Neural Image Compression for Gigapixel Histopathology Image Analysis

Abstract

We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in an unsupervised fashion, retaining high-level information while suppressing pixel-level noise. Second, a convolutional neural network (CNN) is trained on these compressed image representations to predict image-level labels, avoiding the need for fine-grained manual annotations. We compared several encoding strategies, namely reconstruction error minimization, contrastive training and adversarial feature learning, and evaluated NIC on a synthetic task and two public histopathology datasets. We found that NIC can exploit visual cues associated with image-level labels successfully, integrating both global and local visual information. Furthermore, we visualized the regions of the input gigapixel images where the CNN attended to, and confirmed that they overlapped with annotations from human experts.

arXiv commentAccepted in the IEEE Transactions on Pattern Analysis and Machine Intelligence journal

References in corpus (12)

• A Survey on Deep Learning in Medical Image Analysis
• Auto-Encoding Variational Bayes
• Representation Learning with Contrastive Predictive Coding
• Neural Discrete Representation Learning
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Attention-based Deep Multiple Instance Learning
• Adversarially Learned Inference
• Training Deep Nets with Sublinear Memory Cost
• Deep Clustering for Unsupervised Learning of Visual Features
• Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge
• Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks
• Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA

Cited by in corpus (20)

• Deep neural network models for computational histopathology: A survey
• Deep Learning for Whole Slide Image Analysis: An Overview
• Artificial Intelligence for Digital and Computational Pathology
• DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer
• Self-supervised driven consistency training for annotation efficient histopathology image analysis
• Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
• Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
• Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification
• Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
• Gigapixel Histopathological Image Analysis using Attention-based Neural Networks
• Evaluating Generic Auto-ML Tools for Computational Pathology
• Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
• Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis
• HistoCartography: A Toolkit for Graph Analytics in Digital Pathology
• Unlocking the Potential of Digital Pathology: Novel Baselines for Compression
• Tissue Concepts: supervised foundation models in computational pathology
• Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
• Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
• The State of Applying Artificial Intelligence to Tissue Imaging for Cancer Research and Early Detection
• Efficient Classification of Very Large Images with Tiny Objects