Development and Evaluation of an Automated Multimodal Mobile Detection of Oral Cancer Imaging System to Aid in Risk-Based Management of Oral Mucosal Lesions

Sep 23, 2026

Uploaded by Ophelia

Oral cancer is a major global health problem, often diagnosed at an advanced stage despite visible oral mucosal lesions that signal oral potentially malignant disorders. The study addresses a clinical need for effective screening to help frontline providers decide which patients should be referred to oral cancer specialists. It presents a smartphone-based mDOC system using autofluorescence and white light imaging plus an automated multimodal algorithm that outputs referral recommendations. Using cross-validation and a holdout test set, referral decisions showed high sensitivity and moderate specificity compared with expert labels.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Oral cancer burden and diagnostic delays

Oral potentially malignant disorders and need for referral support

Study overview: mDOC system and automated referral algorithm

Data collection and multimodal image classification approach

Training, cross-validation, and holdout evaluation

Results and clinical relevance

Development and Evaluation of an Automated Multimodal Mobile Detection of Oral Cancer Imaging System to Aid in Risk-Based Management of Oral Mucosal Lesions Ruchika Mitbander1, David Brenes1, Jackson B. Coole1, Alex Kortum1, Imran S. Vohra1, Jennifer Carns1, Richard A. Schwarz1, Ida Varghese2, Safia Durab2, Sean Anderson2, Nancy E. Bass2, Ashlee D. Clayton1, Hawraa Badaoui3, Loganayaki Anandasivam4, Rachel A. Giese5, Ann M. Gillenwater3, Nadarajah Vigneswaran2, and Rebecca Richards-Kortum1 | | | | A | | B | S | | T | R | | A | | C | T | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 􀀶 | | Oral cancer is a major global health problem. It is commonly diagnosed at an advanced stage, although often preceded by clinically visible oral mucosal lesions, termed oral potentially malignant disorders, which are associated with an increased risk of oral cancer development. There is an unmet clinical need for effective screening tools to assist frontline healthcare providers to determine which patients should be referred to an oral cancer specialist for evaluation. This study reports the development and evaluation of the mobile detection of oral cancer (mDOC) imaging system and an automated algorithm that generates a referral recommendation from mDOC images. mDOC is a smartphone-based autofluorescence and white light imaging tool that captures images of the oral cavity. Data were collected using mDOC from a total of 332 oral sites in a study of 29 healthy volunteers and 120 patients seeking care for an oral mucosal lesion. A multimodal image classification algorithm was developed to generate a recommendation of “refer” or “do | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | not refer” from mDOC images using expert clinical referral decision as the ground truth label. A referral algorithm was developed using cross-validation methods on 80% of the dataset and then retrained and evaluated on a separate holdout test set. Referral decisions generated in the holdout test set had a sensitivity of 93.9% and a specificity of 79.3% with respect to expert clinical referral decisions. The mDOC system has the potential to be utilized in community physicians’ and dentists’ offices to help identify patients who need further evaluation by an oral cancer specialist.
Prevention Relevance: Our research focuses on improving the early detection of oral precancers/cancers in primary dental care settings with a novel mobile platform that can be used by front-line providers to aid in assessing whether a patient has an oral mucosal condition that requires further follow-up with an oral cancer specialist. | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Introduction Oral cancer is a major global health problem. Despite the ease of direct visual examination of the oral cavity, oral cancer is 1Department of Bioengineering, Rice University, Houston, Texas. 2Department of Diagnostic and Biomedical Sciences, The University of Texas Health Science Cen

FAQs

What problem does the mobile detection system aim to solve?

It targets the need for effective screening so frontline providers can decide which patients with oral mucosal lesions should be referred to an oral cancer specialist for evaluation.

How does the mDOC system capture oral-cavity information?

mDOC is a smartphone-based tool that collects autofluorescence and white light images of the oral cavity.

How were the referral recommendations developed and evaluated?

A multimodal image classification algorithm was trained to generate “refer” or “not refer” recommendations using expert clinical referral decisions as ground truth. It was trained with cross-validation and then retrained and tested on a separate holdout dataset.

Sep 23, 2026

Uploaded by Ophelia