Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World

TL;DR

This paper introduces a deep learning system for classifying dermatopathology slides that achieves high accuracy and robustness across multiple labs and scanner types, aiming to improve skin cancer diagnosis efficiency.

Contribution

The study presents a validated, confidence-scored deep learning approach for whole slide image classification in dermatopathology, demonstrating real-world applicability and high accuracy.

Findings

Achieved up to 98% accuracy with confidence scoring

Validated on 13,537 images from 3 different labs and scanners

System improves diagnostic speed and reproducibility

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 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.