Region of Interest Detection in Melanocytic Skin Tumor Whole Slide Images -- Nevus & Melanoma

TL;DR

This paper presents a deep-learning approach for detecting regions of interest in histopathological images of melanocytic skin tumors, achieving high accuracy in classifying nevi and melanomas, with potential for broader medical applications.

Contribution

The study introduces a novel deep-learning method for slide-level classification and ROI detection in melanocytic skin tumor images, demonstrating high accuracy and potential clinical utility.

Findings

Slide classification accuracy of 92.3%

Effective ROI prediction aligned with pathologists' annotations

Potential extension to other medical image detection tasks

Abstract

Automated region of interest detection in histopathological image analysis is a challenging and important topic with tremendous potential impact on clinical practice. The deep-learning methods used in computational pathology may help us to reduce costs and increase the speed and accuracy of cancer diagnosis. We started with the UNC Melanocytic Tumor Dataset cohort that contains 160 hematoxylin and eosin whole-slide images of primary melanomas (86) and nevi (74). We randomly assigned 80% (134) as a training set and built an in-house deep-learning method to allow for classification, at the slide level, of nevi and melanomas. The proposed method performed well on the other 20% (26) test dataset; the accuracy of the slide classification task was 92.3% and our model also performed well in terms of predicting the region of interest annotated by the pathologists, showing excellent performance of our model on melanocytic skin tumors. Even though we tested the experiments on the skin tumor dataset, our work could also be extended to other medical image detection problems to benefit the clinical evaluation and diagnosis of different tumors.