Treffer: Artificial Intelligence Technique For Detecting Bone Irregularity Using Fastai.

A bone abnormality is a medical condition which is caused by physical damage or diseases. There are many factors which can lead to various abnormalities. An irregularity in a bone is generally diagnosed by orthopedician and radiologists using x-ray images of the affected bone. Bone abnormalities affect more than a billion people in the world. With more than 30 million emergency visits annually, there is a lack of expertise. Although computer aided diagnosis is still very limited in the world. They are mostly confined to research projects and there's been no real world applications. For the past few years there has been a great leap in the development of Artificial Intelligence which now makes it possible to implement and test deep learning models in the medical field. One can get an appropriate amount of data for these implementations. MURA is a database that was made available by Stanford University for testing purposes in a target of achieving a best model for detecting bone abnormalities. Our paper mainly focuses on the advancement in medical imaging technologies targeting the diagnosis at the level of experts for improving health care access. We used python, as a programming tool, and fastai, to process images and implement the model for abnormality detection. The proposed model follows a feed forward network resulting in a good accuracy rate. [ABSTRACT FROM AUTHOR]

Copyright of IEOM European Conference Proceedings is the property of IEOM Society International and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)