DSAGL: Dual-Stream Attention-Guided Learning for Weakly Supervised Whole Slide Image Classification

TL;DR

This paper introduces DSAGL, a novel weakly supervised learning framework for whole-slide image classification that leverages dual-stream attention mechanisms and pseudo labels to improve accuracy and robustness in cancer diagnosis.

Contribution

The paper presents a dual-stream attention-guided learning framework with a lightweight encoder and fusion module, addressing instance ambiguity and semantic consistency in weakly supervised WSI classification.

Findings

Outperforms state-of-the-art MIL methods on multiple datasets.

Achieves higher discriminative accuracy and robustness.

Effectively models long-range dependencies and focuses on relevant regions.

Abstract

Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substantial challenges for conventional supervised learning. We propose DSAGL (Dual-Stream Attention-Guided Learning), a novel weakly supervised classification framework that combines a teacher-student architecture with a dual-stream design. DSAGL explicitly addresses instance-level ambiguity and bag-level semantic consistency by generating multi-scale attention-based pseudo labels and guiding instance-level learning. A shared lightweight encoder (VSSMamba) enables efficient long-range dependency modeling, while a fusion-attentive module (FASA) enhances focus on sparse but diagnostically relevant regions. We further introduce a hybrid loss to enforce mutual consistency between the two streams. Experiments on CIFAR-10, NCT-CRC, and TCGA-Lung datasets demonstrate that DSAGL consistently outperforms state-of-the-art MIL baselines, achieving superior discriminative performance and robustness under weak supervision.