Physics-Embedded Feature Learning for AI in Medical Imaging

2026-03-30

AI Summary

This study addresses the limited interpretability and robustness of current deep learning models in medical image analysis, which often operate as black boxes and neglect the underlying biophysical mechanisms of tumor growth. To bridge this gap, the authors propose PhysNet, a novel framework that integrates reaction-diffusion equations into intermediate feature layers of a convolutional neural network. Within an end-to-end training paradigm, PhysNet jointly optimizes multi-class tumor classification alongside the inference of latent tumor density fields and associated biophysical parameters—such as diffusion and proliferation rates—ensuring physical consistency without compromising performance. Evaluated on a large-scale brain MRI dataset, PhysNet outperforms MobileNetV2, VGG16, VGG19, and ensemble baselines in both classification accuracy and F1 score, while producing interpretable representations aligned with established medical understanding.

Abstract

Deep learning (DL) models have achieved strong performance in an intelligence healthcare setting, yet most existing approaches operate as black boxes and ignore the physical processes that govern tumor growth, limiting interpretability, robustness, and clinical trust. To address this limitation, we propose PhysNet, a physics-embedded DL framework that integrates tumor growth dynamics directly into the feature learning process of a convolutional neural network (CNN). Unlike conventional physics-informed methods that impose physical constraints only at the output level, PhysNet embeds a reaction diffusion model of tumor growth within intermediate feature representations of a ResNet backbone. The architecture jointly performs multi-class tumor classification while learning a latent tumor density field, its temporal evolution, and biologically meaningful physical parameters, including tumor diffusion and growth rates, through end-to-end training. This design is necessary because purely data-driven models, even when highly accurate or ensemble-based, cannot guarantee physically consistent predictions or provide insight into tumor behavior. Experimental results on a large brain MRI dataset demonstrate that PhysNet outperforms multiple state-of-the-art DL baselines, including MobileNetV2, VGG16, VGG19, and ensemble models, achieving superior classification accuracy and F1-score. In addition to improved performance, PhysNet produces interpretable latent representations and learned bio-physical parameters that align with established medical knowledge, highlighting physics-embedded representation learning as a practical pathway toward more trustworthy and clinically meaningful medical AI systems.

Problem

• medical imaging
• tumor growth
• deep learning
• interpretability
• physics-informed AI

Innovation

• physics-embedded learning
• tumor growth modeling
• reaction-diffusion
• interpretable AI
• medical imaging