Automated detection of oral pre-cancerous tongue lesions using deep learning for early diagnosis of oral cavity cancer

TL;DR

This study demonstrates that deep learning models can accurately and automatically identify pre-cancerous tongue lesions from images, potentially enabling early and inexpensive oral cavity cancer screening especially in resource-limited settings.

Contribution

The paper introduces the application of transfer learning with six deep CNN models for early detection of oral pre-cancerous lesions using small datasets, achieving high accuracy and sensitivity.

Findings

Vgg19 achieved 98% accuracy in differentiating benign and pre-cancerous lesions.

ResNet50 distinguished five tongue lesion types with 97% accuracy.

AI+Physician ensemble matched near-human classification performance.

Abstract

Discovering oral cavity cancer (OCC) at an early stage is an effective way to increase patient survival rate. However, current initial screening process is done manually and is expensive for the average individual, especially in developing countries worldwide. This problem is further compounded due to the lack of specialists in such areas. Automating the initial screening process using artificial intelligence (AI) to detect pre-cancerous lesions can prove to be an effective and inexpensive technique that would allow patients to be triaged accordingly to receive appropriate clinical management. In this study, we have applied and evaluated the efficacy of six deep convolutional neural network (DCNN) models using transfer learning, for identifying pre-cancerous tongue lesions directly using a small data set of clinically annotated photographic images to diagnose early signs of OCC. DCNN model based on Vgg19 architecture was able to differentiate between benign and pre-cancerous tongue lesions with a mean classification accuracy of 0.98, sensitivity 0.89 and specificity 0.97. Additionally, the ResNet50 DCNN model was able to distinguish between five types of tongue lesions i.e. hairy tongue, fissured tongue, geographic tongue, strawberry tongue and oral hairy leukoplakia with a mean classification accuracy of 0.97. Preliminary results using an (AI+Physician) ensemble model demonstrate that an automated initial screening process of tongue lesions using DCNNs can achieve near-human level classification performance for diagnosing early signs of OCC in patients.