Journal Article

MeMoSA dataset: A multi-country collection of over 30,000 oral mucosa images with clinically labelled lesions

Jayasinghe, Ruwan Duminda, Rajah, Davinna Satguna, Lee, Hui Ying, Zainuddin, Nurul Izyan, Kadir, Kathreena, Muthukrishnan, Arvind, Hassan, Muhammad Kamil, Rimal, Jyotsna, Ismail, Siti Mazlipah, Kallarakkal, Thomas George, Tilakaratne, Wanninayake Mudiyanselage, Cheong, Sok Ching, Mohamad Zaini, Zuraiza, Kerr, Alexander Ross, Saw, Shier Nee, Patil, Karthikeya, Sin, Wei Jie, Kipli, Nurshaline Pauline Hj, Chan, Chee Seng, Amtha, Rahmi, Liew, Chee Sun, Lau, Shin Hin, Chew, Sara, Nabil, Aliya, Maling, Thaddius Herman, Tan, Chuey Chuan, Abidin, Nur Fauziani Zainul, Sekar, Karthick, Chan, Siew Wui, Rajendran, Senthilmani, Goh, Yet Ching, Zain, Rosnah Binti

2026

Overview

The rising incidence of oral cancer and associated poor prognosis, primarily due to delayed diagnosis, highlight the urgent need for artificial intelligence tools in clinical detection. However, efforts in this regard are hampered by the lack of large and ethnically heterogenous image datasets of oral lesions with clinically validated diagnoses. To address this gap, oral mucosa images captured with mobile device cameras were collected from cohorts spanning five countries. The images were systematically annotated with lesion type classifications as well as specific clinical diagnoses, then assessed for quality. The diagnoses were verified retrospectively by biopsy, where applicable, or by consensus verification by dental experts. The final dataset consists of 30,039 oral mucosa images supplemented by clinical metadata, made available on the MeMoSA Workbench platform. We believe that the MeMoSA dataset will serve as a significant resource to drive the training, evaluation, and refinement of AI-driven diagnostic algorithms, potentially improving diagnostic accuracy and enabling rigorous benchmarking against clinical expert assessments, for the early detection of oral cancer.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 631/67/1665/3016 / 692/1807/1707 / 692/699/3020/1665/3016 / 692/700/139 / 706/648/697/129 / Algorithms / Artificial Intelligence / Automation / Biopsy / Cellular telephones / Data Descriptor / Datasets / Decision making / Dentists / Humanities and Social Sciences / Humans / Informed consent / Lesions / Maxillofacial surgery / Medical diagnosis / Medical screening / Metadata / Mortality / Mouth Mucosa - diagnostic imaging / Mouth Mucosa - pathology / Mouth Neoplasms - diagnosis / Mouth Neoplasms - diagnostic imaging / Mucosa / multidisciplinary / Oral cancer / Science / Science (multidisciplinary)