Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images

TL;DR

This paper introduces a novel graph autoencoder model that leverages foundation model features for breast histopathology image retrieval, significantly improving accuracy over traditional CNN-based methods.

Contribution

It proposes a new attention-based adversarially regularized variational graph autoencoder utilizing foundation model features for improved image retrieval in histopathology.

Findings

Models with foundation model features outperform CNN-based models in mAP and mMV.

UNI features yield the best overall performance among tested foundation models.

Achieved up to 97.6% mAP on BACH dataset, demonstrating high retrieval accuracy.

Abstract

Breast cancer is the most common cancer type in women worldwide. Early detection and appropriate treatment can significantly reduce its impact. While histopathology examinations play a vital role in rapid and accurate diagnosis, they often require experienced medical experts for proper recognition and cancer grading. Automated image retrieval systems have the potential to assist pathologists in identifying cancerous tissues, thereby accelerating the diagnostic process. Nevertheless, proposing an accurate image retrieval model is challenging due to considerable variability among the tissue and cell patterns in histological images. In this work, we leverage the features from foundation models in a novel attention-based adversarially regularized variational graph autoencoder model for breast histological image retrieval. Our results confirm the superior performance of models trained with foundation model features compared to those using pre-trained convolutional neural networks (up to 7.7% and 15.5% for mAP and mMV, respectively), with the pre-trained general-purpose self-supervised model for computational pathology (UNI) delivering the best overall performance. By evaluating two publicly available histology image datasets of breast cancer, our top-performing model, trained with UNI features, achieved average mAP/mMV scores of 96.7%/91.5% and 97.6%/94.2% for the BreakHis and BACH datasets, respectively. Our proposed retrieval model has the potential to be used in clinical settings to enhance diagnostic performance and ultimately benefit patients.