Friska, N and Sudirman, S Classification of Sagittal Lumbar Spine MRI for Lumbar Spinal Stenosis Detection using Transfer Learning of a Deep Convolutional Neural Network. In: IEEE Explore . (World Conference on Smart Trends in Systems, 29 July 2021 - 30 July 2021, London). (Accepted)

Preview

Text WS4 Conference (Accepted-Revised).pdf - Accepted Version Download (729kB) | Preview

Abstract

Analysis of sagittal lumbar spine MRI images remains an important step in automated detection and diagnosis of lumbar spinal stenosis. There are nu-merous algorithms proposed in the literature that can measure the condition of lumbar intervertebral discs through analysis of the lumbar spine in the sagittal view. However, these algorithms rely on using suitable sagittal im-ages as their inputs. Since an MRI data repository contains more than just these specific images, it is, therefore, necessary to employ an algorithm that can automatically select such images from the entire repository. In this pa-per, we demonstrate the application of an image classification method using deep convolutional neural networks for this purpose. Specifically, we use a pre-trained Inception-ResNet-v2 model and retrain it using two sets of T1-weighted and T2-weighted images. Through our experiment, we can con-clude that this method can reach a performance level of 0.91 and 0.93 on the T1 and T2 datasets, respectively when measured using the accuracy, preci-sion, recall, and f1-score metrics. We also show that the difference in per-formance between using the two modalities is statistically significant and us-ing T2-weighted images is preferred over using T1-weighted images.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > R Medicine (General)
Divisions:	Computer Science & Mathematics
Date Deposited:	16 Sep 2021 11:29
Last Modified:	13 Apr 2022 15:18
URI:	https://researchonline.ljmu.ac.uk/id/eprint/15500

View Item