Assessment of image quality on the diagnostic performance of clinicians and deep learning models: Cross-sectional comparative reader study.

Journal: Journal of the European Academy of Dermatology and Venereology : JEADV
Published Date: Dec 10, 2024

Abstract

BACKGROUND: Skin cancer is a prevalent and clinically significant condition, with early and accurate diagnosis being crucial for improved patient outcomes. Dermoscopy and artificial intelligence (AI) hold promise in enhancing diagnostic accuracy. However, the impact of image quality, particularly high dynamic range (HDR) conversion in smartphone images, on diagnostic performance remains poorly understood.

Authors

  • A I Oloruntoba
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • M Asghari-Jafarabadi
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • M Sashindranath
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • Å Ingvar
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • N R Adler
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • C Vico-Alonso
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
  • L Niklasson
    Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark.
  • A L Caixinha
    Department of Dermatology and Venereology, Aarhus University Hospital, Aarhus, Denmark.
  • E Hiscutt
    Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
  • Z Holmes
    Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
  • K B Assersen
    Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark.
  • S Adamson
    Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
  • T Jegathees
    Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
  • T Bertelsen
    Department of Dermatology and Venereology, Aarhus University Hospital, Aarhus, Denmark.
  • V Velasco-Tamariz
    Department of Dermatology, Hospital Universitario 12 de Octubre, Madrid, Spain.
  • T Helkkula
    Department of Dermatology, Skåne University Hospital, Lund, Sweden.
  • S Kristiansen
    Department of Dermatology, Skåne University Hospital, Lund, Sweden.
  • R Toholka
    Department of Surgical Oncology (Dermatology), Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia.
  • M S Goh
    Department of Surgical Oncology (Dermatology), Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia.
  • A Chamberlain
    Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
  • C McCormack
    Department of Surgical Oncology (Dermatology), Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia.
  • T Vestergaard
    Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark.
  • D Mehta
    Monash eResearch Centre, Monash University, Clayton, Melbourne, Victoria, Australia.
  • T D Nguyen
    Monash eResearch Centre, Monash University, Clayton, Melbourne, Victoria, Australia.
  • Z Ge
    Monash eResearch Centre, Monash University, Clayton, Melbourne, Victoria, Australia.
  • H P Soyer
    Dermatology Research Centre, The University of Queensland, The University of Queensland Diamantina Institute, Brisbane; Dermatology Department, Princess Alexandra Hospital, Brisbane, Australia. Electronic address: p.soyer@uq.edu.au.
  • V Mar
    School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.

Keywords

External Resources

Popular Topics
Recent Journals