Assessing diagnostic performance of multimodal LLMs and a custom convolutional neural network in tooth-level caries detection and localization
Aamna Khalid, Ayesha Nooruddin, Nighat Naved, Syed Muhammad Faizan Ahmed, Niha Adnan, Sarang Suresh, Abhishek Lal, Fahad Umer · 2026
Read Assessing diagnostic performance of multimodal LLMs and a custom convolutional neural network in tooth-level caries detection and localization by Aamna Khalid, Ayesha Nooruddin, Nighat Naved, Syed Muhammad Faizan Ahmed, Niha Adnan, Sarang Suresh, Abhishek Lal, Fahad Umer (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13450555.txt.
Description
Aamna Khalid and co-authors set in 2026 two chat models next to a custom fold net on tooth rot calls from mouth photos. Chat models now claim sight skills with no task tune. The net was built and trained for this one task.
Twenty two top view mouth shots form the test set. Dentists also graded each model's marks for truth, box fit, and spare ink. The custom net topped the set on truth and on catch rate by a wide span. Chat models trailed on both find and place tasks. The team backs task built tools for chair side use.
Catalog record
| CREATOR | Aamna Khalid, Ayesha Nooruddin, Nighat Naved, Syed Muhammad Faizan Ahmed, Niha Adnan, Sarang Suresh, Abhishek Lal, Fahad Umer |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |