Lifelong Histopathology Whole Slide Image Retrieval via Distance Consistency Rehearsal

TL;DR

This paper introduces a lifelong histopathology image retrieval framework that effectively manages continuously expanding databases by balancing stability and plasticity, using memory banks and a distance consistency rehearsal module.

Contribution

It proposes a novel lifelong learning approach for whole slide image retrieval that addresses catastrophic forgetting with a distance consistency rehearsal module and local memory bank.

Findings

Outperforms state-of-the-art methods on four public datasets.

Effectively balances stability and plasticity in lifelong learning.

Demonstrates robustness in continuously growing WSI databases.

Abstract

Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical practice, the continuously expanding size of WSI databases limits the practical application of the current CBHIR methods. In this paper, we propose a Lifelong Whole Slide Retrieval (LWSR) framework to address the challenges of catastrophic forgetting by progressive model updating on continuously growing retrieval database. Our framework aims to achieve the balance between stability and plasticity during continuous learning. To preserve system plasticity, we utilize local memory bank with reservoir sampling method to save instances, which can comprehensively encompass the feature spaces of both old and new tasks. Furthermore, A distance consistency rehearsal (DCR) module is designed to ensure the retrieval queue's consistency for previous tasks, which is regarded as stability within a lifelong CBHIR system. We evaluated the proposed method on four public WSI datasets from TCGA projects. The experimental results have demonstrated the proposed method is effective and is superior to the state-of-the-art methods.