A new machine learning approach detects esophageal cancer better than current methods

(Dartmouth-Hitchcock Medical Center) Dartmouth scientists have proposed a new machine learning model for identification of esophageal cancer that could open new avenues for applying deep learning to digital pathology. The novel method automatically learns clinically important regions on whole-slide images for classification. The approach outperformed the current state-of-the-art model that requires detailed, manual annotations by a pathologist for its training. Such systems could assist pathologists in reading slides more accurately and efficiently while eliminating laborious, high-cost data annotation.
Source: EurekAlert! - Cancer - Category: Cancer & Oncology Source Type: news