Domain-adversarial neural networks to address the appearance variability of histopathology images

Abstract

Preparing and scanning histopathology slides consists of several steps, each with a multitude of parameters. The parameters can vary between pathology labs and within the same lab over time, resulting in significant variability of the tissue appearance that hampers the generalization of automatic image analysis methods. Typically, this is addressed with ad-hoc approaches such as staining normalization that aim to reduce the appearance variability. In this paper, we propose a systematic solution based on domain-adversarial neural networks. We hypothesize that removing the domain information from the model representation leads to better generalization. We tested our hypothesis for the problem of mitosis detection in breast cancer histopathology images and made a comparative analysis with two other approaches. We show that combining color augmentation with domain-adversarial training is a better alternative than standard approaches to improve the generalization of deep learning methods.

MICCAI 2017 Workshop on Deep Learning in Medical Image Analysis

References in corpus (1)

• Assessment of algorithms for mitosis detection in breast cancer histopathology images

Cited by in corpus (29)

• Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
• A Survey on Deep Learning for Skin Lesion Segmentation
• A survey, review, and future trends of skin lesion segmentation and classification
• Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques
• MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation
• Deep learning for reconstructing protein structures from cryo-EM density maps: recent advances and future directions
• Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images
• Free-form tumor synthesis in computed tomography images via richer generative adversarial network
• Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
• Application of belief functions to medical image segmentation: A review
• Deep Learning Models for River Classification at Sub-Meter Resolutions from Multispectral and Panchromatic Commercial Satellite Imagery
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
• Deep Active Learning for Computer Vision: Past and Future
• Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net
• Evaluating Generic Auto-ML Tools for Computational Pathology
• Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty
• Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds
• Dynamic Background Reconstruction via MAE for Infrared Small Target Detection
• CartiMorph: a framework for automated knee articular cartilage morphometrics
• Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
• Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes
• Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?
• Multiclass Semantic Segmentation to Identify Anatomical Sub-Regions of Brain and Measure Neuronal Health in Parkinson's Disease
• MAGIC: Microlensing Analysis Guided by Intelligent Computation
• Financial Table Extraction in Image Documents
• UNGT: Ultrasound Nasogastric Tube Dataset for Medical Image Analysis
• Immunofluorescence Capillary Imaging Segmentation: Cases Study
• Analysis of the Compaction Behavior of Textile Reinforcements in Low-Resolution In-Situ CT Scans via Machine-Learning and Descriptor-Based Methods