AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis
Abstract Background Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial i...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2023-07-01
|
Series: | Insights into Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13244-023-01460-3 |
_version_ | 1797778807770316800 |
---|---|
author | Sarah Schlaeger Suprosanna Shit Paul Eichinger Marco Hamann Roland Opfer Julia Krüger Michael Dieckmeyer Simon Schön Mark Mühlau Claus Zimmer Jan S. Kirschke Benedikt Wiestler Dennis M. Hedderich |
author_facet | Sarah Schlaeger Suprosanna Shit Paul Eichinger Marco Hamann Roland Opfer Julia Krüger Michael Dieckmeyer Simon Schön Mark Mühlau Claus Zimmer Jan S. Kirschke Benedikt Wiestler Dennis M. Hedderich |
author_sort | Sarah Schlaeger |
collection | DOAJ |
description | Abstract Background Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare. Methods A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level. Results On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen’s kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05). Conclusions AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients. Critical relevance statement Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions. Graphical Abstract |
first_indexed | 2024-03-12T23:22:53Z |
format | Article |
id | doaj.art-02a50acf4dff45a29a2cdd6df8c4edea |
institution | Directory Open Access Journal |
issn | 1869-4101 |
language | English |
last_indexed | 2024-03-12T23:22:53Z |
publishDate | 2023-07-01 |
publisher | SpringerOpen |
record_format | Article |
series | Insights into Imaging |
spelling | doaj.art-02a50acf4dff45a29a2cdd6df8c4edea2023-07-16T11:18:59ZengSpringerOpenInsights into Imaging1869-41012023-07-0114111110.1186/s13244-023-01460-3AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosisSarah Schlaeger0Suprosanna Shit1Paul Eichinger2Marco Hamann3Roland Opfer4Julia Krüger5Michael Dieckmeyer6Simon Schön7Mark Mühlau8Claus Zimmer9Jan S. Kirschke10Benedikt Wiestler11Dennis M. Hedderich12Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munichjung diagnostics GmbHjung diagnostics GmbHjung diagnostics GmbHDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Neurology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of MunichAbstract Background Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare. Methods A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level. Results On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen’s kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05). Conclusions AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients. Critical relevance statement Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions. Graphical Abstracthttps://doi.org/10.1186/s13244-023-01460-3Magnetic resonance imagingMultiple sclerosisContrast-enhancing lesionsArtificial intelligenceClinical decision support |
spellingShingle | Sarah Schlaeger Suprosanna Shit Paul Eichinger Marco Hamann Roland Opfer Julia Krüger Michael Dieckmeyer Simon Schön Mark Mühlau Claus Zimmer Jan S. Kirschke Benedikt Wiestler Dennis M. Hedderich AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis Insights into Imaging Magnetic resonance imaging Multiple sclerosis Contrast-enhancing lesions Artificial intelligence Clinical decision support |
title | AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis |
title_full | AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis |
title_fullStr | AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis |
title_full_unstemmed | AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis |
title_short | AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis |
title_sort | ai based detection of contrast enhancing mri lesions in patients with multiple sclerosis |
topic | Magnetic resonance imaging Multiple sclerosis Contrast-enhancing lesions Artificial intelligence Clinical decision support |
url | https://doi.org/10.1186/s13244-023-01460-3 |
work_keys_str_mv | AT sarahschlaeger aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT suprosannashit aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT pauleichinger aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT marcohamann aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT rolandopfer aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT juliakruger aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT michaeldieckmeyer aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT simonschon aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT markmuhlau aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT clauszimmer aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT janskirschke aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT benediktwiestler aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis AT dennismhedderich aibaseddetectionofcontrastenhancingmrilesionsinpatientswithmultiplesclerosis |