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.

Download full-text PDF

Source
http://dx.doi.org/10.1111/odi.14206DOI Listing

Publication Analysis

Top Keywords

oral lesions
28
oral
10
image collection
8
collection annotation
8
lesions
8
clinically labelled
8
annotation
5
image
4
annotation platforms
4
platforms establish
4

Similar Publications

Background: Chronic tobacco use, in any form, induces significant cellular alterations in the oral mucosa. This study investigates four distinct cytomorphological changes in oral mucosal cells among smokeless tobacco users, examining their association across different genders and age groups.

Materials And Methods: This cross-sectional study involved collecting mucosal samples from smokeless tobacco (naswar/snuff) users through consecutive sampling.

View Article and Find Full Text PDF

Identifying Pain Subtypes in Patients With Craniofacial Lesions of Fibrous Dysplasia/McCune-Albright Syndrome.

J Oral Maxillofac Surg

December 2024

Assistant Professor, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA; Assistant Professor, Department of Psychiatry, McLean Hospital, Harvard Medical School, Belmont, MA. Electronic address:

Background: Fibrous dysplasia/McCune-Albright syndrome (FD/MAS) is a genetic disorder, marked by bone lesions, often affecting the craniofacial skeleton. Pain is a prevalent yet heterogeneous symptom reported by patients with craniofacial FD. Effective treatments are currently lacking, posing a significant clinical challenge to patient care.

View Article and Find Full Text PDF

Background: Recent biomedical research has shown the unusual, multisystem effects of coronavirus disease 2019 in humans. One specific sequela of a primary severe acute respiratory syndrome coronavirus 2 infection is the reactivation of latent viruses in various tissues, such as Epstein-Barr virus. Epstein-Barr virus has been identified in many inflammatory gastrointestinal lesions, such as microscopic gastritides and colitides.

View Article and Find Full Text PDF

Background: The multi-biological barriers present in the inflammatory microenvironment severely limit the targeted aggregation of anti-inflammatory drugs in the lesion area. However, conventional responsive drug carriers inevitably come into contact with several pro-responsive stimulatory mediators simultaneously, leading to premature drug release and loss of most therapeutic effects. Breaking through the multi-level barriers of the inflammatory microenvironment is essential to improve the enrichment and bioavailability of drugs.

View Article and Find Full Text PDF

Introduction: The introduction of multiparametric prostate magnetic resonance imaging (mpMRI) has revolutionized prostate cancer (PCa) diagnosis, enhancing the localization of clinically significant prostate cancer (csPCa) and guiding targeted biopsies. However, significant disparities in the execution, interpretation, and reporting of prostate MRI examinations across centers necessitate greater standardization and accuracy. This study compares the diagnostic efficacy of mpMRI from academic and nonacademic centers in detecting csPCa and identifies factors associated with csPCa detection.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!