Peer-Reviewed Publication
Sci Rep2020;10(1):3217.February 21, 2020Journal Article
Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload.
Julianna D Ianni1, Rajath E Soans2, Sivaramakrishnan Sankarapandian3, Ramachandra Vikas Chamarthi3, Devi Ayyagari3, Thomas G Olsen4,5, Michael J Bonham3, Coleman C Stavish3, Kiran Motaparthi6, Clay J Cockerell7, Theresa A Feeser3, Jason B Lee8
1Proscia Inc., Philadelphia, Pennsylvania, USA. julianna@proscia.com.
2Proscia Inc., Philadelphia, Pennsylvania, USA. rajath@proscia.com.
3Proscia Inc., Philadelphia, Pennsylvania, USA.
4Department of Dermatology, Boonshoft School of Medicine, Wright State University School of Medicine, Dayton, Ohio, USA.
5Dermatopathology Laboratory of Central States, Dayton, Ohio, USA.
6Department of Dermatology, University of Florida College of Medicine, Gainesville, Florida, USA.
7Cockerell Dermatopathology, Dallas, Texas, USA.
8Departments of Dermatology and Cutaneous Biology, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, Pennsylvania, USA.
Abstract
Standard of care diagnostic procedure for suspected skin cancer is microscopic examination of hematoxylin & eosin stained tissue by a pathologist. Areas of high inter-pathologist discordance and rising biopsy rates necessitate higher efficiency and diagnostic reproducibility. We present and validate a deep learning system which classifies digitized dermatopathology slides into 4 categories. The sy…
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.
Want unlimited research access? See Pro plans