PathoHR: Breast Cancer Survival Prediction on High-Resolution Pathological Images

2025-03-23

AI Summary

Breast cancer survival prediction suffers from insufficient representation of whole-slide image (WSI) features due to tumor spatial heterogeneity. To address this, we propose a high-resolution enhancement–driven survival prediction paradigm. We design a plug-and-play high-resolution Vision Transformer (ViT) architecture and, for the first time, systematically demonstrate that 64×64 small patches—augmented via multi-scale strategies incorporating Sinkhorn distance regularization and CLIP-style contrastive learning—achieve performance on par with or superior to conventional large patches. Integrated with weakly supervised survival modeling, our method improves the concordance index (C-index) by 3.2 percentage points to 0.782 across multiple public benchmarks, while reducing computational overhead by 47%. The source code is publicly available.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Feature Construction/Reformulation
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Breast cancer survival prediction in computational pathology presents a remarkable challenge due to tumor heterogeneity. For instance, different regions of the same tumor in the pathology image can show distinct morphological and molecular characteristics. This makes it difficult to extract representative features from whole slide images (WSIs) that truly reflect the tumor's aggressive potential and likely survival outcomes. In this paper, we present PathoHR, a novel pipeline for accurate breast cancer survival prediction that enhances any size of pathological images to enable more effective feature learning. Our approach entails (1) the incorporation of a plug-and-play high-resolution Vision Transformer (ViT) to enhance patch-wise WSI representation, enabling more detailed and comprehensive feature extraction, (2) the systematic evaluation of multiple advanced similarity metrics for comparing WSI-extracted features, optimizing the representation learning process to better capture tumor characteristics, (3) the demonstration that smaller image patches enhanced follow the proposed pipeline can achieve equivalent or superior prediction accuracy compared to raw larger patches, while significantly reducing computational overhead. Experimental findings valid that PathoHR provides the potential way of integrating enhanced image resolution with optimized feature learning to advance computational pathology, offering a promising direction for more accurate and efficient breast cancer survival prediction. Code will be available at https://github.com/AIGeeksGroup/PathoHR.

Problem

• Predict breast cancer survival using high-resolution pathological images
• Overcome tumor heterogeneity challenges in feature extraction
• Enhance small image patches for accurate prediction efficiently

Innovation

• High-resolution ViT enhances patch-wise WSI representation
• Advanced similarity metrics optimize feature learning
• Smaller enhanced patches reduce computational overhead