Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology

TL;DR

This paper introduces ranking loss and sequestering learning methods to improve image search accuracy and reduce institutional bias in histopathology, demonstrating superior results on a large public dataset.

Contribution

It proposes a novel ranking loss function and sequestering learning approach to enhance search relevance and generalization in histopathology image retrieval.

Findings

Ranking loss improves search relevance.

Sequestering learning reduces institutional bias.

Methods outperform state-of-the-art on large dataset.

Abstract

Recently, deep learning has started to play an essential role in healthcare applications, including image search in digital pathology. Despite the recent progress in computer vision, significant issues remain for image searching in histopathology archives. A well-known problem is AI bias and lack of generalization. A more particular shortcoming of deep models is the ignorance toward search functionality. The former affects every model, the latter only search and matching. Due to the lack of ranking-based learning, researchers must train models based on the classification error and then use the resultant embedding for image search purposes. Moreover, deep models appear to be prone to internal bias even if using a large image repository of various hospitals. This paper proposes two novel ideas to improve image search performance. First, we use a ranking loss function to guide feature extraction toward the matching-oriented nature of the search. By forcing the model to learn the ranking of matched outputs, the representation learning is customized toward image search instead of learning a class label. Second, we introduce the concept of sequestering learning to enhance the generalization of feature extraction. By excluding the images of the input hospital from the matched outputs, i.e., sequestering the input domain, the institutional bias is reduced. The proposed ideas are implemented and validated through the largest public dataset of whole slide images. The experiments demonstrate superior results compare to the-state-of-art.