YOLOv5‐based Detection and Classification of Early and Late Mild Cognitive Impairment through Corpus Callosum Analysis
Vamshi Krishna Kancharla, Neelam Sinha · 2025
Read YOLOv5‐based Detection and Classification of Early and Late Mild Cognitive Impairment through Corpus Callosum Analysis by Vamshi Krishna Kancharla, Neelam Sinha (2025) 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-11716947.txt.
Description
Vamshi Krishna Kancharla and Neelam Sinha repurpose an object-detection network to stage early Alzheimer's decline from brain scans, in this 2025 paper. The corpus callosum, the great fiber bridge between the brain's hemispheres, shrinks as neurodegeneration advances. Distinguishing early from late mild cognitive impairment is a step toward timely care.
Their model adapts YOLOv5, a fast detector built for everyday images, to find the callosum in structural MRI slices and classify the scan as early or late impairment. Unlike earlier texture-only approaches, it uses the callosum plus its surrounding context inside the bounding box. The data came from the ADNI cohort, one hundred subjects split evenly, eighty percent for training. On the test set the model reached ninety-seven percent accuracy. Heat maps from an interpretation method showed where it looked. The authors suggest detection networks deserve a place in neuroimaging toolkits.
Catalog record
| CREATOR | Vamshi Krishna Kancharla, Neelam Sinha |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |