High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection

Autor: Michael Feldman, Natalie Shih, John E. Tomaszewski, Angel Cruz-Roa, Fabio A. González, Hannah Gilmore, Shridar Ganesan, Anant Madabhushi, Ajay Basavanhally
Rok vydání: 2018
Předmět:
0301 basic medicine
Computer science
Social Sciences
Pathology and Laboratory Medicine
Convolutional neural network
Learning and Memory
Animal Cells
Breast Tumors
Medicine and Health Sciences
Image Processing
Computer-Assisted
Psychology
Segmentation
Neurons
Multidisciplinary
Artificial neural network
Invasive Tumors
Oncology
Medicine
Female
Cellular Types
Research Article
Computer and Information Sciences
Adaptive sampling
Neural Networks
Imaging Techniques
Science
Histopathology
Breast Neoplasms
Image processing
Image Analysis
Research and Analysis Methods
03 medical and health sciences
Breast cancer
Breast Cancer
medicine
Learning
Humans
Pixel
business.industry
Cognitive Psychology
Cancers and Neoplasms
Biology and Life Sciences
Digital pathology
Pattern recognition
Cell Biology
medicine.disease
030104 developmental biology
Anatomical Pathology
Cellular Neuroscience
Cognitive Science
Neural Networks
Computer
Artificial intelligence
business
Feature learning
Neuroscience
Zdroj: PLoS ONE
PLoS ONE, Vol 13, Iss 5, p e0196828 (2018)
ISSN: 1932-6203
Popis: Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.
Databáze: OpenAIRE
Externí odkaz: