DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis

TL;DR

This paper introduces DSNet, a dual-stream framework that effectively classifies gigapixel pathology images using only image-level labels by integrating local and regional information, outperforming existing methods.

Contribution

The novel dual-stream architecture combines local patch embeddings and regional thumbnails for weakly-supervised WSI classification, eliminating the need for detailed patch annotations.

Findings

Outperforms state-of-the-art weakly-supervised methods on large datasets

Effectively integrates multi-scale information for accurate classification

Reduces annotation costs by relying on image-level labels

Abstract

We present a novel weakly-supervised framework for classifying whole slide images (WSIs). WSIs, due to their gigapixel resolution, are commonly processed by patch-wise classification with patch-level labels. However, patch-level labels require precise annotations, which is expensive and usually unavailable on clinical data. With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label. To address this issue, we posit that WSI analysis can be effectively conducted by integrating information at both high magnification (local) and low magnification (regional) levels. We auto-encode the visual signals in each patch into a latent embedding vector representing local information, and down-sample the raw WSI to hardware-acceptable thumbnails representing regional information. The WSI label is then predicted with a Dual-Stream Network (DSNet), which takes the transformed local patch embeddings and multi-scale thumbnail images as inputs and can be trained by the image-level label only. Experiments conducted on two large-scale public datasets demonstrate that our method outperforms all recent state-of-the-art weakly-supervised WSI classification methods.