Smartphone-based imaging system could enable faster oral cancer detection
A new smartphone-based imaging system developed by Rice University researchers could soon help dentists detect oral cancer in just minutes — offering an affordable and efficient solution for early diagnosis.
The system, called mDOC (mobile oral cancer detection), combines white light and autofluorescence imaging with artificial intelligence (AI) and machine learning to assess oral lesions. With an average imaging time of only 3.5 minutes, it could prove especially useful in dental clinics that lack specialized training or advanced diagnostic tools.
How mDOC works
Autofluorescence imaging uses blue light to highlight changes in tissue fluorescence, which can signal abnormal cell growth. However, inflammation and other benign conditions can also reduce fluorescence, leading to false alarms.
To improve accuracy, the mDOC system integrates deep learning algorithms that analyze both imaging data and patient risk factors — such as age, smoking habits, and the location of the lesion — before recommending whether a patient needs specialist referral.
What the study found
In a pilot study conducted at two community dental clinics in Houston, Texas, researchers collected data from 50 patients. Each participant underwent imaging of up to five oral sites using mDOC.
Expert clinicians reviewed the results, and the system’s performance was further enhanced using rehearsal training, which blended new patient data with images from previous high-prevalence and healthy populations.
While the system misclassified two of five referral sites, those lesions had resolved by the time of specialist examination — suggesting mDOC may have correctly identified cases not needing further review. The system also generated 21 false positives, highlighting areas for future algorithm refinement.
Future potential
With its short imaging time and user-friendly design, researchers believe mDOC could easily fit into routine dental workflows. They suggest that collecting more detailed patient histories and refining the AI model could further improve diagnostic accuracy and reduce false positives.
If validated through larger clinical trials, this low-cost diagnostic innovation could help bridge healthcare gaps, especially in regions with limited access to oral cancer specialists and advanced imaging equipment.
Stay informed with Dental News Pakistan
CLICK HERE TO JOIN our WhatsApp community for verified global oral health updates, new innovations, expert insights, and breaking dental news delivered straight to your phone.