Physics-Embedded Feature Learning for AI in Medical Imaging

• URL: http://arxiv.org/abs/2603.28057v1
• Date: Mon, 30 Mar 2026 05:45:27 GMT
• Title: Physics-Embedded Feature Learning for AI in Medical Imaging
• Abstract summary: PhysNet is a physics-embedded deep learning framework that integrates tumor growth dynamics directly into the feature learning process.<n>The architecture jointly performs multi-class tumor classification while learning a latent tumor density field.<n> PhysNet produces interpretable latent representations and learned bio-physical parameters that align with established medical knowledge.
• Score: 4.951195507300242
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks [0.0]
  The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction.<n>This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data.
  arXiv  Detail & Related papers  (2026-09-01T15:34:23Z)
• Where Physics Meets Privacy: Federated PINNs for Privacy-Preserving Brain Tumor Biomechanical Modeling [0.0]
  This study presents a federated physics informed neural network combining federated learning with a physics informed loss built on the equations of linear elasticity.<n>The model reached an overall accuracy of 91.4%, against 90.0% for a non federated baseline trained on pooled data, and a rise in pituitary tumor accuracy from 85.6 to 94.5%.
  arXiv  Detail & Related papers  (2026-07-28T19:15:37Z)
• Brain-WM: Brain Glioblastoma World Model [56.45393372490125]
  We present Brain-WM, a pioneering GBM world model that unifies next-step treatment prediction and future MRI generation.<n>Brain-WM encodes latent dynamics into a shared latent space for joint autoregressive treatment prediction and flow-based future MRI generation.<n>Ultimately, Brain-WM offers a robust clinical sandbox for optimizing patient healthcare.
  arXiv  Detail & Related papers  (2026-03-08T09:54:08Z)
• Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective [89.99666725996975]
  The brain age gap prediction (BAGP) models estimate the difference between a person's predicted brain age from data and their chronological age.<n>This tutorial article provides an overview of BAGP and introduces a principled framework for this application based on recent advancements in graph signal processing (GSP)<n>VNNs offer strong theoretical grounding and operational interpretability, enabling robust estimation of brain age gap predictions.
  arXiv  Detail & Related papers  (2025-10-14T17:44:45Z)
• NOBLE -- Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models [63.592664795493725]
  NOBLE is a neural operator framework that learns a mapping from a continuous frequency-modulated embedding of interpretable neuron features to the somatic voltage response induced by current injection.<n>It predicts distributions of neural dynamics accounting for the intrinsic experimental variability.<n>NOBLE is the first scaled-up deep learning framework that validates its generalization with real experimental data.
  arXiv  Detail & Related papers  (2025-06-05T01:01:18Z)
• Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization [3.666412718346211]
  We introduce a novel method that integrates data-driven and physics-based cost functions. We propose a unique discretization scheme that quantifies how well the learned distributions of tumor and brain tissues adhere to their respective growth and elasticity equations.
  arXiv  Detail & Related papers  (2024-09-30T15:36:14Z)
• ContPhy: Continuum Physical Concept Learning and Reasoning from Videos [86.63174804149216]
  ContPhy is a novel benchmark for assessing machine physical commonsense. We evaluated a range of AI models and found that they still struggle to achieve satisfactory performance on ContPhy. We also introduce an oracle model (ContPRO) that marries the particle-based physical dynamic models with the recent large language models.
  arXiv  Detail & Related papers  (2024-02-09T01:09:21Z)
• Explainable Deep Learning for Tumor Dynamic Modeling and Overall Survival Prediction using Neural-ODE [0.0]
  We propose the use of Tumor Dynamic Neural-ODE as a pharmacology-informed neural network. We show that TDNODE overcomes a key limitation of existing models in its ability to make unbiased predictions from truncated data. We show that the generated metrics can be used to predict patients' overall survival (OS) with high accuracy.
  arXiv  Detail & Related papers  (2023-08-02T18:08:27Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• Translational Quantum Machine Intelligence for Modeling Tumor Dynamics in Oncology [18.069876260017605]
  Quantum Machine Intelligence offers unparalleled insights into tumor dynamics via a quantum mechanics perspective. We introduce a novel hybrid quantum-classical neural architecture named $eta-$Net that enables quantifying quantum dynamics of tumor burden concerning treatment effects.
  arXiv  Detail & Related papers  (2022-02-21T08:46:58Z)
• Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets [63.62764375279861]
  We propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions. Using a data set with 161 cases, we demonstrate that pre-trained EfficientNets with larger input resolutions lead to significant performance improvements.
  arXiv  Detail & Related papers  (2021-09-10T13:07:11Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.