Training Artificial Neural Networks to Detect Multiple Sclerosis Lesions Using Granulometric Data from Preprocessed Magnetic Resonance Images with Morphological Transformations
Authors:
- Edgar Rafael Ponce de Leon-SanchezELEdgar Rafael Ponce de Leon-Sanchez
- Jorge Domingo Mendiola-SantibañezJorge Domingo Mendiola-Santibañez
- Omar Arturo Dominguez-RamirezOmar Arturo Dominguez-Ramirez
- Ana Marcela Herrera-NavarroAHAna Marcela Herrera-Navarro
- Alberto Vazquez-CervantesAVAlberto Vazquez-Cervantes
- Hugo Jimenez-HernandezHugo Jimenez-Hernandez
- Diana Margarita Cordova-EsparzaDiana Margarita Cordova-Esparza
- María de Los Angeles Cuán HernándezMHMaría de Los Angeles Cuán Hernández
- Horacio Senties-MadridHSHoracio Senties-Madrid
Open Access
- 31 August 2024
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 12 (9) , 145
Abstract
The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool used for diagnosing MS, understanding the course of the disease, and analyzing the effects of treatments. However, undesirable components may appear during the generation of MRI scans, such as noise or intensity variations. Mathematical morphology (MM) is a powerful image analysis technique that helps to filter the image and extract relevant structures. Granulometry is an image measurement tool for measuring MM that determines the size distribution of objects in an image without explicitly segmenting each object. While several methods have been proposed for the automatic segmentation of MS lesions in MRI scans, in some cases, only simple data preprocessing, such as image resizing to standardize the input dimensions, has been performed before the algorithm training. Therefore, this paper proposes an MRI preprocessing algorithm capable of performing elementary morphological transformations in brain images of MS patients and healthy individuals in order to delete undesirable components and extract the relevant structures such as MS lesions. Also, the algorithm computes the granulometry in MRI scans to describe the size qualities of lesions. Using this algorithm, we trained two artificial neural networks (ANNs) to predict MS diagnoses. By computing the differences in granulometry measurements between an image with MS lesions and a reference image (without lesions), we determined the size characterization of the lesions. Then, the ANNs were evaluated with the validation set, and the performance results (test accuracy = 0.9753; cross-entropy loss = 0.0247) show that the proposed algorithm can support specialists in making decisions to diagnose MS and estimating the disease progress based on granulometry values.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Current approaches in glioblastoma multiforme immunotherapyClinical and Translational Oncology, 2024
- Learning with limited annotations: A survey on deep semi-supervised learning for medical image segmentationComputers in Biology and Medicine, 2023
- An entropy-based membership approach on type-II fuzzy set (EMT2FCM) for biomedical image segmentationEngineering Applications of Artificial Intelligence, 2023
- Boosting multiple sclerosis lesion segmentation through attention mechanismComputers in Biology and Medicine, 2023
- Delve into Multiple Sclerosis (MS) lesion exploration: A modified attention U-Net for MS lesion segmentation in Brain MRIComputers in Biology and Medicine, 2022
- Factors affecting adherence to disease-modifying therapies in multiple sclerosis: systematic reviewJournal of Neurology, 2021
- MPRAGE to MP2RAGE UNI translation via generative adversarial network improves the automatic tissue and lesion segmentation in multiple sclerosis patientsComputers in Biology and Medicine, 2021
- MicroRNA expression classification for pediatric multiple sclerosis identificationJournal of Ambient Intelligence and Humanized Computing, 2021
- Multiple sclerosis segmentation method in magnetic resonance imaging using fuzzy connectedness, binarization, mathematical morphology, and 3D reconstructionResearch on Biomedical Engineering, 2020
- Revised diagnostic criteria of multiple sclerosisAutoimmunity Reviews, 2014