Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading
Lipei Zhang (University of Cambridge), Yiran Wei (University of Cambridge), Ying Fu (Beijing Institute of Technology), Stephen J. Price (University of Cambridge), Carola-Bibiane B Schönlieb (Cambridge University), Chao Li (University of Cambridge)*
The 33rd British Machine Vision Conference
Abstract
Whole slide images (WSI) provide valuable phenotypic information for histological assessment and malignancy grading of tumors. The WSI-based grading promises to provide rapid diagnostic support and facilitate digital health. Currently, the most commonly used WSIs are derived from formalin-fixed paraffin-embedded (FFPE) and Frozen section. The majority of automatic tumor grading models are developed based on FFPE sections, which could be affected by the artifacts introduced from tissue processing. The frozen section exists problems such as low quality that might influence training within single modality as well. To overcome these problems in the single modal training and achieve better multi-modal and discriminative representation disentanglement in brain tumor, we propose a mutual contrastive low-rank learning (MCL) scheme to integrate FFPE and frozen sections for glioma grading. We first design a mutual learning scheme to jointly optimize the model training based on FFPE and frozen sections. In this proposed scheme, we design a normalized modality contrastive loss (NMC-loss), which could promote to disentangle multi-modality complementary representation of FFPE and frozen sections from the same patient. To reduce intra-class variance, and increase inter-class margin at intra- and inter-patient levels, we conduct a low-rank (LR) loss. Our experiments show that the proposed scheme achieves better performance than the model trained based on each single modality or mixed modalities without reducing the efficiency of inference, and even improves the feature extraction in classical attention-based multiple instances learning methods (MIL). The combination of NMC-loss and low-rank loss outperforms other typical contrastive loss functions. The source code is in https://github.com/uceclz0/MCL_glioma_grading.Video
Citation
@inproceedings{Zhang_2022_BMVC,
author = {Lipei Zhang and Yiran Wei and Ying Fu and Stephen J. Price and Carola-Bibiane B Schönlieb and Chao Li},
title = {Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/1071.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by