Magnetic resonance imaging of fetal and neonatal brains reveals rapid neurodevelopment marked by substantial anatomical changes unfolding within days. Studying this critical stage of the developing human brain, therefore, requires accurate brain models-referred to as atlases-of high spatial and temporal resolution. To meet these demands, established traditional atlases and recently proposed deep learning-based methods rely on large and comprehensive datasets. This poses a major challenge for studying brains in the presence of pathologies for which data remains scarce. We address this limitation with CINeMA (Conditional Implicit Neural Multi-Modal Atlas), a novel framework for creating high-resolution, spatio-temporal, multimodal brain atlases, suitable for low-data settings. Unlike established methods, CINeMA operates in latent space, avoiding compute-intensive image registration and reducing atlas construction times from days to minutes. Furthermore, it enables flexible conditioning on anatomical features including gestational age, birth age, and pathologies like agenesis of the corpus callosum and ventriculomegaly of varying degree. CINeMA supports downstream tasks such as tissue segmentation and age prediction whereas its generative properties enable synthetic data creation and anatomically informed data augmentation. Surpassing state-of-the-art methods in accuracy, efficiency, and versatility, CINeMA represents a powerful tool for advancing brain research. We release the code and atlases at https://github.com/m-dannecker/CINeMA.

Domain generalization remains a critical challenge in medical imaging, where models trained on single sources often fail under real-world distribution shifts. We propose KG-DG, a neuro-symbolic framework for diabetic retinopathy (DR) classification that integrates vision transformers with expert-guided symbolic reasoning to enable robust generalization across unseen domains. Our approach leverages clinical lesion ontologies through structured, rule-based features and retinal vessel segmentation, fusing them with deep visual representations via a confidence-weighted integration strategy. The framework addresses both single-domain generalization (SDG) and multi-domain generalization (MDG) by minimizing the KL divergence between domain embeddings, thereby enforcing alignment of high-level clinical semantics. Extensive experiments across four public datasets (APTOS, EyePACS, Messidor-1, Messidor-2) demonstrate significant improvements: up to a 5.2% accuracy gain in cross-domain settings and a 6% improvement over baseline ViT models. Notably, our symbolic-only model achieves a 63.67% average accuracy in MDG, while the complete neuro-symbolic integration achieves the highest accuracy compared to existing published baselines and benchmarks in challenging SDG scenarios. Ablation studies reveal that lesion-based features (84.65% accuracy) substantially outperform purely neural approaches, confirming that symbolic components act as effective regularizers beyond merely enhancing interpretability. Our findings establish neuro-symbolic integration as a promising paradigm for building clinically robust, and domain-invariant medical AI systems.

 : High-grade serous ovarian carcinoma (HGSOC) is characterised by significant spatial and temporal heterogeneity, often presenting at an advanced metastatic stage. One of the most common treatment approaches involves neoadjuvant chemotherapy (NACT), followed by surgery. However, the multi-scale complexity of HGSOC poses a major challenge in evaluating response to NACT.  : Here, we present a multi-task deep learning approach that facilitates simultaneous segmentation of pelvic/ovarian and omental lesions in contrast-enhanced computerised tomography (CE-CT) scans, as well as treatment response assessment in metastatic ovarian cancer. The model combines multi-scale feature representations from two identical U-Net architectures, allowing for an in-depth comparison of CE-CT scans acquired before and after treatment. The network was trained using 198 CE-CT images of 99 ovarian cancer patients for predicting segmentation masks and evaluating treatment response.  : It achieves an AUC of 0.78 (95% CI [0.70-0.91]) in an independent cohort of 98 scans of 49 ovarian cancer patients from a different institution. In addition to the classification performance, the segmentation Dice scores are only slightly lower than the current state-of-the-art for HGSOC segmentation.  : This work is the first to demonstrate the feasibility of a multi-task deep learning approach in assessing chemotherapy-induced tumour changes across the main disease burden of patients with complex multi-site HGSOC, which could be used for treatment response evaluation and disease monitoring.

