Synchrotron‐Based Deep Learning Network of the Inner Ear: Development and Expert Validation
Ashley Micuda, Kyle Rioux, Luke Helpard, Munir Demir Bajin, Zahra Kassam, Sachin Pandey, Jaehyun Hwang, Griselda T Romero‐Sanchez, Manas Sharma, Lorne S Parnes, Hanif M Ladak, Sumit K Agrawal · 2026
Read Synchrotron‐Based Deep Learning Network of the Inner Ear: Development and Expert Validation by Ashley Micuda, Kyle Rioux, Luke Helpard, Munir Demir Bajin, Zahra Kassam, Sachin Pandey, Jaehyun Hwang, Griselda T Romero‐Sanchez, Manas Sharma, Lorne S Parnes, Hanif M Ladak, Sumit K Agrawal (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-13569625.txt.
Description
Ashley Micuda and colleagues built a deep-learning system that outlines the inner ear on ordinary CT scans better than human experts, publishing the validation study in 2026. Inner-ear shape guides cochlear implant choice and tuning, yet hand tracing from clinical scans is slow, variable, and limited by resolution. The team trained the network on 4,784 paired datasets from 100 cadaver specimens imaged with high-resolution synchrotron scans and varied clinical CT machines.
On unseen scans, the network beat every individual expert, the expert average, and a consensus segmentation, reaching a Dice overlap of 0.922 against synchrotron truth at resolutions down to 625 micrometres. The authors present it as the first automated inner-ear segmenter to surpass experts, setting a new standard for surgical planning and implant fitting.
Catalog record
| CREATOR | Ashley Micuda, Kyle Rioux, Luke Helpard, Munir Demir Bajin, Zahra Kassam, Sachin Pandey, Jaehyun Hwang, Griselda T Romero‐Sanchez, Manas Sharma, Lorne S Parnes, Hanif M Ladak, Sumit K Agrawal |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |