Localization of Intervertebral Discs Using Deep-Learning and Region Growing Technique

DOI

10.2991/978-94-6463-196-8_8How to use a DOI?

Keywords

Spinal cord segmentation; IVD localization; Intervertebral Disc; Localization

Abstract

Detection and Marking of Intervertebral discs (IVD) of the spinal cord is relevant as it notably enables experts to diagnose spinal cord injury. Many of the experts from medical field do this task manually, therefore there may be risk of wrong labeling of in-vertebral disks and this job is tedious. There are several automated methods are already implemented for CT-SCAN images and MRI images as well. Most of the methods are not freely available and the existing methods fails if the image quality fluctuates. There is another factor that affects the localization go wrong when the algorithms for localization fails to hit discs or it has false positive detection. In this paper we adopted Fully Convolutional Network (FCN), Stacked Hourglass Network with Multi-level Attention Mechanism and region growing technique for vertebral disc localization and segmentation. Deep learning has been used to tackle with false positive detection with the help of pose estimation and semantic segmentation techniques. The accuracy of the results were compared by the ground truth pixel location against predicted pixels location. Spine generic public multi-center dataset was used to evaluate the proposed method.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sujata Satpute
AU  - Ramesh Manza
AU  - Ganesh Manza
AU  - Anjum Shaikh
PY  - 2023
DA  - 2023/08/10
TI  - Localization of Intervertebral Discs Using Deep-Learning and Region Growing Technique
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 88
EP  - 98
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_8
DO  - 10.2991/978-94-6463-196-8_8
ID  - Satpute2023
ER  -