Severity Classification of Parkinson’s Disease via Synthesis of Energy Skeleton Images from Videos Produced in Uncontrolled Environments
Nejib Ben Hadj-Alouane, Arav Dhoot, Monia Turki-Hadj Alouane, Vinod Pangracious, Rajesh K Tripathy, Haipeng Liu · 2024
Read Severity Classification of Parkinson’s Disease via Synthesis of Energy Skeleton Images from Videos Produced in Uncontrolled Environments by Nejib Ben Hadj-Alouane, Arav Dhoot, Monia Turki-Hadj Alouane, Vinod Pangracious, Rajesh K Tripathy, Haipeng Liu (2024) 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-11640083.txt.
Description
Grading Parkinson's disease from ordinary video could reach patients far from specialist clinics. The authors of a 2024 study turn walking clips filmed in uncontrolled settings into skeleton energy images, still pictures that compress a gait sequence into one frame. Three deep learning models then read those images: a plain convolutional network, a residual network, and a vision transformer. The goal is both spotting the disease and sorting its severity.
Training accuracy passed 99 percent for two of the models. In testing, the residual network scored a perfect mark, the transformer nearly matched it, and the plain network trailed at about 96 percent. The team credits the energy image step for making messy home video readable by standard models.
Catalog record
| CREATOR | Nejib Ben Hadj-Alouane, Arav Dhoot, Monia Turki-Hadj Alouane, Vinod Pangracious, Rajesh K Tripathy, Haipeng Liu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |