Standardizing Medical Images at Scale for AI

2026-03-16

AI Summary

This work addresses the significant domain shift in medical images caused by variations in imaging devices and staining protocols, which severely limits the cross-institutional generalization of AI models. The authors propose PhyCV, a preprocessing framework grounded in optical physics that models images as optical fields. By employing differentiable, parameterized virtual diffraction propagation and coherent phase detection, PhyCV suppresses non-semantic variations—such as color and illumination—while preserving diagnostically critical structures. Notably, this is the first approach to leverage deterministic, physics-driven transformations for medical image standardization, eliminating the need for data augmentation or complex domain generalization techniques. Evaluated on Camelyon17-WILDS, PhyCV improves out-of-distribution accuracy in breast cancer classification from 70.8% to 90.9%, matching or surpassing state-of-the-art methods with minimal computational overhead.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep learning has achieved remarkable success in medical image analysis, yet its performance remains highly sensitive to the heterogeneity of clinical data. Differences in imaging hardware, staining protocols, and acquisition conditions produce substantial domain shifts that degrade model generalization across institutions. Here we present a physics-based data preprocessing framework based on the PhyCV (Physics-Inspired Computer Vision) family of algorithms, which standardizes medical images through deterministic transformations derived from optical physics. The framework models images as spatially varying optical fields that undergo a virtual diffractive propagation followed by coherent phase detection. This process suppresses non-semantic variability such as color and illumination differences while preserving diagnostically relevant texture and structural features. When applied to histopathological images from the Camelyon17-WILDS benchmark, PhyCV preprocessing improves out-of-distribution breast-cancer classification accuracy from 70.8% (Empirical Risk Minimization baseline) to 90.9%, matching or exceeding data-augmentation and domain-generalization approaches at negligible computational cost. Because the transform is physically interpretable, parameterizable, and differentiable, it can be deployed as a fixed preprocessing stage or integrated into end-to-end learning. These results establish PhyCV as a generalizable data refinery for medical imaging-one that harmonizes heterogeneous datasets through first-principles physics, improving robustness, interpretability, and reproducibility in clinical AI systems.

Problem

• medical image heterogeneity
• domain shift
• model generalization
• clinical AI robustness
• image standardization

Innovation

• PhyCV
• physics-based preprocessing
• medical image standardization
• domain generalization
• differentiable optics