Foundation models (FMs) such as CLIP and SAM have recently shown great promise in image segmentation tasks, yet their adaptation to 3D medical imaging-particularly for pathology detection and segmentation-remains underexplored. A critical challenge arises from the domain gap between natural images and medical volumes: existing FMs, pre-trained on 2D data, struggle to capture 3D anatomical context, limiting their utility in clinical applications like tumor segmentation. To address this, we propose an adaptation framework called TAGS: Tumor Adaptive Guidance for SAM, which unlocks 2D FMs for 3D medical tasks through multi-prompt fusion. By preserving most of the pre-trained weights, our approach enhances SAM's spatial feature extraction using CLIP's semantic insights and anatomy-specific prompts. Extensive experiments on three open-source tumor segmentation datasets prove that our model surpasses the state-of-the-art medical image segmentation models (+46.88% over nnUNet), interactive segmentation frameworks, and other established medical FMs, including SAM-Med2D, SAM-Med3D, SegVol, Universal, 3D-Adapter, and SAM-B (at least +13% over them). This highlights the robustness and adaptability of our proposed framework across diverse medical segmentation tasks.

Image segmentation plays a central role in computer vision applications such as medical imaging, industrial inspection, and environmental monitoring. However, evaluating segmentation performance can be particularly challenging when ground truth is not clearly defined, as is often the case in tasks involving subjective interpretation. These challenges are amplified by inter- and intra-observer variability, which complicates the use of human annotations as a reliable reference. To address this, we propose a novel validation framework-referred to as the three-blind validation strategy-that enables rigorous assessment of segmentation models in contexts where subjectivity and label variability are significant. The core idea is to have a third independent expert, blind to the labeler identities, assess a shuffled set of segmentations produced by multiple human annotators and/or automated models. This allows for the unbiased evaluation of model performance and helps uncover patterns of disagreement that may indicate systematic issues with either human or machine annotations. The primary objective of this study is to introduce and demonstrate this validation strategy as a generalizable framework for robust model evaluation in subjective segmentation tasks. We illustrate its practical implementation in a mammography use case involving dense tissue segmentation while emphasizing its potential applicability to a broad range of segmentation scenarios.

Desmoid tumors are rare, locally invasive soft-tissue tumors with unpredictable clinical behavior. Imaging plays a crucial role in their diagnosis, measurement of disease burden, and assessment of treatment response. However, desmoid tumors' unique imaging features present challenges to conventional imaging metrics. The heterogeneous nature of these tumors, with a variable composition (fibrous, myxoid, or cellular), complicates accurate delineation of tumor boundaries and volumetric assessment. Furthermore, desmoid tumors can demonstrate prolonged stability or spontaneous regression, and biologic quiescence is often manifested by collagenization rather than bulk size reduction, making traditional size-based response criteria, such as Response Evaluation Criteria in Solid Tumors (RECIST), suboptimal. To overcome these limitations, advanced imaging techniques offer promising opportunities. Functional and parametric imaging methods, such as diffusion-weighted MRI, dynamic contrast-enhanced MRI, and T2 relaxometry, can provide insights into tumor cellularity and maturation. Radiomics and artificial intelligence approaches may enhance quantitative analysis by extracting and correlating complex imaging features with biological behavior. Moreover, imaging biomarkers could facilitate earlier detection of treatment efficacy or resistance, enabling tailored therapy. By integrating advanced imaging into clinical practice, it may be possible to refine the evaluation of disease burden and treatment response, ultimately improving the management and outcomes of patients with desmoid tumors.

Automatic pancreas segmentation in CT scans is crucial for various medical applications, including early diagnosis and computer-assisted surgery. However, existing segmentation methods remain suboptimal due to significant pancreas size variations across slices and severe class imbalance caused by the pancreas's small size and CT scanner movement during imaging. Traditional computer vision techniques struggle with these challenges, while deep learning-based approaches, despite their success in other domains, still face limitations in pancreas segmentation. To address these issues, we propose a novel, three-stage workflow that enhances segmentation accuracy and computational efficiency. First, we introduce External Contour Cropping (ECC), a background cleansing technique that mitigates class imbalance. Second, we propose a Size Ratio (SR) technique that restructures the training dataset based on the relative size of the target organ, improving the robustness of the model against anatomical variations. Third, we develop MOMUNet, an ultra-lightweight segmentation model with only 1.31 million parameters, designed for optimal performance on limited computational resources. Our proposed workflow achieves an improvement in Dice Score (DSC) of 2.56% over state-of-the-art (SOTA) models in the NIH-Pancreas dataset and 2.97% in the MSD-Pancreas dataset. Furthermore, applying the proposed model to another small organ, such as colon cancer segmentation in the MSD-Colon dataset, yielded a DSC of 68.4%, surpassing the SOTA models. These results demonstrate the effectiveness of our approach in significantly improving segmentation accuracy for small abdomen organs including pancreas and colon, making deep learning more accessible for low-resource medical facilities.

Deep learning methods provide enormous promise in automating manually intense tasks such as medical image segmentation and provide workflow assistance to clinical experts. Deep neural networks (DNN) require a significant amount of training examples and a variety of expert opinions to capture the nuances and the context, a challenging proposition in oncological studies (H. Wang et al., Nature, vol. 620, no. 7972, pp. 47-60, Aug 2023). Inter-reader variability among clinical experts is a real-world problem that severely impacts the generalization of DNN reproducibility. This study proposes quantifying the variability in DNN performance using expert opinions and exploring strategies to train the network and adapt between expert opinions. We address the inter-reader variability problem in the context of prostate gland segmentation using a well-studied DNN, the 3D U-Net model. Reference data includes magnetic resonance imaging (MRI, T2-weighted) with prostate glandular anatomy annotations from two expert readers (R#1, n = 342 and R#2, n = 204). 3D U-Net was trained and tested with individual expert examples (R#1 and R#2) and had an average Dice coefficient of 0.825 (CI, [0.81 0.84]) and 0.85 (CI, [0.82 0.88]), respectively. Combined training with a representative cohort proportion (R#1, n = 100 and R#2, n = 150) yielded enhanced model reproducibility across readers, achieving an average test Dice coefficient of 0.863 (CI, [0.85 0.87]) for R#1 and 0.869 (CI, [0.87 0.88]) for R#2. We re-evaluated the model performance across the gland volumes (large, small) and found improved performance for large gland size with an average Dice coefficient to be at 0.846 [CI, 0.82 0.87] and 0.872 [CI, 0.86 0.89] for R#1 and R#2, respectively, estimated using fivefold cross-validation. Performance for small gland sizes diminished with average Dice of 0.8 [0.79, 0.82] and 0.8 [0.79, 0.83] for R#1 and R#2, respectively.

Deep learning, a subset of machine learning, is widely utilized in medical applications. Identifying maxillary sinus pathologies before surgical interventions is crucial for ensuring successful treatment outcomes. Cone beam computed tomography (CBCT) is commonly employed for maxillary sinus evaluations due to its high resolution and lower radiation exposure. This study aims to assess the accuracy of artificial intelligence (AI) algorithms in detecting maxillary sinus pathologies from CBCT scans. A dataset comprising 1000 maxillary sinuses (MS) from 500 patients was analyzed using CBCT. Sinuses were categorized based on the presence or absence of pathology, followed by segmentation of the maxillary sinus. Manual segmentation masks were generated using the semiautomatic software ITK-SNAP, which served as a reference for comparison. A convolutional neural network (CNN)-based machine learning model was then implemented to automatically segment maxillary sinus pathologies from CBCT images. To evaluate segmentation accuracy, metrics such as the Dice similarity coefficient (DSC) and intersection over union (IoU) were utilized by comparing AI-generated results with human-generated segmentations. The automated segmentation model achieved a Dice score of 0.923, a recall of 0.979, an IoU of 0.887, an F1 score of 0.970, and a precision of 0.963. This study successfully developed an AI-driven approach for segmenting maxillary sinus pathologies in CBCT images. The findings highlight the potential of this method for rapid and accurate clinical assessment of maxillary sinus conditions using CBCT imaging.

To evaluate the value of employing artificial intelligence (AI)-assisted CT pulmonary angiography (CTPA) for patients with chronic thromboembolic pulmonary hypertension (CTEPH) and chronic thromboembolic disease (CTED). A single-center, retrospective analysis of 350 sequential patients with right heart catheterization (RHC)-confirmed CTEPH, CTED, and normal controls was conducted. Parameters such as the main pulmonary artery diameter (MPAd), the ratio of MPA to ascending aorta diameter (MPAd/AAd), the ratio of right to left ventricle diameter (RVd/LVd), and the ratio of RV to LV volume (RVv/LVv) were evaluated using automated AI software and compared with manual analysis. The reliability was assessed through an intraclass correlation coefficient (ICC) analysis. The diagnostic accuracy was determined using receiver-operating characteristic (ROC) curves. Compared to CTED and control groups, CTEPH patients were significantly more likely to have elevated automatic CTPA metrics (all p < 0.001, respectively). Automated MPAd, MPAd/Aad, and RVv/LVv had a strong correlation with mPAP (r = 0.952, 0.904, and 0.815, respectively, all p < 0.001). The automated and manual CTPA analyses showed strong concordance. For the CTEPH and CTED categories, the optimal area under the curve (AU-ROC) reached 0.939 (CI: 0.908-0.969). In the CTEPH and control groups, the best AU-ROC was 0.970 (CI: 0.953-0.988). In the CTED and control groups, the best AU-ROC was 0.782 (CI: 0.724-0.840). Automated AI-driven CTPA analysis provides a dependable approach for evaluating patients with CTEPH, CTED, and normal controls, demonstrating excellent consistency and efficiency. Question Guidelines do not advocate for applying treatment protocols for CTEPH to patients with CTED; early detection of the condition is crucial. Findings Automated CTPA analysis was feasible in 100% of patients with good agreement and would have added information for early detection and identification. Clinical relevance Automated AI-driven CTPA analysis provides a reliable approach demonstrating excellent consistency and efficiency. Additionally, these noninvasive imaging findings may aid in treatment stratification and determining optimal intervention directed by RHC.

This study centers around the competition between Convolutional Neural Networks (CNNs) with large convolutional kernels and Vision Transformers in the domain of computer vision, delving deeply into the issues pertaining to parameters and computational complexity that stem from the utilization of large convolutional kernels. Even though the size of the convolutional kernels has been extended up to 51×51, the enhancement of performance has hit a plateau, and moreover, striped convolution incurs a performance degradation. Enlightened by the hierarchical visual processing mechanism inherent in humans, this research innovatively incorporates a shared parameter mechanism for large convolutional kernels. It synergizes the expansion of the receptive field enabled by large convolutional kernels with the extraction of fine-grained features facilitated by small convolutional kernels. To address the surging number of parameters, a meticulously designed parameter sharing mechanism is employed, featuring fine-grained processing in the central region of the convolutional kernel and wide-ranging parameter sharing in the periphery. This not only curtails the parameter count and mitigates the model complexity but also sustains the model's capacity to capture extensive spatial relationships. Additionally, in light of the problems of spatial feature information loss and augmented memory access during the 1×1 convolutional channel compression phase, this study further puts forward a dynamic channel sampling approach, which markedly elevates the accuracy of tumor subregion segmentation. To authenticate the efficacy of the proposed methodology, a comprehensive evaluation has been conducted on three brain tumor segmentation datasets, namely BraTs2020, BraTs2024, and Medical Segmentation Decathlon Brain 2018. The experimental results evince that the proposed model surpasses the current mainstream ConvNet and Transformer architectures across all performance metrics, proffering novel research perspectives and technical stratagems for the realm of medical image segmentation.

Glioblastoma (GBM) is a highly aggressive brain tumor with poor prognosis. This study aimed to construct and validate a radiomics-based machine learning model for predicting overall survival (OS) in IDH-wildtype GBM after maximal safe surgical resection using magnetic resonance imaging. A total of 582 patients were retrospectively enrolled, comprising 301 in the training cohort, 128 in the internal validation cohort, and 153 in the external validation cohort. Volumes of interest (VOIs) from contrast-enhanced T1-weighted imaging (CE-T1WI) were segmented into three regions: contrast-enhancing tumor, necrotic non-enhancing core, and peritumoral edema using an ResNet-based segmentation network. A total of 4,227 radiomic features were extracted and filtered using LASSO-Cox regression to identify signatures. The prognostic model was constructed using the Mime prediction framework, categorizing patients into high- and low-risk groups based on the median OS. Model performance was assessed using the concordance index (CI) and Kaplan-Meier survival analysis. Independent prognostic factors were identified through multivariable Cox regression analysis, and a nomogram was developed for individualized risk assessment. The Step Cox [backward] + RSF model achieved CIs of 0.89, 0.81, and 0.76 in the training, internal and external validation cohorts. Log-rank tests demonstrated significant survival differences between high- and low-risk groups across all cohorts (P < 0.05). Multivariate Cox analysis identified age (HR: 1.022; 95% CI: 0.979, 1.009, P < 0.05), KPS score (HR: 0.970, 95% CI: 0.960, 0.978, P < 0.05), rad-scores of the necrotic non-enhancing core (HR: 8.164; 95% CI: 2.439, 27.331, P < 0.05), and peritumoral edema (HR: 3.748; 95% CI: 1.212, 11.594, P < 0.05) as independent predictors of OS. A nomogram integrating these predictors provided individualized risk assessment. This deep learning segmentation-based radiomics model demonstrated robust performance in predicting OS in GBM after maximal safe surgical resection. By incorporating radiomic signatures and advanced machine learning algorithms, it offers a non-invasive tool for personalized prognostic assessment and supports clinical decision-making.

Surface-based cortical analysis is valuable for a variety of neuroimaging tasks, such as spatial normalization, parcellation, and gray matter (GM) thickness estimation. However, most tools for estimating cortical surfaces work exclusively on scans with at least 1 mm isotropic resolution and are tuned to a specific magnetic resonance (MR) contrast, often T1-weighted (T1w). This precludes application using most clinical MR scans, which are very heterogeneous in terms of contrast and resolution. Here, we use synthetic domain-randomized data to train the first neural network for explicit estimation of cortical surfaces from scans of any contrast and resolution, without retraining. Our method deforms a template mesh to the white matter (WM) surface, which guarantees topological correctness. This mesh is further deformed to estimate the GM surface. We compare our method to recon-all-clinical (RAC), an implicit surface reconstruction method which is currently the only other tool capable of processing heterogeneous clinical MR scans, on ADNI and a large clinical dataset (n=1,332). We show a approximately 50 % reduction in cortical thickness error (from 0.50 to 0.24 mm) with respect to RAC and better recovery of the aging-related cortical thinning patterns detected by FreeSurfer on high-resolution T1w scans. Our method enables fast and accurate surface reconstruction of clinical scans, allowing studies (1) with sample sizes far beyond what is feasible in a research setting, and (2) of clinical populations that are difficult to enroll in research studies. The code is publicly available at https://github.com/simnibs/brainnet.