Treffer: X-ray body Part Classification Using Custom CNN.

INTRODUCTION: This work represents a significant step forward by harnessing the power of deep learning to classify Xray images into distinct body parts. Over the years X-ray pictures were evaluated manually. OBJECTIVE: Our aim is to automate X-ray interpretation using deep learning techniques. METHOD: Leveraging cutting-edge frameworks such as FastAI and TensorFlow, a Convolutional Neural Network (CNN) has been meticulously trained on a dataset comprising DICOM images and their corresponding labels. RESULT: The results achieved by the model are indeed promising, as it demonstrates a remarkable ability to accurately identify various body parts. CNN shows 97.38% performance by compared with other classifiers. CONCLUSION: This innovation holds the potential to revolutionize medical diagnosis and treatment planning through the automation of image analysis, marking a substantial leap forward in the field of healthcare technology. [ABSTRACT FROM AUTHOR]

Copyright of EAI Endorsed Transactions on Pervasive Health & Technology is the property of EAI - European Alliance for Innovation n.o. 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.)