Comparison of computer systems and ranking criteria for automatic melanoma detection in dermoscopic images

TL;DR

This study evaluates how different ranking criteria, segmentation methods, and classifiers affect the performance assessment of computer systems for melanoma detection in dermoscopic images, emphasizing the importance of high-sensitivity measures for clinical relevance.

Contribution

It systematically compares ranking measures and classifiers, revealing their impact on system performance evaluation and highlighting the limited effect of segmentation improvements.

Findings

Ranking criteria significantly influence system rankings.

Classifier choice impacts diagnostic accuracy more than segmentation method.

High-sensitivity measures are crucial for clinical application.

Abstract

Melanoma is the deadliest form of skin cancer. Computer systems can assist in melanoma detection, but are not widespread in clinical practice. In 2016, an open challenge in classification of dermoscopic images of skin lesions was announced. A training set of 900 images with corresponding class labels and semi-automatic/manual segmentation masks was released for the challenge. An independent test set of 379 images was used to rank the participants. This article demonstrates the impact of ranking criteria, segmentation method and classifier, and highlights the clinical perspective. We compare five different measures for diagnostic accuracy by analysing the resulting ranking of the computer systems in the challenge. Choice of performance measure had great impact on the ranking. Systems that were ranked among the top three for one measure, dropped to the bottom half when changing performance measure. Nevus Doctor, a computer system previously developed by the authors, was used to investigate the impact of segmentation and classifier. The unexpected small impact of automatic versus semi-automatic/manual segmentation suggests that improvements of the automatic segmentation method w.r.t. resemblance to semi-automatic/manual segmentation will not improve diagnostic accuracy substantially. A small set of similar classification algorithms are used to investigate the impact of classifier on the diagnostic accuracy. The variability in diagnostic accuracy for different classifier algorithms was larger than the variability for segmentation methods, and suggests a focus for future investigations. From a clinical perspective, the misclassification of a melanoma as benign has far greater cost than the misclassification of a benign lesion. For computer systems to have clinical impact, their performance should be ranked by a high-sensitivity measure.