Automated segmentation for early detection of uveal melanoma.

Journal: Canadian journal of ophthalmology. Journal canadien d'ophtalmologie
Published Date:

Abstract

OBJECTIVE: Uveal melanoma is the most common intraocular malignancy in adults. Current screening and triaging methods for melanocytic choroidal tumours face inherent limitations, particularly in regions with limited access to specialized ocular oncologists. This study explores the potential of machine learning to automate tumour segmentation. We develop and evaluate a machine-learning model for lesion segmentation using ultra-wide-field fundus photography.

Authors

  • Jiechao Ma
    InferVision, Beijing, 100020, China.
  • Sabrina P Iddir
    Department of Ophthalmology and Visual Sciences, University of Illinois Chicago, Chicago, IL, 60612, USA.
  • Sanjay Ganesh
    Department of Ophthalmology and Visual Sciences, University of Illinois Chicago, Chicago, IL, 60612, USA.
  • Darvin Yi
    Stanford University, Department of Radiology, Stanford, CA.
  • Michael J Heiferman
    Department of Ophthalmology and Visual Sciences, University of Illinois Chicago, Chicago, IL, 60612, USA. mheif@uic.edu.