Examining the Foundation: An Algorithmic Structure for Detecting Bone Fractures
Author(s): Aditya Achawale1, Prof.Yogita More2, Pratik Ghuge3, Ganesh Zole4, Ashwin Bnkar5
Affiliation: 1,2,3,4,5Department of computer science engineering 1,2,3,4,5SRCOE, Pune, India
Page No: 10-13-
Volume issue & Publishing Year: Volume 1 Issue 3,Aug-2024
Journal: International Journal of Modern Engineering and Management | IJMEM
ISSN NO: 3048-8230
DOI:
Abstract:
This paper explores advanced algorithmic frameworks for detecting bone fractures, with a focus on their practicality and effectiveness. By drawing from synthetic aperture radar technology, the study examines Microwave Imaging (MWI) as a non-ionizing method for diagnosing superficial bone fractures. This is particularly relevant in emergency settings where traditional X-rays are either unavailable or unsuitable, such as in cases involving pregnant women or children. The proposed method uses a single Vivaldi antenna operating within the 8.3-11.1 GHz frequency range to scan the bones. It collects scattered electromagnetic fields and reconstructs images using the Kirchhoff migration algorithm. A key advantage of this technique is its simplicity in air, eliminating the need for immersion in liquids. To improve diagnostic accuracy, Singular Value Decomposition (SVD) is applied to remove artifacts from skin and background. The technique was tested through simulations and experiments with multilayer phantoms and ex-vivo animal bones. The results indicate that the method can swiftly and accurately detect small transverse bone fractures, as narrow as 1 mm and 13 mm in depth, even when covered by a 2 mm thick layer of skin. This demonstrates the method's capability to overcome existing limitations in medical imaging.
Keywords:
Microwave Imaging, Non-Ionizing Diagnosis, Superficial Bone Fractures, Synthetic Aperture Radar, Singular Value Decomposition (SVD), Bone Morphology
Reference:
[1] J. Gao, ‘ ‘Restudy of the name and usage of the bone tallies unearthed from the han period Chang’an city-site,’ ’ HuaxiaArchaeol., no. 3, pp. 109–113, Sep. 2011.
[2] C. N. Tu, G. Wang, J. Tian, H. J. Li, and T. Li, ‘ ‘Research on classification algorithm of oracle bone inscriptions based on deep learning,’ ’ Modern Comput., vol. 27, no. 26, pp. 67–72, Sep. 2021.
[3] Y. H. Yu, H. B. Zhang, X. Li, J. J. Kou, K. Li, G. H. Geng, and M. Q. Zhou, ‘ ‘Depth classification model of Qin terracotta fragments based on data augmentation,’ ’ Laser Optoelectronics Prog., vol. 59, no. 18, pp. 111–120, Aug. 2022..
[4] J. N. Feng, Q. Zhou, R. R. Zhang, Y. Wang, and H. J. Luo, ‘ ‘Intelligent chronological study of chinese ancient ceramics based on convolutional neural networks,’ ’ J. Ceram., vol. 43, no. 1, pp. 145–152, Feb. 2022.
[5] J. Wang, Y. Gao, and J. Shi, ‘ ‘Scene classification of optical high-resolution remote sensing images using vision transformer and graph convolutional network,’ ’ Acta Photon. Sinica, vol. 50, no. 11, 2021, Art. no. 1128002.
[6] M. Caron, H. Touvron, I. Misra, H. Jegou, J. Mairal, P. Bojanowski, and A. Joulin, ‘ ‘Emerging properties in self-supervised vision transformers,’ ’ in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2021, pp. 9650–9660.