Abstract
Bone age is an effective indicator for diagnosis of various diseases and determining the time of treatment. This radiological procedures are performed routinely by paediatrician and endocrinologistis to investigate developmental abnormalities, genetic disorders and metabolic complications. However, estimating bone age is one of the biggest challenge in the domain of radiodiagnosis as it is a time consuming procedure and require domain expertise. In this work, we have proposed metric learning technique on a small sized data set. Our model is efficiently performing multi-class classification to predict bone age by learning latent representation of images using an end to end structure. We found compelling evidence that using metric learning can yield state-of-the-art classification accuracy while reducing training data requirements to just a tenth of those employed by current approaches.The proposed model holds the promise to assist radiologist in estimating bone age with speed and accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Advanced Machine Vision Paradigms for Medical Image Analysis
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
