RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification

Abstract

The whole slide histopathology images (WSIs) play a critical role in gastric cancer diagnosis. However, due to the large scale of WSIs and various sizes of the abnormal area, how to select informative regions and analyze them are quite challenging during the automatic diagnosis process. The multi-instance learning based on the most discriminative instances can be of great benefit for whole slide gastric image diagnosis. In this paper, we design a recalibrated multi-instance deep learning method (RMDL) to address this challenging problem. We first select the discriminative instances, and then utilize these instances to diagnose diseases based on the proposed RMDL approach. The designed RMDL network is capable of capturing instance-wise dependencies and recalibrating instance features according to the importance coefficient learned from the fused features. Furthermore, we build a large whole-slide gastric histopathology image dataset with detailed pixel-level annotations. Experimental results on the constructed gastric dataset demonstrate the significant improvement on the accuracy of our proposed framework compared with other state-of-the-art multi-instance learning methods. Moreover, our method is general and can be extended to other diagnosis tasks of different cancer types based on WSIs.

Accepted at Medical Image Analysis. Code: https://github.com/EmmaW8/RMDL

References in corpus (4)

• Distilling the Knowledge in a Neural Network
• A Structured Self-attentive Sentence Embedding
• Recurrent Models of Visual Attention
• Assessment of algorithms for mitosis detection in breast cancer histopathology images

Cited by in corpus (13)

• Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks
• Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy
• GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection
• Deep Learning for Computational Cytology: A Survey
• Gastric histopathology image segmentation using a hierarchical conditional random field
• An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification
• Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
• Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
• A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning
• A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
• GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric Cancer
• Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning
• Kernel Self-Attention in Deep Multiple Instance Learning