SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification

2025-09-04

AI Summary

To address the challenges of modeling instance spatial relationships, high computational complexity in long-sequence dependency modeling, and inconsistent sequence lengths between training and inference in whole-slide image (WSI) classification, this paper proposes an efficient and scalable multiple-instance learning (MIL) framework. Our method explicitly encodes the intrinsic spatial layout of instances via learnable coordinate-based positional embeddings. Furthermore, we introduce an MLP-based Spatial Attention Correlation (SAC) module that captures global instance dependencies in linear time complexity—eliminating the need for custom CUDA kernels while ensuring both high performance and deployment efficiency. Evaluated on CAMELYON16, TCGA-LUNG, and TCGA-BRCA benchmarks, our approach achieves state-of-the-art classification accuracy, significantly outperforming existing MIL methods.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We propose Spatial-Aware Correlated Multiple Instance Learning (SAC-MIL) for performing WSI classification. SAC-MIL consists of a positional encoding module to encode position information and a SAC block to perform full instance correlations. The positional encoding module utilizes the instance coordinates within the slide to encode the spatial relationships instead of the instance index in the input WSI sequence. The positional encoding module can also handle the length extrapolation issue where the training and testing sequences have different lengths. The SAC block is an MLP-based method that performs full instance correlation in linear time complexity with respect to the sequence length. Due to the simple structure of MLP, it is easy to deploy since it does not require custom CUDA kernels, compared to Transformer-based methods for WSI classification. SAC-MIL has achieved state-of-the-art performance on the CAMELYON-16, TCGA-LUNG, and TCGA-BRAC datasets. The code will be released upon acceptance.

Problem

• Classifying histopathology whole slide images using spatial-aware multiple instance learning
• Handling variable sequence lengths between training and testing WSI data
• Performing full instance correlations with linear time complexity efficiently

Innovation

• Spatial encoding using instance coordinates instead of indices
• MLP-based correlation with linear time complexity
• Handles variable sequence lengths during testing