The prevalence of oral potentially malignant disorders (OPMDs) and oral cancer is surging in low- and middle-income countries. A lack of resources for population screening in remote locations delays the detection of these lesions in the early stages and contributes to higher mortality and a poor quality of life. Digital imaging and artificial intelligence (AI) are promising tools for cancer screening. This study aimed to evaluate the utility of AI-based techniques for detecting OPMDs in the Indian population using photographic images of oral cavities captured using a smartphone. A dataset comprising 1120 suspicious and 1058 non-suspicious oral cavity photographic images taken by trained front-line healthcare workers (FHWs) was used for evaluating the performance of different deep learning models based on convolution (DenseNets) and Transformer (Swin) architectures. The best-performing model was also tested on an additional independent test set comprising 440 photographic images taken by untrained FHWs (set I). DenseNet201 and Swin Transformer (base) models show high classification performance with an F1-score of 0.84 (CI 0.79–0.89) and 0.83 (CI 0.78–0.88) on the internal test set, respectively. However, the performance of models decreases on test set I, which has considerable variation in the image quality, with the best F1-score of 0.73 (CI 0.67–0.78) obtained using DenseNet201. The proposed AI model has the potential to identify suspicious and non-suspicious oral lesions using photographic images. This simplified image-based AI solution can assist in screening, early detection, and prompt referral for OPMDs.

Oral cancer though preventable, shows high mortality and affect the overall quality of life when detected in late stages. Screening techniques that enable early diagnosis are the need of the hour. The present work aims to evaluate the effectiveness of AI screening tools in the diagnosis of OPMDs and Oral cancers via native or web-application (cloud) using smart phone devices. We trained and tested two deep learning models namely DenseNet201 and FixCaps using 518 images of the oral cavity. While DenseNet201 is a pre-trained model, we modified the FixCaps model from capsule network and trained it ground up. Standardized protocols were used to annotate and classify the lesions (suspicious vs. non-suspicious). In terms of model performance, DenseNet201 achieved an F1 score of 87.50% and AUC of 0.97; while FixCaps exhibited F1 score of 82.8% and AUC of 0.93. DenseNet201 model (20 M) serves as a robust screening model (accuracy 88.6%) that can be hosted on a web-application in the cloud servers; while the adapted FixCaps model with its low parameter size of 0.83 M exhibits comparable accuracy (83.8%) allowing easy transitioning into a native phone-based screening application.