Cargando…
Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis
The diagnosis of multiple sclerosis (MS) is usually based on clinical symptoms and signs of damage to the central nervous system, which is assessed using magnetic resonance imaging. The correct interpretation of these data requires excellent clinical expertise and experience. Deep neural networks ai...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7775402/ https://www.ncbi.nlm.nih.gov/pubmed/33390890 http://dx.doi.org/10.3389/fnins.2020.609468 |
_version_ | 1783630458371702784 |
---|---|
author | Lopatina, Alina Ropele, Stefan Sibgatulin, Renat Reichenbach, Jürgen R. Güllmar, Daniel |
author_facet | Lopatina, Alina Ropele, Stefan Sibgatulin, Renat Reichenbach, Jürgen R. Güllmar, Daniel |
author_sort | Lopatina, Alina |
collection | PubMed |
description | The diagnosis of multiple sclerosis (MS) is usually based on clinical symptoms and signs of damage to the central nervous system, which is assessed using magnetic resonance imaging. The correct interpretation of these data requires excellent clinical expertise and experience. Deep neural networks aim to assist clinicians in identifying MS using imaging data. However, before such networks can be integrated into clinical workflow, it is crucial to understand their classification strategy. In this study, we propose to use a convolutional neural network to identify MS patients in combination with attribution algorithms to investigate the classification decisions. The network was trained using images acquired with susceptibility-weighted imaging (SWI), which is known to be sensitive to the presence of paramagnetic iron components and is routinely applied in imaging protocols for MS patients. Different attribution algorithms were used to the trained network resulting in heatmaps visualizing the contribution of each input voxel to the classification decision. Based on the quantitative image perturbation method, we selected DeepLIFT heatmaps for further investigation. Single-subject analysis revealed veins and adjacent voxels as signs for MS, while the population-based study revealed relevant brain areas common to most subjects in a class. This pattern was found to be stable across different echo times and also for a multi-echo trained network. Intensity analysis of the relevant voxels revealed a group difference, which was found to be primarily based on the T1w magnitude images, which are part of the SWI calculation. This difference was not observed in the phase mask data. |
format | Online Article Text |
id | pubmed-7775402 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-77754022021-01-02 Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis Lopatina, Alina Ropele, Stefan Sibgatulin, Renat Reichenbach, Jürgen R. Güllmar, Daniel Front Neurosci Neuroscience The diagnosis of multiple sclerosis (MS) is usually based on clinical symptoms and signs of damage to the central nervous system, which is assessed using magnetic resonance imaging. The correct interpretation of these data requires excellent clinical expertise and experience. Deep neural networks aim to assist clinicians in identifying MS using imaging data. However, before such networks can be integrated into clinical workflow, it is crucial to understand their classification strategy. In this study, we propose to use a convolutional neural network to identify MS patients in combination with attribution algorithms to investigate the classification decisions. The network was trained using images acquired with susceptibility-weighted imaging (SWI), which is known to be sensitive to the presence of paramagnetic iron components and is routinely applied in imaging protocols for MS patients. Different attribution algorithms were used to the trained network resulting in heatmaps visualizing the contribution of each input voxel to the classification decision. Based on the quantitative image perturbation method, we selected DeepLIFT heatmaps for further investigation. Single-subject analysis revealed veins and adjacent voxels as signs for MS, while the population-based study revealed relevant brain areas common to most subjects in a class. This pattern was found to be stable across different echo times and also for a multi-echo trained network. Intensity analysis of the relevant voxels revealed a group difference, which was found to be primarily based on the T1w magnitude images, which are part of the SWI calculation. This difference was not observed in the phase mask data. Frontiers Media S.A. 2020-12-18 /pmc/articles/PMC7775402/ /pubmed/33390890 http://dx.doi.org/10.3389/fnins.2020.609468 Text en Copyright © 2020 Lopatina, Ropele, Sibgatulin, Reichenbach and Güllmar. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Lopatina, Alina Ropele, Stefan Sibgatulin, Renat Reichenbach, Jürgen R. Güllmar, Daniel Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title | Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title_full | Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title_fullStr | Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title_full_unstemmed | Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title_short | Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis |
title_sort | investigation of deep-learning-driven identification of multiple sclerosis patients based on susceptibility-weighted images using relevance analysis |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7775402/ https://www.ncbi.nlm.nih.gov/pubmed/33390890 http://dx.doi.org/10.3389/fnins.2020.609468 |
work_keys_str_mv | AT lopatinaalina investigationofdeeplearningdrivenidentificationofmultiplesclerosispatientsbasedonsusceptibilityweightedimagesusingrelevanceanalysis AT ropelestefan investigationofdeeplearningdrivenidentificationofmultiplesclerosispatientsbasedonsusceptibilityweightedimagesusingrelevanceanalysis AT sibgatulinrenat investigationofdeeplearningdrivenidentificationofmultiplesclerosispatientsbasedonsusceptibilityweightedimagesusingrelevanceanalysis AT reichenbachjurgenr investigationofdeeplearningdrivenidentificationofmultiplesclerosispatientsbasedonsusceptibilityweightedimagesusingrelevanceanalysis AT gullmardaniel investigationofdeeplearningdrivenidentificationofmultiplesclerosispatientsbasedonsusceptibilityweightedimagesusingrelevanceanalysis |