Reject Option for Medical Image Classification Using CNN-Derived Latent-Space Neighbourhood Analysis.

Unmasking clinical shortcuts: a latent-space audit of dense convolutional networks for chest radiography

Deep convolutional neural networks (CNNs) in medical imaging can achieve acceptable global discrimination while still relying on shortcut-sensitive signals that undermine reliability in clinically important subgroups. In chest radiography, non-pathological factors such as image acquisition view, support devices, and su...

Weakly Supervised MRI-Based Classification of Alzheimer’s Disease Using Clinical Pseudo-Labels

Alzheimer’s disease (AD) classification from structural magnetic resonance imaging (MRI) may benefit from weak supervision that uses clinically meaningful but imperfect supervisory signals. We evaluated a weakly supervised framework in which a multilayer perceptron (MLP) trained on age, sex, and Mini-Mental State Exami...

Ensemble Approaches for GAN Membership Inference and Latent Vector Prediction

A modified dual-task DenseNet121 with Grad-CAM interpretability for brain tumor classification from MRI

Modified DenseNet121 (Dual-Task framework built on a modified DenseNet121 with a custom regularization stack) is introduced to detect abnormalities and identify three tumor types in a single architecture and offers reproducible, interpretable, and research prototype foundation for future clinical translation of neuro-o...

From Image Latent Space to Fuzzy Rules: Interpretable Analysis of Gastrointestinal Foundation Model

Foundation models pretrained on large-scale datasets demonstrate strong transferability to medical imaging tasks. However, understanding how their latent representations encode clinically relevant information remains an open challenge in safety-critical domains. This study proposes a prototype-based fuzzy-rule framewor...

Beyond accuracy: calibration and uncertainty in multi-architecture ensembles for MedMNIST classification