Development of a clinically oriented system for melanoma diagnosis. (September 2017)

• Record Type: Journal Article
• Authors: Barata, Catarina; Emre Celebi, M.; Marques, Jorge S.
• Is Part Of: Pattern recognition. Volume 69(2017:Sep.)
• Page Start: 270
• Page End: 285
• Publication Date: 2017-09
• Subjects: Melanoma diagnosis -- Computer aided diagnosis system -- Detection of dermoscopic structures -- Image annotation -- Corr-LDA -- Feature fusion; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.04.023
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A clinically computer aided diagnosis system is proposed for melanoma diagnosis. The system diagnoses the lesions using features that have a medical meaning. The system learns to detect various relevant dermoscopic criteria using text labels. An image annotation method is used to associate image regions with the criteria. Feature fusion is used to combine medical information and diagnose the lesions. Abstract: Dermatologists have stated their preference for computer aided diagnosis (CAD) systems that provide medical justifications for the estimated diagnosis of a skin lesion. Such systems are considered to be clinically oriented in the sense that they try to detect clinical criteria and then perform a diagnosis based on that information. Unfortunately, the development of clinically inspired systems is hampered by several challenges: (i) the lack of datasets with detailed information regarding the presence and location of clinical criteria; (ii) the subtlety of some diagnostic criteria, which makes them difficult to detect; and (iii) the difficulty of using the detected criteria to predict a diagnosis. In this work, we propose a machine learning framework to address these issues. First, an image annotation approach is used to detect various medical criteria (color, texture and color structures). Information is, then, extracted from the detected criteria and a late fusion method is used to obtain a lesion diagnosis. A sensitivity of 84.6% and a specificity of 74.2% are obtained on a multi-source dataset of 804 images.