Back To Projects

Dental Segmentation of The Mandible Using AI

Khushi G.

Dental segmentation can help with decision-support issues in medical diagnosis, such as human identification and maxillofacial surgery, as well as orthodontic therapy, implant planning, and other issues. This leads to my research question; “How do I automate the task required to diagnose a dental problem during a dental visit?”

Dental segmentation can help with decision-support issues in medical diagnosis, such as human identification and maxillofacial surgery, as well as orthodontic therapy, implant planning, and other issues. This leads to my research question; “How do I automate the task required to diagnose a dental problem during a dental visit?” The approach to solve this was to train an AI with images pre-segmented by experts and then test it. This process is also called image segmentation. The AI had eventually gotten a test accuracy score of 0.940 and test IoU score of 0.904. The closer to one that these scores are the better. Pixel accuracy and Iou score were surprisingly similar. I think that this is a good thing because it means both seem pretty accurate. The AI has its flaws but it can segment images when given images

Explore More!

Khushi G.
Joseph Vincent
Aerospace Engineering PhD Candidate at Stanford

Related Projects

Multi-Label Prediction of Protein Subcellular Localizations through Machine Learning and State-of-the-art Structural Embeddings
This research explores various machine learning models to predict protein subcellular localization using UniProt’s Swiss-Prot database and Meta’s high-performing ESM2 structural embeddings.
Alfred B.
Mentored by Ayush Pandit
Training a Machine Learning Model to Recognize Signs of Depression
Many people have not had a professional diagnosis, and could have depression without being aware of it. To attempt to answer this question, I used a person’s daily habits and how they change, and attempt to predict if they will experience a depressive episode in the future.
Bwohan W.
Mentored by Barbie Duckworth
Diabetic Retinopathy Evaluation: A ViT Approach
This study explores the use of a Vision Transformer (ViT) model to classify diabetic retinopathy severity from fundus images, demonstrating promising accuracy through transfer learning and data augmentation techniques. While results fell short of state-of-the-art benchmarks, the model shows potential for improving early diagnosis through AI-driven medical imaging.
Adi M.
Mentored by Abdullah Rashed Ahmed
Inspirit AI

About Inspirit AI

Home Team Impact

Programs

Live Online Learn More Apply Now

Join Our Mailing List

Stay up to date with all things Inspirit AI!

Subscribe

© 2022 Inspirit AI. All Rights Reserved.

Terms and conditions | Refund policy | Privacy policy

Research Paper