties in model training and convergence and low segmentation accuracy. To address these issues, a novel multi-stage training and a deep supervision model based segmentation approach is proposed. It primary integrates multi-stage training, pseudo- labeling technique, and a developed deep supervision model with attention mechanism (DLAU-Net), specifically designed for 3D abdominal multi-organ segmentation. The DLAU-Net enhances segmentation performance and model adaptability through an improved network architecture. The multi-stage training strategy accelerates model convergence and enhances generalizability, effectively addressing the diversity of abdominal organ structures. The introduction of pseudo-labeling training alleviates the bottleneck of labeled data scarcity and further improves the model's generalization performance and training efficiency. Experiments were conducted on a large dataset provided by the FLARE 2023 Challenge. Comprehensive ablation studies and comparative experiments were conducted to validate the effectiveness of the proposed method. Our method achieves an average organ accuracy (AVG) of 90.5% and a Dice Similarity Coefficient (DSC) of 89.05% and exhibits exceptional performance in terms of training speed and handling data diversity, particularly in the segmentation tasks of critical abdominal organs such as the liver, spleen, and kidneys, significantly outperforming existing comparative methods.

To develop a robust group-level brain parcellation method using deep learning based on resting-state functional magnetic resonance imaging (rs-fMRI), aiming to release the model assumptions made by previous approaches. We proposed Brain Deep Embedded Clustering (BDEC), a deep clustering model that employs a loss function designed to maximize inter-class separation and enhance intra-class similarity, thereby promoting the formation of functionally coherent brain regions. Compared to ten widely used brain parcellation methods, the BDEC model demonstrates significantly improved performance in various functional homogeneity metrics. It also showed favorable results in parcellation validity, downstream tasks, task inhomogeneity, and generalization capability. The BDEC model effectively captures intrinsic functional properties of the brain, supporting reliable and generalizable parcellation outcomes. BDEC provides a useful parcellation for brain network analysis and dimensionality reduction of rs-fMRI data, while also contributing to a deeper understanding of the brain's functional organization.

Propose and evaluate an automatic approach for predicting the optimal inversion time (TI) for dark and gray blood images for flow-independent dark-blood delayed-enhancement (FIDDLE) acquisition based on free-breathing FIDDLE TI-scout images. In 267 patients, the TI-scout sequence acquired single-shot magnetization-prepared and associated reference images (without preparation) on a 3 T Magnetom Vida and a 1.5 T Magnetom Sola scanner. Data were reconstructed into phase-corrected TI-scout images typically covering TIs from 140 to 440 ms (20 ms increment). A deep learning network was trained to segment the myocardium and blood pool in reference images. These segmentation masks were transferred to the TI-scout images to derive intensity features of myocardium and blood, with which T₁-recovery curves were determined by logarithmic fitting. The optimal TI for dark and gray blood images were derived as linear functions of the TI in which both T₁-curves cross. This TI-prediction pipeline was evaluated in 64 clinical subjects. The pipeline predicted optimal TIs with an average error less than 10 ms compared to manually annotated optimal TIs. The presented approach reliably and automatically predicted optimal TI for dark and gray blood FIDDLE acquisition, with an average error less than the TI increment of the FIDDLE TI-scout sequence.

Vascular aging is an important phenotype characterized by structural and geometric remodeling. Some individuals exhibit supernormal vascular aging, associated with improved cardiovascular outcomes; others experience early vascular aging, linked to adverse cardiovascular outcomes. The aorta is the artery that exhibits the most prominent age-related changes; however, the biological mechanisms underlying aortic aging, its genetic architecture, and its relationship with cardiovascular structure, function, and disease states remain poorly understood. We developed sex-specific models to quantify aortic age on the basis of aortic geometric phenotypes derived from 3-dimensional tomographic imaging data in 2 large biobanks: the UK Biobank and the Penn Medicine BioBank. Convolutional neural ne2rk-assisted 3-dimensional segmentation of the aorta was performed in 56 104 magnetic resonance imaging scans in the UK Biobank and 6757 computed tomography scans in the Penn Medicine BioBank. Aortic vascular age index (AVAI) was calculated as the difference between the vascular age predicted from geometric phenotypes and the chronological age, expressed as a percent of chronological age. We assessed associations with cardiovascular structure and function using multivariate linear regression and examined the genetic architecture of AVAI through genome-wide association studies, followed by Mendelian randomization to assess causal associations. We also constructed a polygenic risk score for AVAI. AVAI displayed numerous associations with cardiac structure and function, including increased left ventricular mass (standardized β=0.144 [95% CI, 0.138, 0.149]; <i>P</i><0.0001), wall thickness (standardized β=0.061 [95% CI, 0.054, 0.068]; <i>P</i><0.0001), and left atrial volume maximum (standardized β=0.060 [95% CI, 0.050, 0.069]; <i>P</i><0.0001). AVAI exhibited high genetic heritability (<i>h</i>²=40.24%). We identified 54 independent genetic loci (<i>P</i><5×10^-⁸) associated with AVAI, which further exhibited gene-level associations with the fibrillin-1 (<i>FBN1</i>) and elastin (<i>ELN1</i>) genes. Mendelian randomization supported causal associations between AVAI and atrial fibrillation, vascular dementia, aortic aneurysm, and aortic dissection. A polygenic risk score for AVAI was associated with an increased prevalence of atrial fibrillation, hypertension, aortic aneurysm, and aortic dissection. Early aortic aging is significantly associated with adverse cardiac remodeling and important cardiovascular disease states. AVAI exhibits a polygenic, highly heritable genetic architecture. Mendelian randomization analyses support a causal association between AVAI and cardiovascular diseases, including atrial fibrillation, vascular dementia, aortic aneurysms, and aortic dissection.