Non-small cell lung cancer (NSCLC) is a complex disease characterized by diverse clinical, genetic, and histopathologic traits, necessitating personalized treatment approaches. While numerous biomarkers have been introduced for NSCLC prognostication, no single source of information can provide a comprehensive understanding of the disease. However, integrating biomarkers from multiple sources may offer a holistic view of the disease, enabling more accurate predictions. In this study, we present MetaPredictomics, a framework that integrates clinicopathologic data with PET/CT radiomics from the primary tumor and presumed healthy organs (referred to as "organomics") to predict postsurgical recurrence. A fully automated deep learning-based segmentation model was employed to delineate 19 affected (whole lung and the affected lobe) and presumed healthy organs from CT images of the presurgical PET/CT scans of 145 NSCLC patients sourced from a publicly available data set. Using PyRadiomics, 214 features (107 from CT, 107 from PET) were extracted from the gross tumor volume (GTV) and each segmented organ. In addition, a clinicopathologic feature set was constructed, incorporating clinical characteristics, histopathologic data, gene mutation status, conventional PET imaging biomarkers, and patients' treatment history. GTV Radiomics, each of the organomics, and the clinicopathologic feature sets were each fed to a time-to-event prediction machine, based on glmboost, to establish first-level models. The risk scores obtained from the first-level models were then used as inputs for meta models developed using a stacked ensemble approach. Questing optimized performance, we assessed meta models established upon all combinations of first-level models with concordance index (C-index) ≥0.6. The performance of all the models was evaluated using the average C-index across a unique 3-fold cross-validation scheme for fair comparison. The clinicopathologic model outperformed other first-level models with a C-index of 0.67, followed closely by GTV radiomics model with C-index of 0.65. Among the organomics models, whole-lung and aorta models achieved top performance with a C-index of 0.65, while 12 organomics models achieved C-indices of ≥0.6. Meta models significantly outperformed the first-level models with the top 100 achieving C-indices between 0.703 and 0.731. The clinicopathologic, whole lung, esophagus, pancreas, and GTV models were the most frequently present models in the top 100 meta models with frequencies of 98, 71, 69, 62, and 61, respectively. In this study, we highlighted the value of maximizing the use of medical imaging for NSCLC recurrence prognostication by incorporating data from various organs, rather than focusing solely on the tumor and its immediate surroundings. This multisource integration proved particularly beneficial in the meta models, where combining clinicopathologic data with tumor radiomics and organomics models significantly enhanced recurrence prediction.

The effectiveness of convolutional neural networks in medical image segmentation relies on large-scale, high-quality annotations, which are costly and time-consuming to obtain. Even expert-labeled datasets inevitably contain noise arising from subjectivity and coarse delineations, which disrupt feature learning and adversely impact model performance. To address these challenges, this study propose a Geometric-Structural Dual-Guided Network (GSD-Net), which integrates geometric and structural cues to improve robustness against noisy annotations. It incorporates a Geometric Distance-Aware module that dynamically adjusts pixel-level weights using geometric features, thereby strengthening supervision in reliable regions while suppressing noise. A Structure-Guided Label Refinement module further refines labels with structural priors, and a Knowledge Transfer module enriches supervision and improves sensitivity to local details. To comprehensively assess its effectiveness, we evaluated GSD-Net on six publicly available datasets: four containing three types of simulated label noise, and two with multi-expert annotations that reflect real-world subjectivity and labeling inconsistencies. Experimental results demonstrate that GSD-Net achieves state-of-the-art performance under noisy annotations, achieving improvements of 2.52% on Kvasir, 22.76% on Shenzhen, 8.87% on BU-SUC, and 4.59% on BraTS2020 under SR simulated noise. The codes of this study are available at https://github.com/ortonwang/GSD-Net.

Accurate breast MRI lesion detection is critical for early cancer diagnosis, especially in high-risk populations. We present a classification pipeline that adapts a pretrained foundation model, the Medical Slice Transformer (MST), for breast lesion classification using dynamic contrast-enhanced MRI (DCE-MRI). Leveraging DINOv2-based self-supervised pretraining, MST generates robust per-slice feature embeddings, which are then used to train a Kolmogorov--Arnold Network (KAN) classifier. The KAN provides a flexible and interpretable alternative to conventional convolutional networks by enabling localized nonlinear transformations via adaptive B-spline activations. This enhances the model's ability to differentiate benign from malignant lesions in imbalanced and heterogeneous clinical datasets. Experimental results demonstrate that the MST+KAN pipeline outperforms the baseline MST classifier, achieving AUC = 0.80 \pm 0.02 while preserving interpretability through attention-based heatmaps. Our findings highlight the effectiveness of combining foundation model embeddings with advanced classification strategies for building robust and generalizable breast MRI analysis tools.

The aim of this study was to develop, test and validate automated interpretable deep learning algorithms for the assessment and classification of the spheno-occipital synchondrosis (SOS) fusion stages from a cone beam computed tomography (CBCT). The sample consisted of 723 CBCT scans of orthodontic patients from private practices in the midwestern United States. The SOS fusion stages were classified by two orthodontists and an oral and maxillofacial radiologist. The advanced deep learning models employed consisted of ResNet, EfficientNet and ConvNeXt. Additionally, a new attention-based model, ConvNeXt + Conv Attention, was developed to enhance classification accuracy by integrating attention mechanisms for capturing subtle medical imaging features. Laslty, YOLOv11 was integrated for fully-automated region detection and segmentation. ConvNeXt + Conv Attention outperformed the other models and achieved a 88.94% accuracy with manual cropping and 82.49% accuracy in a fully automated workflow. This study introduces a novel artificial intelligence-based pipeline that reliably automates the classification of the SOS fusion stages using advanced deep learning models, with the highest accuracy achieved by ConvNext + Conv Attention. These models enhance the efficiency, scalability and consistency of SOS staging while minimising manual intervention from the clinician, underscoring the potential for AI-driven solutions in orthodontics and clinical workflows.

