VivaKitBone Fracture Detection on X-rays
Faster R-CNN (torchvision, BSD licence - no AGPL code) draws boxes around suspected fractures on hand, leg, hip and shoulder X-rays. Learn anchors, IoU, NMS and how average precision is really computed - in plain NumPy you can read.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| Box [email protected] (fractured test images) | 0.493 |
| Image-level ROC-AUC (399 test images) | 0.866 |
| Image-level sensitivity | 0.714 |
| Image-level specificity | 0.821 |
FracAtlas is small and hard - fractures are tiny and only 719 of 4,083 images contain one. These are honest baseline numbers. Trained in 25 min on an RTX 5070 Laptop GPU.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
Abedeen I. et al. (2023). FracAtlas: A Dataset for Fracture Classification, Localization and Segmentation of Musculoskeletal Radiographs. Scientific Data 10, 521. doi:10.6084/m9.figshare.22363012 - CC BY 4.0.
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.