Diagnostic performance of convolutional neural network-based AI in detecting oral squamous cell carcinoma: a meta-analysis

Comprehensive Summary

This article presents a systematic review and meta-analysis evaluating the diagnostic performance of convolutional neural network (CNN)- based artificial intelligence models in detecting oral squamous cell carcinoma (OSCC). Analyzing 14 studies encompassing over 61,000 samples derived from clinical images and histopathological data, the authors found that CNN-based models demonstrated very high diagnostic accuracy, with pooled sensitivity and specificity both around 94% and an area under the receiver operating characteristic curve (AUC) of 0.98. These results indicate that AI systems are highly effective at both identifying true OSCC cases and correctly excluding non-cancer cases.

Outcomes and Implications

The findings of this study have important implications for both clinical dentistry and broader cancer diagnostics. The high diagnostic accuracy of CNN-based AI models suggests that these tools could play a significant role in early detection of oral squamous cell carcinoma, which is critical for improving patient survival and reducing treatment morbidity. Additionally, AI-assisted screening may help standardize diagnostic accuracy, reduce human error, and prompt earlier referrals for biopsy and treatment.