This study aimed to develop a deep learning (DL) framework using registration-guided generative adversarial networks (RegGAN) to synthesize contrast-enhanced CT (Syn-CECT) from non-contrast CT (NCCT), enabling iodine-free esophageal cancer (EC) T-staging. A retrospective multicenter analysis included 1,092 EC patients (2013-2024) divided into training (N = 313), internal (N = 117), and external test cohorts (N = 116 and N = 546). RegGAN synthesized Syn-CECT by integrating registration and adversarial training to address NCCT-CECT misalignment. Tumor segmentation used CSSNet with hierarchical feature fusion, while T-staging employed a dual-path DL model combining radiomic features (from NCCT/Syn-CECT) and Vision Transformer-derived deep features. Performance was validated via quantitative metrics (NMAE, PSNR, SSIM), Dice scores, AUC, and reader studies comparing six clinicians with/without model assistance. RegGAN achieved Syn-CECT quality comparable to real CECT (NMAE = 0.1903, SSIM = 0.7723; visual scores: p ≥ 0.12). CSSNet produced accurate tumor segmentation (Dice = 0.89, 95% HD = 2.27 in external tests). The DL staging model outperformed machine learning (AUC = 0.7893-0.8360 vs. ≤ 0.8323), surpassing early-career clinicians (AUC = 0.641-0.757) and matching experts (AUC = 0.840). Syn-CECT-assisted clinicians improved diagnostic accuracy (AUC increase: ~ 0.1, p < 0.01), with decision curve analysis confirming clinical utility at > 35% risk threshold. The RegGAN-based framework eliminates contrast agents while maintaining diagnostic accuracy for EC segmentation (Dice > 0.88) and T-staging (AUC > 0.78). It offers a safe, cost-effective alternative for patients with iodine allergies or renal impairment and enhances diagnostic consistency across clinician experience levels. This approach addresses limitations of invasive staging and repeated contrast exposure, demonstrating transformative potential for resource-limited settings.

Autism Spectrum Disorder (ASD) is a neurological condition that affects the brain, leading to challenges in speech, communication, social interaction, repetitive behaviors, and motor skills. This research aims to develop a deep learning based model for the accurate diagnosis and classification of autistic symptoms in children, thereby benefiting both patients and their families. Existing literature indicates that classification methods typically analyze region based summaries of Functional Magnetic Resonance Imaging (fMRI). However, few studies have explored the diagnosis of ASD using brain imaging. The complexity and heterogeneity of biomedical data modeling for big data analysis related to ASD remain unclear. In the present study, the Autism Brain Imaging Data Exchange 1 (ABIDE-1) dataset was utilized, comprising 1,112 participants, including 539 individuals with ASD and 573 controls from 17 different sites. The dataset, originally in NIfTI format, required conversion to a computer-readable extension. For ASD classification, the researcher proposed and implemented a VGG20 architecture. This deep learning VGG20 model was applied to neuroimages to distinguish ASD from the non ASD cases. Four evaluation metrics were employed which are recall, precision, F1-score, and accuracy. Experimental results indicated that the proposed model achieved an accuracy of 61%. Prior to this work, machine learning algorithms had been applied to the ABIDE-1 dataset, but deep learning techniques had not been extensively utilized for this dataset and the methods implied in this study as this research is conducted to facilitate the early diagnosis of ASD.

Prostate cancer is a leading health concern for men, yet current clinical assessments of tumor aggressiveness rely on invasive procedures that often lead to inconsistencies. There remains a critical need for accurate, noninvasive diagnosis and grading methods. Here we developed a foundation model trained on multiparametric magnetic resonance imaging (MRI) and paired pathology data for noninvasive diagnosis and grading of prostate cancer. Our model, MRI-based Predicted Transformer for Prostate Cancer (MRI-PTPCa), was trained under contrastive learning on nearly 1.3 million image-pathology pairs from over 5,500 patients in discovery, modeling, external and prospective cohorts. During real-world testing, prediction of MRI-PTPCa demonstrated consistency with pathology and superior performance (area under the curve above 0.978; grading accuracy 89.1%) compared with clinical measures and other prediction models. This work introduces a scalable, noninvasive approach to prostate cancer diagnosis and grading, offering a robust tool to support clinical decision-making while reducing reliance on biopsies.