Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images

TL;DR

This paper presents an ensemble deep learning system for melanoma detection in dermoscopy images, achieving state-of-the-art accuracy and specificity, potentially aiding early diagnosis and reducing unnecessary biopsies.

Contribution

The study introduces a novel ensemble approach combining deep learning and traditional methods for improved melanoma recognition in dermoscopy images.

Findings

Achieved 7.5% improvement in AUC (0.843 vs. 0.783)

Increased specificity at 95% sensitivity to 36.8%

Outperformed expert dermatologists in accuracy and specificity on test images

Abstract

Melanoma is the deadliest form of skin cancer. While curable with early detection, only highly trained specialists are capable of accurately recognizing the disease. As expertise is in limited supply, automated systems capable of identifying disease could save lives, reduce unnecessary biopsies, and reduce costs. Toward this goal, we propose a system that combines recent developments in deep learning with established machine learning approaches, creating ensembles of methods that are capable of segmenting skin lesions, as well as analyzing the detected area and surrounding tissue for melanoma detection. The system is evaluated using the largest publicly available benchmark dataset of dermoscopic images, containing 900 training and 379 testing images. New state-of-the-art performance levels are demonstrated, leading to an improvement in the area under receiver operating characteristic curve of 7.5% (0.843 vs. 0.783), in average precision of 4% (0.649 vs. 0.624), and in specificity measured at the clinically relevant 95% sensitivity operating point 2.9 times higher than the previous state-of-the-art (36.8% specificity compared to 12.5%). Compared to the average of 8 expert dermatologists on a subset of 100 test images, the proposed system produces a higher accuracy (76% vs. 70.5%), and specificity (62% vs. 59%) evaluated at an equivalent sensitivity (82%).