Snuffy: Efficient Whole Slide Image Classifier

📅 2024-08-15
🏛️ European Conference on Computer Vision
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Digital pathology whole-slide image (WSI) classification under the multiple-instance learning (MIL) paradigm faces key bottlenecks: high computational overhead, reliance on large-scale self-supervised learning (SSL) pretraining, and degraded cross-domain transfer performance. This paper proposes a lightweight MIL framework that eliminates redundant SSL pretraining and enables continual few-shot adaptation. Its core innovation is a pathology-specific sparse Transformer pooling mechanism: we theoretically prove it to be a universal approximator and derive the tightest known probabilistic upper bound on its required depth. This mechanism drastically reduces computational complexity while achieving state-of-the-art accuracy at both WSI- and patch-level on CAMELYON16 and TCGA lung cancer datasets. Notably, training costs are substantially reduced compared to prevailing methods.

Technology Category

Application Category

📝 Abstract
Whole Slide Image (WSI) classification with multiple instance learning (MIL) in digital pathology faces significant computational challenges. Current methods mostly rely on extensive self-supervised learning (SSL) for satisfactory performance, requiring long training periods and considerable computational resources. At the same time, no pre-training affects performance due to domain shifts from natural images to WSIs. We introduce Snuffy architecture, a novel MIL-pooling method based on sparse transformers that mitigates performance loss with limited pre-training and enables continual few-shot pre-training as a competitive option. Our sparsity pattern is tailored for pathology and is theoretically proven to be a universal approximator with the tightest probabilistic sharp bound on the number of layers for sparse transformers, to date. We demonstrate Snuffy's effectiveness on CAMELYON16 and TCGA Lung cancer datasets, achieving superior WSI and patch-level accuracies. The code is available on https://github.com/jafarinia/snuffy.
Problem

Research questions and friction points this paper is trying to address.

Addresses computational challenges in WSI classification using MIL.
Reduces reliance on extensive self-supervised learning for performance.
Introduces Snuffy, a sparse transformer-based MIL-pooling method.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Sparse transformers for MIL-pooling
Tailored sparsity for pathology images
Continual few-shot pre-training capability
🔎 Similar Papers
No similar papers found.
H
Hossein Jafarinia
Sharif University of Technology, Tehran, Iran
A
Alireza Alipanah
Sharif University of Technology, Tehran, Iran
D
Danial Hamdi
Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
S
Saeed Razavi
Sharif University of Technology, Tehran, Iran
N
Nahal Mirzaie
Sharif University of Technology, Tehran, Iran
M
M. H. Rohban
Sharif University of Technology, Tehran, Iran