Digital imaging biomarkers feed machine learning for melanoma screening. uri icon

Overview

abstract

  • We developed an automated approach for generating quantitative image analysis metrics (imaging biomarkers) that are then analysed with a set of 13 machine learning algorithms to generate an overall risk score that is called a Q-score. These methods were applied to a set of 120 "difficult" dermoscopy images of dysplastic nevi and melanomas that were subsequently excised/classified. This approach yielded 98% sensitivity and 36% specificity for melanoma detection, approaching sensitivity/specificity of expert lesion evaluation. Importantly, we found strong spectral dependence of many imaging biomarkers in blue or red colour channels, suggesting the need to optimize spectral evaluation of pigmented lesions.

publication date

  • December 19, 2016

Research

keywords

  • Biomarkers, Tumor
  • Dermoscopy
  • Melanoma
  • Nevus, Pigmented
  • Skin Neoplasms

Identity

PubMed Central ID

  • PMC5516237

Scopus Document Identifier

  • 85007249848

Digital Object Identifier (DOI)

  • 10.1111/exd.13250

PubMed ID

  • 27783441

Additional Document Info

volume

  • 26

issue

  • 7