Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification

TL;DR

This paper introduces HC-FT, a clustering-based feature fine-tuning method for WSI classification that improves MIL performance by purifying positive and negative samples, leading to higher accuracy on medical datasets.

Contribution

The paper proposes a novel heuristic clustering-driven fine-tuning approach to enhance MIL in WSI classification by effectively selecting purified training samples.

Findings

Achieved 97.13% AUC on CAMELYON16 dataset.

Achieved 85.85% AUC on BRACS dataset.

Outperformed existing methods consistently.

Abstract

In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning by providing purified positive and hard negative samples. Our method first employs a well-trained MIL model to evaluate the confidence of patches. Then, patches with high confidence are marked as positive samples, while the remaining patches are used to identify crucial negative samples. After two rounds of heuristic clustering and selection, purified positive and hard negative samples are obtained to facilitate feature fine-tuning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively, consistently outperforming all compared methods.