Resource-Frugal Classification and Analysis of Pathology Slides Using Image Entropy
This work addresses the need for efficient and interpretable pathology slide analysis for clinicians, though it is incremental as it builds on existing CNN techniques with a focus on resource constraints.
The paper tackles the problem of classifying lung cancer subtypes from pathology slides using a resource-frugal CNN method, achieving accuracies comparable to more complex models while enabling deployment on mobile devices and providing visual probability maps for clinician assessment.
Pathology slides of lung malignancies are classified using resource-frugal convolution neural networks (CNNs) that may be deployed on mobile devices. In particular, the challenging task of distinguishing adenocarcinoma (LUAD) and squamous-cell carcinoma (LUSC) lung cancer subtypes is approached in two stages. First, whole-slide histopathology images are downsampled to a size too large for CNN analysis but large enough to retain key anatomic detail. The downsampled images are decomposed into smaller square tiles, which are sifted based on their image entropies. A lightweight CNN produces tile-level classifications that are aggregated to classify the slide. The resulting accuracies are comparable to those obtained with much more complex CNNs and larger training sets. To allow clinicians to visually assess the basis for the classification -- that is, to see the image regions that underlie it -- color-coded probability maps are created by overlapping tiles and averaging the tile-level probabilities at a pixel level.