Image collection and annotation platforms to establish a multi-source database of oral lesions

Rajendran S 1 , Lim JH 2 , Yogalingam K 1 , Kallarakkal TG 3 , Zain RB 3 , Jayasinghe RD 4 Show all authors , Rimal J 5 , Kerr AR 6 , Amtha R 7 , Patil K 8 , Welikala RA 9 , Lim YZ 1 , Remagnino P 9 , Gibson J 10 , Tilakaratne WM 3 , Liew CS 11 , Yang YH 12 , Barman SA 9 , Chan CS 2 , Cheong SC 1

Affiliations 

  • 1 Digital Health Research Unit, Cancer Research Malaysia, Subang Jaya, Malaysia
  • 2 Centre of Image and Signal Processing, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia
  • 3 Department of Oral and Maxillofacial Clinical Sciences, Faculty of Dentistry, University of Malaya, Kuala Lumpur, Malaysia
  • 4 Department of Oral Medicine and Periodontology, Centre for Research in Oral Cancer, Faculty of Dental Sciences, University of Peradeniya, Peradeniya, Sri Lanka
  • 5 Department of Oral Medicine and Radiology, BP Koirala Institute of Health Sciences, Dharan, Nepal
  • 6 Oral and Maxillofacial Pathology, Radiology and Medicine, New York University, New York, New York, USA
  • 7 Faculty of Dentistry, Trisakti University, Jakarta, Indonesia
  • 8 Oral Medicine and Radiology, JSS Dental College and Hospital, JSS Academy of Higher Education & Research, Mysuru, India
  • 9 Digital Information Research Centre, Faculty of Science, Engineering and Computing, Kingston University, Surrey, UK
  • 10 Institute of Dentistry, University of Aberdeen, Aberdeen, UK
  • 11 Department of Computer System & Technology, Faculty of Computer Science & Information Technology, University of Malaya, Kuala Lumpur, Malaysia
  • 12 National Institute of Cancer Research, National Health Research Institutes, Tainan, Taiwan
Oral Dis, 2023 Jul;29(5):2230-2238.
PMID: 35398971 DOI: 10.1111/odi.14206

Abstract

OBJECTIVE: To describe the development of a platform for image collection and annotation that resulted in a multi-sourced international image dataset of oral lesions to facilitate the development of automated lesion classification algorithms.

MATERIALS AND METHODS: We developed a web-interface, hosted on a web server to collect oral lesions images from international partners. Further, we developed a customised annotation tool, also a web-interface for systematic annotation of images to build a rich clinically labelled dataset. We evaluated the sensitivities comparing referral decisions through the annotation process with the clinical diagnosis of the lesions.

RESULTS: The image repository hosts 2474 images of oral lesions consisting of oral cancer, oral potentially malignant disorders and other oral lesions that were collected through MeMoSA® UPLOAD. Eight-hundred images were annotated by seven oral medicine specialists on MeMoSA® ANNOTATE, to mark the lesion and to collect clinical labels. The sensitivity in referral decision for all lesions that required a referral for cancer management/surveillance was moderate to high depending on the type of lesion (64.3%-100%).

CONCLUSION: This is the first description of a database with clinically labelled oral lesions. This database could accelerate the improvement of AI algorithms that can promote the early detection of high-risk oral lesions.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

MeSH terms
Similar publications