Scalable Whole Slide Image Representation Using K-Mean Clustering and Fisher Vector Aggregation

TL;DR

This paper introduces a scalable WSI classification method that combines patch-based deep features, K-means clustering, and Fisher vector encoding to efficiently handle gigapixel images with high accuracy.

Contribution

The paper proposes a novel scalable approach for WSI classification using clustering and Fisher vectors, improving efficiency and accuracy over existing methods.

Findings

Achieves superior accuracy compared to baseline methods.

Demonstrates high scalability for large gigapixel images.

Provides robust tissue structure representation.

Abstract

Whole slide images (WSIs) are high-resolution, gigapixel sized images that pose significant computational challenges for traditional machine learning models due to their size and heterogeneity.In this paper, we present a scalable and efficient methodology for WSI classification by leveraging patch-based feature extraction, clustering, and Fisher vector encoding. Initially, WSIs are divided into fixed size patches, and deep feature embeddings are extracted from each patch using a pre-trained convolutional neural network (CNN). These patch-level embeddings are subsequently clustered using K-means clustering, where each cluster aggregates semantically similar regions of the WSI. To effectively summarize each cluster, Fisher vector representations are computed by modeling the distribution of patch embeddings in each cluster as a parametric Gaussian mixture model (GMM). The Fisher vectors from each cluster are concatenated into a high-dimensional feature vector, creating a compact and informative representation of the entire WSI. This feature vector is then used by a classifier to predict the WSI's diagnostic label. Our method captures local and global tissue structures and yields robust performance for large-scale WSI classification, demonstrating superior accuracy and scalability compared to other approaches.