A low-cost, smartphone-based imaging system could be used by dental professionals to detect oral cancer in minutes.
Researchers at Rice University have developed a system – called mDOC – that combines white light and autofluorescence imaging with machine learning to assess oral lesions.
With an average imaging time of 3.5 minutes, the team believe it could help to plug gaps where there is a lack of specialised training to distinguish between benign and potentially malignant conditions.
Autofluorescence imaging uses blue light to detect changes in tissue fluorescence, which can indicate abnormal growth. However, this method alone can be misleading, as benign conditions like inflammation also reduce fluorescence. To improve accuracy, therefore, the mDOC system uses a deep learning algorithm that analyses both image data and patient risk factors – such as age, smoking habits and anatomic location – to make referral recommendations.
What results did the imaging system produce?
In this study, researchers collected data from 50 patients at two community dental clinics in Houston, Texas. Each patient underwent imaging of up to five oral sites using the mDOC device, with the images then reviewed by expert clinicians.
The team used a rehearsal training method, combining new data with previously collected images from high-prevalence and healthy populations to improve the model’s performance in typical dental settings, where suspicious lesions are rare.
The system misclassified two of five referral sites but those lesions had resolved by the time of the specialist visit – suggesting that mDOC may have correctly predicted that no further evaluation was necessary. However, it also produced 21 false positives, indicating room for improvement in accuracy.
With its short imaging time, researchers bleieve the system could easily fit into routine dental workflows. Future improvement suggestions included collecting more detailed patient history and refining the algorithm to reduce false positives.
Follow Dentistry.co.uk on Instagram to keep up with all the latest dental news and trends.
