Automated Femoral, Acetabular, and Global Offset Measurements on Pelvis Radiograph Using Deep Learning
Jack C. Casey, Seong J. Jang, Billy I. Kim, Kyle N. Kunze, Chris Anderson, David J. Mayman, Seth A. Jerabek, Jonathan M. Vigdorchik, Peter K. Sculco · 2026
Read Automated Femoral, Acetabular, and Global Offset Measurements on Pelvis Radiograph Using Deep Learning by Jack C. Casey, Seong J. Jang, Billy I. Kim, Kyle N. Kunze, Chris Anderson, David J. Mayman, Seth A. Jerabek, Jonathan M. Vigdorchik, Peter K. Sculco (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-13533620.txt.
Description
Jack Casey and co-authors report an orthopedics study, published in 2026, on teaching a neural network to measure hip geometry from X-rays. In hip replacement surgery, offsets, the sideways distances that set the joint's leverage, decide how well the native anatomy is restored, but hand measurement is slow and varies by reader. Five hundred pelvis films were marked with key landmarks to train a segmentation network.
The trained model measured femoral, acetabular, and global offsets on both hips in under two seconds per film. Against two trained readers on a fresh set of ninety films, its agreement was strong across all three measures. The authors present the tool as a way to make large cohort offset studies practical.
Catalog record
| CREATOR | Jack C. Casey, Seong J. Jang, Billy I. Kim, Kyle N. Kunze, Chris Anderson, David J. Mayman, Seth A. Jerabek, Jonathan M. Vigdorchik, Peter K. Sculco |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 18 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |