Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification

Yash Sharma, Aman Shrivastava, Lubaina Ehsan, Christopher A. Moskaluk, Sana Syed*, Donald E. Brown*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

80 Scopus citations

Abstract

In recent years, the availability of digitized Whole Slide Images (WSIs) has enabled the use of deep learning-based computer vision techniques for automated disease diagnosis. However, WSIs present unique computational and algorithmic challenges. WSIs are gigapixel-sized (∼100K pixels), making them infeasible to be used directly for training deep neural networks. Also, often only slide-level labels are available for training as detailed annotations are tedious and can be time-consuming for experts. Approaches using multiple-instance learning (MIL) frameworks have been shown to overcome these challenges. Current state-of-the-art approaches divide the learning framework into two decoupled parts: a convolutional neural network (CNN) for encoding the patches followed by an independent aggregation approach for slide-level prediction. In this approach, the aggregation step has no bearing on the representations learned by the CNN encoder. We have proposed an end-to-end framework that clusters the patches from a WSI into k-groups, samples k0 patches from each group for training, and uses an adaptive attention mechanism for slide level prediction; Cluster-to-Conquer (C2C). We have demonstrated that dividing a WSI into clusters can improve the model training by exposing it to diverse discriminative features extracted from the patches. We regularized the clustering mechanism by introducing a KL-divergence loss between the attention weights of patches in a cluster and the uniform distribution. The framework is optimized end-to-end on slide-level cross-entropy, patch-level cross-entropy, and KL-divergence loss (Implementation: https://github.com/YashSharma/C2C).

Original languageEnglish
Pages (from-to)682-698
Number of pages17
JournalProceedings of Machine Learning Research
Volume143
StatePublished - 2021
Externally publishedYes
Event4th Conference on Medical Imaging with Deep Learning, MIDL 2021 - Virtual, Online, Germany
Duration: 7 Jul 20219 Jul 2021

Keywords

  • Deep Learning
  • Histopathology
  • Multi-Instance Learning
  • Weak Supervision

Fingerprint

Dive into the research topics of 'Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification'. Together they form a unique fingerprint.

Cite this