Facioscapulohumeral muscular dystrophy (FSHD) is a genetic neuromuscular disorder characterized by progressive muscle degeneration with substantial variability in severity and progression patterns. FSHD is a highly heterogeneous disease; however, current clinical metrics used for tracking disease progression lack sensitivity for personalized assessment, which greatly limits the design and execution of clinical trials. This study introduces a multi-scale machine learning framework leveraging whole-body magnetic resonance imaging (MRI) and clinical data to predict regional, muscle, joint, and functional progression in FSHD. The goal this work is to create a 'digital twin' of individual FSHD patients that can be leveraged in clinical trials. Using a combined dataset of over 100 patients from seven studies, MRI-derived metrics-including fat fraction, lean muscle volume, and fat spatial heterogeneity at baseline-were integrated with clinical and functional measures. A three-stage random forest model was developed to predict annualized changes in muscle composition and a functional outcome (timed up-and-go (TUG)). All model stages revealed strong predictive performance in separate holdout datasets. After training, the models predicted fat fraction change with a root mean square error (RMSE) of 2.16% and lean volume change with a RMSE of 8.1 ml in a holdout testing dataset. Feature analysis revealed that metrics of fat heterogeneity within muscle predicts muscle-level progression. The stage 3 model, which combined functional muscle groups, predicted change in TUG with a RMSE of 0.6 s in the holdout testing dataset. This study demonstrates the machine learning models incorporating individual muscle and performance data can effectively predict MRI disease progression and functional performance of complex tasks, addressing the heterogeneity and nonlinearity inherent in FSHD. Further studies incorporating larger longitudinal cohorts, as well as comprehensive clinical and functional measures, will allow for expanding and refining this model. As many neuromuscular diseases are characterized by variability and heterogeneity similar to FSHD, such approaches have broad applicability.

Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants ($\leq$32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 $\pm$ 0.10, balanced accuracy of 0.69 $\pm$ 0.10, and an F1-score of 0.67 $\pm$ 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 $\pm$ 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.

<i>"Just Accepted" papers have undergone full peer review and have been accepted for publication in <i>Radiology: Artificial Intelligence</i>. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content.</i> Purpose To develop a transformer-based deep learning model-MR-Transformer-that leverages ImageNet pretraining and three-dimensional (3D) spatial correlations to predict the progression of knee osteoarthritis to TKR using MRI. Materials and Methods This retrospective study included 353 case-control matched pairs of coronal intermediate-weighted turbo spin-echo (COR-IW-TSE) and sagittal intermediate-weighted turbo spin-echo with fat suppression (SAG-IW-TSE-FS) knee MRIs from the Osteoarthritis Initiative (OAI) database, with a follow-up period up to 9 years, and 270 case-control matched pairs of coronal short-tau inversion recovery (COR-STIR) and sagittal proton density fat-saturated (SAG-PD-FAT-SAT) knee MRIs from the Multicenter Osteoarthritis Study (MOST) database, with a follow-up period up to 7 years. Performance of the MR-Transformer to predict the progression of knee osteoarthritis was compared with that of existing state-of-the-art deep learning models (TSE-Net, 3DMeT, and MRNet) using sevenfold nested cross-validation across the four MRI tissue sequences. Results MR-Transformer achieved areas under the receiver operating characteristic curves (AUCs) of 0.88 (95% CI: 0.85, 0.91), 0.88 (95% CI: 0.85, 0.90), 0.86 (95% CI: 0.82, 0.89), and 0.84 (95% CI: 0.81, 0.87) for COR-IW-TSE, SAG-IW-TSE-FS, COR-STIR, and SAG-PD-FAT-SAT, respectively. The model achieved a higher AUC than that of 3DMeT for all MRI sequences (<i>P</i> < .001). The model showed the highest sensitivity of 83% (95% CI: 78, 87%) and specificity of 83% (95% CI: 76, 88%) for the COR-IW-TSE MRI sequence. Conclusion Compared with the existing deep learning models, the MR-Transformer exhibited state-of-the-art performance in predicting the progression of knee osteoarthritis to TKR using MRIs. ©RSNA, 2025.

Endovascular aortic aneurysm repair (EVAR) requires long-term surveillance to detect and treat postoperative complications. However, prediction models to optimise follow-up strategies are still lacking. The primary objective of this study is to develop predictive models of post-operative outcomes following elective EVAR using Artificial Intelligence (AI)-driven analysis. The secondary objective is to investigate morphological aortic changes following EVAR. This international, multicentre, observational study will retrospectively include 500 patients who underwent elective EVAR. Primary outcomes are EVAR postoperative complications including deaths, re-interventions, endoleaks, limb occlusion and stent-graft migration occurring within 1 year and at mid-term follow-up (1 to 3 years). Secondary outcomes are aortic anatomical changes. Morphological changes following EVAR will be analysed and compared based on preoperative and postoperative CT angiography (CTA) images (within 1 to 12 months, and at the last follow-up) using the AI-based software PRAEVAorta 2 (Nurea). Deep learning algorithms will be applied to stratify the risk of postoperative outcomes into low or high-risk categories. The training and testing dataset will be respectively composed of 70% and 30% of the cohort. The study protocol is designed to ensure that the sponsor and the investigators comply with the principles of the Declaration of Helsinki and the ICH E6 good clinical practice guideline. The study has been approved by the ethics committee of the University Hospital of Patras (Patras, Greece) under the number 492/05.12.2024. The results of the study will be presented at relevant national and international conferences and submitted for publication to peer-review journals.