Purpose: Deep learning methods have shown promising results in the segmentation, and detection of diseases in medical images. However, most methods are trained and tested on data from a single source, modality, organ, or disease type, overlooking the combined potential of other available annotated data. Numerous small annotated medical image datasets from various modalities, organs, and diseases are publicly available. In this work, we aim to leverage the synergistic potential of these datasets to improve performance on unseen data. Approach: To this end, we propose a novel algorithm called MMIS-Net (MultiModal Medical Image Segmentation Network), which features Similarity Fusion blocks that utilize supervision and pixel-wise similarity knowledge selection for feature map fusion. Additionally, to address inconsistent class definitions and label contradictions, we created a one-hot label space to handle classes absent in one dataset but annotated in another. MMIS-Net was trained on 10 datasets encompassing 19 organs across 2 modalities to build a single model. Results: The algorithm was evaluated on the RETOUCH grand challenge hidden test set, outperforming large foundation models for medical image segmentation and other state-of-the-art algorithms. We achieved the best mean Dice score of 0.83 and an absolute volume difference of 0.035 for the fluids segmentation task, as well as a perfect Area Under the Curve of 1 for the fluid detection task. Conclusion: The quantitative results highlight the effectiveness of our proposed model due to the incorporation of Similarity Fusion blocks into the network's backbone for supervision and similarity knowledge selection, and the use of a one-hot label space to address label class inconsistencies and contradictions.

Cardiac Magnetic Resonance (CMR) imaging is a critical tool for diagnosing and managing cardiovascular disease, yet its utility is often limited by the sparse acquisition of 2D short-axis slices, resulting in incomplete volumetric information. Accurate 3D reconstruction from these sparse slices is essential for comprehensive cardiac assessment, but existing methods face challenges, including reliance on predefined interpolation schemes (e.g., linear or spherical), computational inefficiency, and dependence on additional semantic inputs such as segmentation labels or motion data. To address these limitations, we propose a novel \textbf{Ca}rdiac \textbf{L}atent \textbf{I}nterpolation \textbf{D}iffusion (CaLID) framework that introduces three key innovations. First, we present a data-driven interpolation scheme based on diffusion models, which can capture complex, non-linear relationships between sparse slices and improves reconstruction accuracy. Second, we design a computationally efficient method that operates in the latent space and speeds up 3D whole-heart upsampling time by a factor of 24, reducing computational overhead compared to previous methods. Third, with only sparse 2D CMR images as input, our method achieves SOTA performance against baseline methods, eliminating the need for auxiliary input such as morphological guidance, thus simplifying workflows. We further extend our method to 2D+T data, enabling the effective modeling of spatiotemporal dynamics and ensuring temporal coherence. Extensive volumetric evaluations and downstream segmentation tasks demonstrate that CaLID achieves superior reconstruction quality and efficiency. By addressing the fundamental limitations of existing approaches, our framework advances the state of the art for spatio and spatiotemporal whole-heart reconstruction, offering a robust and clinically practical solution for cardiovascular imaging.

X-ray digital subtraction angiography (DSA) is frequently used when evaluating minimally invasive medical interventions. DSA predominantly visualizes vessels, and soft tissue anatomy is less visible or invisible in DSA. Visualization of cerebral anatomy could aid physicians during treatment. This study aimed to develop and evaluate a deep learning model to predict vascular territories that are not explicitly visible in DSA imaging acquired during ischemic stroke treatment. We trained an nnUNet model with manually segmented intracranial carotid artery and middle cerebral artery vessel territories on minimal intensity projection DSA acquired during ischemic stroke treatment. We compared the model to a traditional atlas registration model using the Dice similarity coefficient (DSC) and average surface distance (ASD). Additionally, we qualitatively assessed the success rate in both models using an external test. The segmentation model was trained on 1224 acquisitions from 361 patients with ischemic stroke. The segmentation model had a significantly higher DSC (0.96 vs 0.82, p<0.001) and lower ASD compared to the atlas model (13.8 vs 47.3, p<0.001). The success rate of the segmentation model (85%) was higher compared to the atlas registration model (66%) in the external test set. A deep learning method for the segmentation of vascular territories without explicit borders on cerebral DSA demonstrated superior accuracy and quality compared to the traditional atlas-based method. This approach has the potential to be applied to other anatomical structures for enhanced visualization during X-ray guided medical procedures. The code is publicly available at https://github.com/RuishengSu/autoTICI.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition marked by disruptions in brain connectivity. Functional MRI (fMRI) offers a non-invasive window into large-scale neural dynamics by measuring blood-oxygen-level-dependent (BOLD) signals across the brain. These signals can be modeled as interactions among Regions of Interest (ROIs), which are grouped into functional communities based on their underlying roles in brain function. Emerging evidence suggests that connectivity patterns within and between these communities are particularly sensitive to ASD-related alterations. Effectively capturing these patterns and identifying interactions that deviate from typical development is essential for improving ASD diagnosis and enabling biomarker discovery. In this work, we introduce ASDFormer, a Transformer-based architecture that incorporates a Mixture of Pooling-Classifier Experts (MoE) to capture neural signatures associated with ASD. By integrating multiple specialized expert branches with attention mechanisms, ASDFormer adaptively emphasizes different brain regions and connectivity patterns relevant to autism. This enables both improved classification performance and more interpretable identification of disorder-related biomarkers. Applied to the ABIDE dataset, ASDFormer achieves state-of-the-art diagnostic accuracy and reveals robust insights into functional connectivity disruptions linked to ASD, highlighting its potential as a tool for biomarker discovery.

Patient-specific bone models are essential for designing surgical guides and preoperative planning, as they enable the visualization of intricate anatomical structures. However, traditional CT-based approaches for creating bone models are limited to preoperative use due to the low flexibility and high radiation exposure of CT and time-consuming manual delineation. Here, we introduce Semi-Supervised Reconstruction with Knowledge Distillation (SSR-KD), a fast and accurate AI framework to reconstruct high-quality bone models from biplanar X-rays in 30 seconds, with an average error under 1.0 mm, eliminating the dependence on CT and manual work. Additionally, high tibial osteotomy simulation was performed by experts on reconstructed bone models, demonstrating that bone models reconstructed from biplanar X-rays have comparable clinical applicability to those annotated from CT. Overall, our approach accelerates the process, reduces radiation exposure, enables intraoperative guidance, and significantly improves the practicality of bone models, offering transformative applications in orthopedics.

Medical ultrasound image segmentation presents a formidable challenge in the realm of computer vision. Traditional approaches rely on Convolutional Neural Networks (CNNs) and Transformer-based methods to address the intricacies of medical image segmentation. Nevertheless, inherent limitations persist, as CNN-based methods tend to disregard long-range dependencies, while Transformer-based methods may overlook local contextual information. To address these deficiencies, we propose a novel Feature Aggregation Module (FAM) designed to process two input features from the preceding layer. These features are seamlessly directed into two branches of the Convolution and Cross-Attention Parallel Module (CCAPM) to endow them with different roles in each of the two branches to help establish a strong connection between the two input features. This strategy enables our module to focus concurrently on both long-range dependencies and local contextual information by judiciously merging convolution operations with cross-attention mechanisms. Moreover, by integrating FAM within our proposed Spatial-Channel Regulation Module (SCRM), the ability to discern salient regions and informative features warranting increased attention is enhanced. Furthermore, by incorporating the SCRM into the encoder block of the UNet architecture, we introduce a novel framework dubbed Spatial-Channel Regulation Network (SCRNet). The results of our extensive experiments demonstrate the superiority of SCRNet, which consistently achieves state-of-the-art (SOTA) performance compared to existing methods.

Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correlations instead of clinically meaningful features. We introduce LCRReg, a novel regularisation approach that leverages Latent Concept Representations (LCRs) (e.g., Concept Activation Vectors (CAVs)) to guide models toward semantically grounded representations. LCRReg requires no concept labels in the main training set and instead uses a small auxiliary dataset to synthesise high-quality, disentangled concept examples. We extract LCRs for predefined relevant features, and incorporate a regularisation term that guides a Convolutional Neural Network (CNN) to activate within latent subspaces associated with those concepts. We evaluate LCRReg across synthetic and real-world medical tasks. On a controlled toy dataset, it significantly improves robustness to injected spurious correlations and remains effective even in multi-concept and multiclass settings. On the diabetic retinopathy binary classification task, LCRReg enhances performance under both synthetic spurious perturbations and out-of-distribution (OOD) generalisation. Compared to baselines, including multitask learning, linear probing, and post-hoc concept-based models, LCRReg offers a lightweight, architecture-agnostic strategy for improving model robustness without requiring dense concept supervision. Code is available at the following link: https://github.com/Trustworthy-AI-UU-NKI/lcr\_regularization

We introduce Med-CTX, a fully transformer based multimodal framework for explainable breast cancer ultrasound segmentation. We integrate clinical radiology reports to boost both performance and interpretability. Med-CTX achieves exact lesion delineation by using a dual-branch visual encoder that combines ViT and Swin transformers, as well as uncertainty aware fusion. Clinical language structured with BI-RADS semantics is encoded by BioClinicalBERT and combined with visual features utilising cross-modal attention, allowing the model to provide clinically grounded, model generated explanations. Our methodology generates segmentation masks, uncertainty maps, and diagnostic rationales all at once, increasing confidence and transparency in computer assisted diagnosis. On the BUS-BRA dataset, Med-CTX achieves a Dice score of 99% and an IoU of 95%, beating existing baselines U-Net, ViT, and Swin. Clinical text plays a key role in segmentation accuracy and explanation quality, as evidenced by ablation studies that show a -5.4% decline in Dice score and -31% in CIDEr. Med-CTX achieves good multimodal alignment (CLIP score: 85%) and increased confi dence calibration (ECE: 3.2%), setting a new bar for trustworthy, multimodal medical architecture.

Prediction of sex is among important topics of forensic medicine and forensic anthropology. In studies conducted for sex prediction, pelvis and cranium bones are the most preferred bones. In cases when it is difficult to examine the pelvis and cranium bones, vertebrae have been the subject of research in sex analysis studies. The aim of this study is to predict sex by using Computed Tomography (CT) images of the vertebra prominens (C7). Another aim of the study is to make automatic measurements using labeling on C7. This retrospective study included images of 100 female and 100 male individuals (aged 2050 years). CT Images on the personal workstation (Horos Project, Version 3.0) were made orthogonal in the entire plane. They were transferred to the Sekazu program in DICOM format. The labels of the bookmarks determined on C7 were placed on the images by the Radiologist and Anatomist according to their coordinates. Then, automatic measurements were performed in the program and calculations were made. Optimization of the study was achieved by automatic measurements, thus eliminating the effects of intra-observer and/or inter-observer measurement errors. Sixteen length and 3 angle parameters were analysed by using machine learning (ML) algorithms. The accuracy rates in sex prediction using ML algorithms with the parameters obtained as a result of the analysis are as follows: Ada Boost Classification 8791%, Decision Tree 8592%, Extra Trees Classifier 8793%, Gradient Boosting Model 8591%, Gaussian Naive Bayes 8791%, Gaussian Process Classifier 8191%, K-nearest Neighbour Regression 8493%, Linear Discriminant Analysis 8894%, Linear Support Vector Classification 8892%, Non-Linear Support Vector Classification 8393%, Quadratic Discriminant Analysis 8790%, Random Forest 8392%, Support Vector Machines 8492%. In this study, it was predicted that sex prediction could be made up to 94% using ML algorithms from the parameters of vertebra prominens, which is an atypical vertebra. Therefore, we can say that vertebra prominens also shows sexual dimorphism.

BackgroundCognitive decline and memory loss in Alzheimer's disease (AD) progresses over time. Early diagnosis is crucial for initiating treatment that can slow progression and preserve daily functioning. However, challenges such as overfitting in prediction models, underutilized biomarker features, and noisy imaging data hinder the accuracy of current detection methods.ObjectiveThis study proposes a novel deep learning-based framework aimed at improving the identification of AD stages while addressing the limitations of existing diagnostic techniques.MethodsStructural MRI scans are employed as the primary diagnostic tool. To enhance image quality, contrast-limited adaptive histogram equalization and wavelet soft thresholding are applied for noise reduction. Biomarker segmentation focuses on ventricular and hippocampal abnormalities, optimized using a firefly algorithm. Dimensionality reduction is performed via Linear Discriminant Analysis to minimize overfitting. Finally, a Deep Belief Network optimized using the Cuckoo Search algorithm is employed for classification and feature learning.ResultsThe proposed framework demonstrates improved performance over existing methods, achieving a 0.66% increase in accuracy and a 0.0345% decrease in error rate for AD stage detection.ConclusionsThis deep learning strategy shows promise as an effective tool for early and accurate AD stage identification. Enhanced segmentation, dimensionality reduction, and classification contribute to its improved performance, offering a meaningful advancement in AD diagnostics.