CrossFusion: A Multi-Scale Cross-Attention Convolutional Fusion Model for Cancer Survival Prediction

2025-03-03

AI Summary

To address the challenges of large-scale, irregularly shaped whole-slide images (WSIs) and difficulty in modeling multi-granularity histopathological patterns for cancer survival prediction, this paper proposes a multi-scale cross-attention convolutional fusion framework. The method employs multi-magnification patch sampling and introduces a cross-scale cross-attention mechanism to explicitly capture fine-grained interactions between cellular-level abnormalities and tissue-level architectural patterns. It further incorporates lightweight convolutional feature fusion and integrates WSI-level Cox regression for survival risk modeling. Evaluated on six public cancer datasets, the framework significantly outperforms existing state-of-the-art methods. Performance improves consistently when integrating pathology-specific backbone networks. The source code is publicly available.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Cancer survival prediction from whole slide images (WSIs) is a challenging task in computational pathology due to the large size, irregular shape, and high granularity of the WSIs. These characteristics make it difficult to capture the full spectrum of patterns, from subtle cellular abnormalities to complex tissue interactions, which are crucial for accurate prognosis. To address this, we propose CrossFusion, a novel multi-scale feature integration framework that extracts and fuses information from patches across different magnification levels. By effectively modeling both scale-specific patterns and their interactions, CrossFusion generates a rich feature set that enhances survival prediction accuracy. We validate our approach across six cancer types from public datasets, demonstrating significant improvements over existing state-of-the-art methods. Moreover, when coupled with domain-specific feature extraction backbones, our method shows further gains in prognostic performance compared to general-purpose backbones. The source code is available at: https://github.com/RustinS/CrossFusion

Problem

• Predict cancer survival from whole slide images
• Integrate multi-scale features for accurate prognosis
• Improve survival prediction across six cancer types

Innovation

• Multi-scale feature integration framework
• Cross-attention convolutional fusion model
• Domain-specific feature extraction backbones