Physics-Embedded Feature Learning for AI in Medical Imaging

TL;DR

PhysNet is a physics-embedded deep learning framework that integrates tumor growth dynamics into CNNs for improved interpretability, robustness, and accuracy in medical imaging classification tasks.

Contribution

This work introduces PhysNet, which embeds a reaction diffusion tumor growth model within CNN features, enabling end-to-end learning of physically meaningful parameters and improved performance.

Findings

PhysNet outperforms state-of-the-art models on brain MRI tumor classification.

PhysNet produces interpretable tumor density and growth parameters.

PhysNet achieves higher accuracy and F1-score than baseline models.

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.