Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach

Abstract

Analysis of histopathology slides is a critical step for many diagnoses, and in particular in oncology where it defines the gold standard. In the case of digital histopathological analysis, highly trained pathologists must review vast whole-slide-images of extreme digital resolution ($100,000^2$ pixels) across multiple zoom levels in order to locate abnormal regions of cells, or in some cases single cells, out of millions. The application of deep learning to this problem is hampered not only by small sample sizes, as typical datasets contain only a few hundred samples, but also by the generation of ground-truth localized annotations for training interpretable classification and segmentation models. We propose a method for disease localization in the context of weakly supervised learning, where only image-level labels are available during training. Even without pixel-level annotations, we are able to demonstrate performance comparable with models trained with strong annotations on the Camelyon-16 lymph node metastases detection challenge. We accomplish this through the use of pre-trained deep convolutional networks, feature embedding, as well as learning via top instances and negative evidence, a multiple instance learning technique from the field of semantic segmentation and object detection.

References in corpus (2)

• A Survey on Deep Learning in Medical Image Analysis
• Deep Learning for Identifying Metastatic Breast Cancer

Cited by in corpus (16)

• Deep Learning for Whole Slide Image Analysis: An Overview
• RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification
• Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
• Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
• WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images
• Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Gigapixel Histopathological Image Analysis using Attention-based Neural Networks
• Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
• Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
• Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers
• A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
• Federated Survival Analysis with Discrete-Time Cox Models
• Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations
• Efficient Classification of Very Large Images with Tiny Objects
• Weakly supervised training of pixel resolution segmentation models on whole slide images