SegAN for Recognition of Caries From 2D-Panoramic X-Ray Images

Accurate recognition and segmentation of dental caries in 2D panoramic X-ray images are crucial for timely diagnosis and strategic treatment planning. The current study uses a Generative Adversarial Network (GAN) model named SegAN to segment the X-ray samples to recognize the caries. The SegAN model works in an adversarial architecture in which the generator focuses on creating precise segmentation maps of caries from 2D panoramic X-ray images. On the other hand, the discriminator ensures that the output matches realistic segmentation patterns. The SegAN model efficiently handles the local and global contextual information for precise segmentation by considering Pixel-Wise and structural loss measures that assist in better segmentation of complex structures. Moreover, the SegAN model efficiently deals with noisy data and effectively handles class imbalances. Data augmentation, like histogram equalization and affine transforms, is performed on the input images for precise segmentation of the samples. The model was evaluated on both raw and preprocessed dental X-ray images using standard quantitative metrics. SegAN demonstrated superior performance compared to traditional segmentation approaches, achieving an accuracy of 98.5%, and a dice coefficient of 0.936 in caries detection.