Health AI Central
Share:
Peer-Reviewed Publication
PLoS One2018;13(5):e0196828.January 1, 2018Journal Article

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

Angel Cruz-Roa1,2, Hannah Gilmore3, Ajay Basavanhally4, Michael Feldman5, Shridar Ganesan6, Natalie Shih5, John Tomaszewski7, Anant Madabhushi8, Fabio González2
1School of Engineering, Universidad de los Llanos, Villavicencio, Meta, Colombia.
2Dept. of Computing Systems and Industrial Engineering, Universidad Nacional de Colombia, Bogotá, Cundinamarca, Colombia.
3University Hospitals Case Medical Center, Cleveland, OH, United States of America.
4Inspirata Inc., Tampa, FL, United States of America.
5Hospital of the University of Pennsylvania, Philadelphia, PA, United States of America.
6Cancer Institute of New Jersey, New Brunswick, NJ, United States of America.
7University at Buffalo, The State University of New York, Buffalo, NY, United States of America.
8Case Western Reserve University, Cleveland, OH, United States of America.
PubMed PMC DOI PDF

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…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.