Using deep learning for dermatologist-level detection of suspicious pigmented skin lesions from wide-field images.

Journal: Science translational medicine
Published Date: Feb 17, 2021

Abstract

A reported 96,480 people were diagnosed with melanoma in the United States in 2019, leading to 7230 reported deaths. Early-stage identification of suspicious pigmented lesions (SPLs) in primary care settings can lead to improved melanoma prognosis and a possible 20-fold reduction in treatment cost. Despite this clinical and economic value, efficient tools for SPL detection are mostly absent. To bridge this gap, we developed an SPL analysis system for wide-field images using deep convolutional neural networks (DCNNs) and applied it to a 38,283 dermatological dataset collected from 133 patients and publicly available images. These images were obtained from a variety of consumer-grade cameras (15,244 nondermoscopy) and classified by three board-certified dermatologists. Our system achieved more than 90.3% sensitivity (95% confidence interval, 90 to 90.6) and 89.9% specificity (89.6 to 90.2%) in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, avoiding the need for cumbersome individual lesion imaging. We also present a new method to extract intrapatient lesion saliency (ugly duckling criteria) on the basis of DCNN features from detected lesions. This saliency ranking was validated against three board-certified dermatologists using a set of 135 individual wide-field images from 68 dermatological patients not included in the DCNN training set, exhibiting 82.96% (67.88 to 88.26%) agreement with at least one of the top three lesions in the dermatological consensus ranking. This method could allow for rapid and accurate assessments of pigmented lesion suspiciousness within a primary care visit and could enable improved patient triaging, utilization of resources, and earlier treatment of melanoma.

Authors

  • Luis R Soenksen
    Department of Biological Engineering, Massachusetts Institute of Technology (MIT), Cambridge, MA, 02139, USA.
  • Timothy Kassis
    Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Susan T Conover
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.
  • Berta Marti-Fuster
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.
  • Judith S Birkenfeld
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.
  • Jason Tucker-Schwartz
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.
  • Asif Naseem
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.
  • Robert R Stavert
    Division of Dermatology, Cambridge Health Alliance, 1493 Cambridge Street, Cambridge, MA 02139, USA.
  • Caroline C Kim
    Pigmented Lesion Program, Newton Wellesley Dermatology Associates, 65 Walnut Street Suite 520 Wellesley Hills, MA 02481, USA.
  • Maryanne M Senna
    Department of Dermatology, Harvard Medical School, 25 Shattuck St, Boston, MA 02115, USA.
  • José Avilés-Izquierdo
    Department of Dermatology, Hospital General Universitario Gregorio Marañón, Calle del Dr. Esquerdo 46, 28007 Madrid, Spain.
  • James J Collins
    Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA, USA.
  • Regina Barzilay
    Computer Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology , 77 Massachusetts Avenue , Cambridge , MA 02139 , USA . Email: regina@csail.mit.edu.
  • Martha L Gray
    Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, USA.

Keywords

External Resources

Popular Topics
Recent Journals