Dataset Information

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

ABSTRACT: 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%.

SUBMITTER: Cruz-Roa A

PROVIDER: S-EPMC5967747 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Cruz-Roa Angel A Gilmore Hannah H Basavanhally Ajay A Feldman Michael M Ganesan Shridar S Shih Natalie N Tomaszewski John J Madabhushi Anant A González Fabio F

PloS one 20180524 5

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) a ...[more]

PMID: 29795581

Similar Datasets

Project description:Background Image-based machine learning tools hold great promise for clinical applications in pathology research. However, the ideal end-users of these computational tools (e.g., pathologists and biological scientists) often lack the programming experience required for the setup and use of these tools which often rely on the use of command line interfaces. Methods We have developed Histo-Cloud, a tool for segmentation of whole slide images (WSIs) that has an easy-to-use graphical user interface. This tool runs a state-of-the-art convolutional neural network (CNN) for segmentation of WSIs in the cloud and allows the extraction of features from segmented regions for further analysis. Results By segmenting glomeruli, interstitial fibrosis and tubular atrophy, and vascular structures from renal and non-renal WSIs, we demonstrate the scalability, best practices for transfer learning, and effects of dataset variability. Finally, we demonstrate an application for animal model research, analyzing glomerular features in three murine models. Conclusions Histo-Cloud is open source, accessible over the internet, and adaptable for segmentation of any histological structure regardless of stain. Plain language summary Artificial intelligence (AI) is the ability of a computer to conduct complex tasks that humans are capable of performing. AI is useful in the field of pathology, which involves analyzing images of the microscopic structure of different tissues. However, AI can be difficult to set up and apply to the task. One specific task, segmentation, involves picking specific structures out of tissue images and is a prime candidate for automation with AI. In our study, we have created a tool for pathology image segmentation which runs in the cloud (is accessible over the web). We demonstrate the tool by using it to segment various structures from kidney tissue. Our experiments show that the tool is easy to use, accurate, and can estimate the presence of one type of scarring as reliably as human experts. Lutnick et al. develop a cloud-based deep learning tool for whole slide image segmentation. The authors provide several examples of its application in renal pathology, for segmenting glomeruli, interstitial fibrosis and other features of interest.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets