AI in Dentistry: Mental Foramen Detection and Segmentation
Manage episode 444599864 series 3605861
This research paper explores the use of deep learning to improve the accuracy of detecting and segmenting the mental foramen in dental orthopantomogram images. The authors compared the performance of various deep learning models, including U-Net, U-Net++, ResUNet, and LinkNet, using a dataset of 1000 panoramic radiographs. The study found that the U-Net model consistently performed best for both round and square-shaped masks, achieving a Dice Coefficient of 0.79 and an Intersection over Union of 0.67. This research has implications for enhancing dental diagnostics and improving patient outcomes.
Read more here: https://arxiv.org/pdf/2408.04763
65 epizódok