Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload

Autor: Sivaramakrishnan Sankarapandian, Kiran Motaparthi, Michael J. Bonham, Thomas G. Olsen, Coleman C. Stavish, Julianna D. Ianni, Ramachandra Vikas Chamarthi, Theresa A. Feeser, Rajath E. Soans, Jason B. Lee, Clay J. Cockerell, Devi Ayyagari
Rok vydání: 2020
Předmět:
0301 basic medicine
Pathology
medicine.medical_specialty
Skin Neoplasms
Standard of care
Classification and taxonomy
Computer science
lcsh:Medicine
Workload
Article
Pattern Recognition
Automated
03 medical and health sciences
Deep Learning
0302 clinical medicine
Suspected skin cancer
Image Interpretation
Computer-Assisted
Machine learning
Image Processing
Computer-Assisted
medicine
Humans
Computational models
Computer Simulation
Prospective Studies
lcsh:Science
Cell Proliferation
Multidisciplinary
business.industry
Deep learning
lcsh:R
Multi site
Reproducibility of Results
Identification (information)
030104 developmental biology
ROC Curve
030220 oncology & carcinogenesis
Calibration
Whole slide image
Melanocytes
lcsh:Q
Neural Networks
Computer
Dermatopathology
Artificial intelligence
business
Algorithms
Zdroj: Scientific Reports, Vol 10, Iss 1, Pp 1-12 (2020)
Scientific Reports
ISSN: 2045-2322
DOI: 10.1038/s41598-020-59985-2
Popis: 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 system is developed using 5,070 images from a single lab, and tested on an uncurated set of 13,537 images from 3 test labs, using whole slide scanners manufactured by 3 different vendors. The system’s use of deep-learning-based confidence scoring as a criterion to consider the result as accurate yields an accuracy of up to 98%, and makes it adoptable in a real-world setting. Without confidence scoring, the system achieved an accuracy of 78%. We anticipate that our deep learning system will serve as a foundation enabling faster diagnosis of skin cancer, identification of cases for specialist review, and targeted diagnostic classifications.
Databáze: OpenAIRE
Externí odkaz: