Improving Diagnostic Accuracy for Oral Cancer with inpainting Synthesis Lesions Generated Using Diffusion Models
This addresses data scarcity in oral cancer diagnostics for medical AI applications, though it is incremental as it applies existing diffusion model techniques to a specific domain.
The study tackled the problem of limited annotated datasets for oral cancer diagnostics by synthesizing realistic lesions using a fine-tuned diffusion model with inpainting, resulting in a classification accuracy of 0.97 for differentiating cancerous tissues and detection accuracy of 0.85 for lesion locations.
In oral cancer diagnostics, the limited availability of annotated datasets frequently constrains the performance of diagnostic models, particularly due to the variability and insufficiency of training data. To address these challenges, this study proposed a novel approach to enhance diagnostic accuracy by synthesizing realistic oral cancer lesions using an inpainting technique with a fine-tuned diffusion model. We compiled a comprehensive dataset from multiple sources, featuring a variety of oral cancer images. Our method generated synthetic lesions that exhibit a high degree of visual fidelity to actual lesions, thereby significantly enhancing the performance of diagnostic algorithms. The results show that our classification model achieved a diagnostic accuracy of 0.97 in differentiating between cancerous and non-cancerous tissues, while our detection model accurately identified lesion locations with 0.85 accuracy. This method validates the potential for synthetic image generation in medical diagnostics and paves the way for further research into extending these methods to other types of cancer diagnostics.