https://github.com/sohambasu07/bonejointslocalization

Detection of Bone Joints using Deep Learning
https://github.com/sohambasu07/bonejointslocalization

bone-jonts centernet computer-vision convolutional-neural-networks deep-learning detection-model efficientdet medical-image-processing medical-imaging object-detection xray-images yolov3 yolov7

Last synced: 3 months ago
JSON representation

Detection of Bone Joints using Deep Learning

• Host: GitHub
• URL: https://github.com/sohambasu07/bonejointslocalization
• Owner: Sohambasu07
• License: mit
• Created: 2022-09-12T17:34:50.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2024-11-01T20:26:57.000Z (11 months ago)
• Last Synced: 2024-11-01T21:24:09.890Z (11 months ago)
• Topics: bone-jonts, centernet, computer-vision, convolutional-neural-networks, deep-learning, detection-model, efficientdet, medical-image-processing, medical-imaging, object-detection, xray-images, yolov3, yolov7
• Language: Jupyter Notebook
• Homepage:
• Size: 583 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

          
A Comparative Study of Multiple Deep Learning Algorithms for Efficient Localization of Bone Joints in the Upper Limbs of Human Body


[Soumalya Bose](https://scholar.google.com/citations?user=Y_pbe8kAAAAJ&hl=en), [Soham Basu](https://scholar.google.com/citations?user=VFrBx88AAAAJ&hl=en), [Indranil Bera](https://www.linkedin.com/in/indranil-bera-16007196), [Sambit Mallick](https://www.linkedin.com/in/sambit-mallick-428b31235), [Snigdha Paul](https://www.linkedin.com/in/snigdha-paul-bb4355252), [Saumodip Das](https://www.linkedin.com/in/saumodip-das-3b37b822a), [Swarnendu Sil](https://www.linkedin.com/in/swarnendu-sil-641abb22b), [Swarnava Ghosh](https://www.linkedin.com/in/swarnava-ghosh-28711b178), [Anindya Sen](https://scholar.google.com/citations?user=vA6hgasAAAAJ&hl=en)

[![springer](https://img.shields.io/badge/Springer-Paper-rgb(50,50,200))](https://link.springer.com/chapter/10.1007/978-981-19-9819-5_46)

[![paper](https://img.shields.io/badge/arXiv-Paper-brightgreen)](https://arxiv.org/abs/2410.20639)

[![dataset](https://img.shields.io/badge/MURA-Dataset-red)](https://stanfordmlgroup.github.io/competitions/mura/)

[![saved_models](https://img.shields.io/badge/Saved-Models-yellow)](https://drive.google.com/drive/folders/1lgz6nURTzDC2HbEBdGaf-sVS0jgQiysC?usp=sharing) 



Conference: 6th International Conference on Computational Vision and Bio Inspired Computing - ICCVBIC 2022 (Nov 18 - 19, 2022) 

Published in - Advances in Intelligent Systems and Computing (vol. 1439) - Springer Singapore, April 8, 2023.



> **Abstract:** *This paper addresses the medical imaging problem of joint detection in the upper limbs, viz. elbow, shoulder, wrist and finger joints. Localization of joints from X-Ray and Computerized Tomography (CT) scans is an essential step for the assessment of various bone-related medical conditions like Osteoarthritis, Rheumatoid Arthritis, and can even be used for automated bone fracture detec-tion. Automated joint localization also detects the corresponding bones and can serve as input to deep learning-based models used for the computerized diagnosis of the aforementioned medical disorders. This increases the accuracy of predic-tion and aids the radiologists with analyzing the scans, which is quite a complex and exhausting task. This paper provides a detailed comparative study between diverse Deep Learning (DL) models – YOLOv3, YOLOv7, EfficientDet and CenterNet in multiple bone joint detections in the upper limbs of the human body. The research analyses the performance of different DL models, mathematically, graphically and visually. These models are trained and tested on a portion of the openly available MURA (musculoskeletal radiographs) dataset. The study found that the best Mean Average Precision (mAP0.5:0.95) values of YOLOv3, YOLOv7, EfficientDet and CenterNet are 35.3, 48.3, 46.5 and 45.9 respectively. Besides, it has been found YOLOv7 performed the best for accurately predicting the bound-ing boxes while YOLOv3 performed the worst in the Visual Analysis test.*



Notebooks for model training, testing and evaluation in /Notebooks 

Saved Models are available at at this link.



Cite our work


    

    Bose, S., Basu, S., Bera, I., Mallick, S., Paul, S., Das, S., Sil, S., Ghosh, S., Sen, A. (2022). A Comparative Study of Multiple Deep Learning Algorithms for Efficient Localization of Bone Joints in the Upper Limbs of Human Body. In: Smys, S., Tavares, J.M.R.S., Shi, F. (eds) Computational Vision and Bio-Inspired Computing. Advances in Intelligent Systems and Computing, vol 1439. Springer, Singapore. https://doi.org/10.1007/978-981-19-9819-5_46.



Contact

For any queries, please contact: soham.basu07@gmail.com