Unsupervised Histopathology Image Synthesis

Abstract

Hematoxylin and Eosin stained histopathology image analysis is essential for the diagnosis and study of complicated diseases such as cancer. Existing state-of-the-art approaches demand extensive amount of supervised training data from trained pathologists. In this work we synthesize in an unsupervised manner, large histopathology image datasets, suitable for supervised training tasks. We propose a unified pipeline that: a) generates a set of initial synthetic histopathology images with paired information about the nuclei such as segmentation masks; b) refines the initial synthetic images through a Generative Adversarial Network (GAN) to reference styles; c) trains a task-specific CNN and boosts the performance of the task-specific CNN with on-the-fly generated adversarial examples. Our main contribution is that the synthetic images are not only realistic, but also representative (in reference styles) and relatively challenging for training task-specific CNNs. We test our method for nucleus segmentation using images from four cancer types. When no supervised data exists for a cancer type, our method without supervision cost significantly outperforms supervised methods which perform across-cancer generalization. Even when supervised data exists for all cancer types, our approach without supervision cost performs better than supervised methods.

References in corpus (9)

• Explaining and Harnessing Adversarial Examples
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• Smart Augmentation - Learning an Optimal Data Augmentation Strategy
• Triple Generative Adversarial Nets
• Playing for Data: Ground Truth from Computer Games
• Towards Adversarial Retinal Image Synthesis
• Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation

Cited by in corpus (12)

• Generative Adversarial Network in Medical Imaging: A Review
• Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
• Deep Synthetic Minority Over-Sampling Technique
• Conditional Infilling GANs for Data Augmentation in Mammogram Classification
• Deep Learning architectures for generalized immunofluorescence based nuclear image segmentation
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology
• Chest X-ray Inpainting with Deep Generative Models
• Latent Space Optimal Transport for Generative Models
• Ensembling with Deep Generative Views
• Unified cross-modality feature disentangler for unsupervised multi-domain MRI abdomen organs segmentation
• Towards Stable Imbalanced Data Classification via Virtual Big Data Projection
• Synthetic Generation of Three-Dimensional Cancer Cell Models from Histopathological Images