Constrained Deep Weak Supervision for Histopathology Image Segmentation

Abstract

In this paper, we develop a new weakly-supervised learning algorithm to learn to segment cancerous regions in histopathology images. Our work is under a multiple instance learning framework (MIL) with a new formulation, deep weak supervision (DWS); we also propose an effective way to introduce constraints to our neural networks to assist the learning process. The contributions of our algorithm are threefold: (1) We build an end-to-end learning system that segments cancerous regions with fully convolutional networks (FCN) in which image-to-image weakly-supervised learning is performed. (2) We develop a deep week supervision formulation to exploit multi-scale learning under weak supervision within fully convolutional networks. (3) Constraints about positive instances are introduced in our approach to effectively explore additional weakly-supervised information that is easy to obtain and enjoys a significant boost to the learning process. The proposed algorithm, abbreviated as DWS-MIL, is easy to implement and can be trained efficiently. Our system demonstrates state-of-the-art results on large-scale histopathology image datasets and can be applied to various applications in medical imaging beyond histopathology images such as MRI, CT, and ultrasound images.

References in corpus (1)

• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

Cited by in corpus (22)

• Machine learning methods for histopathological image analysis
• Deep neural network models for computational histopathology: A survey
• Constrained-CNN losses for weakly supervised segmentation
• Multiple instance dense connected convolution neural network for aerial image scene classification
• Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos
• Automated Classification of Histopathology Images Using Transfer Learning
• Recent Progress in Transformer-based Medical Image Analysis
• A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
• NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery
• WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images
• 3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
• Constrained domain adaptation for Image segmentation
• Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning
• Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity
• Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound
• OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation
• Hierarchical learning, forecasting coherent spatio-temporal individual and aggregated building loads
• HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
• CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio
• Constrained unsupervised anomaly segmentation
• Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation