Enhancing Precision in Multiple Sclerosis Lesion Segmentation: A U-Net Based Machine Learning Approach with Data Augmentation

41 Pages Posted: 4 Jan 2024

See all articles by Oezdemir Cetin

Oezdemir Cetin

Technical University of Darmstadt

Berkay Canel

Technical University of Darmstadt

Gamze Dogali

Technical University of Darmstadt

Unal 'Zak' Sakoglu

University of Houston

Multiple version iconThere are 2 versions of this paper

Abstract

The segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) data presents a significant challenge due to the necessity for large volumes of training data and a sophisticated training process. Traditional MRI datasets often lack the extensive sample sizes required for effective training, necessitating the exploration of alternative methods for accurate segmentation. This study proposes a robust machine learning algorithm designed to identify MS lesions using both single-modal and multi-modal MRI data. The proposed algorithm employs Convolutional Neural Networks (CNNs) in the form of U-Net architecture, a renowned model for biomedical image segmentation. To address the issue of insufficient training data, data augmentation techniques have been implemented, enhancing the diversity and volume of the training set. The dataset for this study was created from MRI data of 20 subjects. The algorithm’s effectiveness was evaluated using the Dice score, a statistical tool that measures the similarity between two samples. The model achieved a Dice score of 0.7960 in the training set and 0.7912 in the test set, demonstrating its effectiveness in performing segmentation of MS from multi-modal MRI data. The predicted locations of MS lesions were compared with the corresponding layers of white matter, gray matter, and cerebrospinal fluid within the brain. This innovative approach aims to enhance the accuracy and efficiency of MS lesion segmentation, contributing to advancements in precision medicine and the overall understanding of Multiple Sclerosis.

Note:
Funding declaration: Oezdemir Cetin is supported by the Alexander von Humboldt Foundation and the Hessian State Ministry of Higher Education, Research, and the Arts. Unal Sakoglu is supported by UHCL.

Conflict of Interests: None.

Ethical Approval: The study was approved by the Sakarya University Faculty of Medicine ethics committee. Written informed consent was obtained from all participants.

Keywords: Multiple Sclerosis, multi-modal MRI, Segmentation

Suggested Citation

Cetin, Oezdemir and Canel, Berkay and Dogali, Gamze and Sakoglu, Unal 'Zak', Enhancing Precision in Multiple Sclerosis Lesion Segmentation: A U-Net Based Machine Learning Approach with Data Augmentation. Available at SSRN: https://ssrn.com/abstract=4668288 or http://dx.doi.org/10.2139/ssrn.4668288

Oezdemir Cetin (Contact Author)

Technical University of Darmstadt ( email )

Universitaets- und Landesbibliothek Darmstadt
Magdalenenstrasse 8
Darmstadt, D-64289
Germany

Berkay Canel

Technical University of Darmstadt ( email )

Universitaets- und Landesbibliothek Darmstadt
Magdalenenstrasse 8
Darmstadt, D-64289
Germany

Gamze Dogali

Technical University of Darmstadt ( email )

Universitaets- und Landesbibliothek Darmstadt
Magdalenenstrasse 8
Darmstadt, D-64289
Germany

Unal 'Zak' Sakoglu

University of Houston ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
44
Abstract Views
212
PlumX Metrics