Deep Feature–Based Detection of Chiari Malformation Type I from Sagittal T2-Weighted MRI Using a Hybrid CNN–Machine Learning Framework
Zülküf Akdemir, Murat Canayaz · 2026
Read Deep Feature–Based Detection of Chiari Malformation Type I from Sagittal T2-Weighted MRI Using a Hybrid CNN–Machine Learning Framework by Zülküf Akdemir, Murat Canayaz (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-13256354.txt.
Description
Zülküf Akdemir and Murat Canayaz present a 2026 study teaching computers to spot Chiari malformation type I, a hindbrain defect, on MRI scans. Diagnosis normally rests on radiologists judging subtle anatomy, and readings vary. Their hybrid system first extracts deep features from sagittal scans with pretrained image networks, then hands those features to classic classifiers.
The dataset covered 764 images from 550 adults scanned on two machines. Features from the ResNet-50 network performed best, and a soft-voting ensemble of classifiers reached perfect scores across every measure in patient-level cross-validation. A lighter network, MobileNetV2, was nearly as strong but slightly less stable. The authors propose the system as a diagnostic aid for radiologists, while the perfect score on one dataset invites testing on outside hospitals before clinical trust.
Catalog record
| CREATOR | Zülküf Akdemir, Murat Canayaz |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |