Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning
Background: Identifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have repor...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/6/632 |
| _version_ | 1827306588812083200 |
|---|---|
| author | Jason Uwaeze Ponnada A. Narayana Arash Kamali Vladimir Braverman Michael A. Jacobs Alireza Akhbardeh |
| author_facet | Jason Uwaeze Ponnada A. Narayana Arash Kamali Vladimir Braverman Michael A. Jacobs Alireza Akhbardeh |
| author_sort | Jason Uwaeze |
| collection | DOAJ |
| description | Background: Identifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have reported that repeated administration of GBCA results in the accumulation of Gd in tissues. In addition, GBCA administration increases health care costs. Thus, reducing or eliminating GBCA administration for active lesion detection is important for improved patient safety and reduced healthcare costs. Current state-of-the-art methods for identifying active lesions in brain MRI without GBCA administration utilize data-intensive deep learning methods. Objective: To implement nonlinear dimensionality reduction (NLDR) methods, locally linear embedding (LLE) and isometric feature mapping (Isomap), which are less data-intensive, for automatically identifying active lesions on brain MRI in MS patients, without the administration of contrast agents. Materials and Methods: Fluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images were included in the multiparametric MRI dataset used in this study. Subtracted pre- and post-contrast T1-weighted images were labeled by experts as active lesions (ground truth). Unsupervised methods, LLE and Isomap, were used to reconstruct multiparametric brain MR images into a single embedded image. Active lesions were identified on the embedded images and compared with ground truth lesions. The performance of NLDR methods was evaluated by calculating the Dice similarity (DS) index between the observed and identified active lesions in embedded images. Results: LLE and Isomap, were applied to 40 MS patients, achieving median DS scores of 0.74 ± 0.1 and 0.78 ± 0.09, respectively, outperforming current state-of-the-art methods. Conclusions: NLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool. |
| first_indexed | 2024-04-24T18:24:00Z |
| format | Article |
| id | doaj.art-ded521a7bac1498a9c50b90736904862 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-04-24T18:24:00Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-ded521a7bac1498a9c50b907369048622024-03-27T13:33:23ZengMDPI AGDiagnostics2075-44182024-03-0114663210.3390/diagnostics14060632Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine LearningJason Uwaeze0Ponnada A. Narayana1Arash Kamali2Vladimir Braverman3Michael A. Jacobs4Alireza Akhbardeh5Department of Computer Science, Rice University, Houston, TX 77005, USADepartment of Diagnostic and Interventional Imaging, The University of Texas Health Science Center at Houston, Houston, TX 77030, USADepartment of Diagnostic and Interventional Imaging, The University of Texas Health Science Center at Houston, Houston, TX 77030, USADepartment of Computer Science, Rice University, Houston, TX 77005, USADepartment of Computer Science, Rice University, Houston, TX 77005, USADepartment of Diagnostic and Interventional Imaging, The University of Texas Health Science Center at Houston, Houston, TX 77030, USABackground: Identifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have reported that repeated administration of GBCA results in the accumulation of Gd in tissues. In addition, GBCA administration increases health care costs. Thus, reducing or eliminating GBCA administration for active lesion detection is important for improved patient safety and reduced healthcare costs. Current state-of-the-art methods for identifying active lesions in brain MRI without GBCA administration utilize data-intensive deep learning methods. Objective: To implement nonlinear dimensionality reduction (NLDR) methods, locally linear embedding (LLE) and isometric feature mapping (Isomap), which are less data-intensive, for automatically identifying active lesions on brain MRI in MS patients, without the administration of contrast agents. Materials and Methods: Fluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images were included in the multiparametric MRI dataset used in this study. Subtracted pre- and post-contrast T1-weighted images were labeled by experts as active lesions (ground truth). Unsupervised methods, LLE and Isomap, were used to reconstruct multiparametric brain MR images into a single embedded image. Active lesions were identified on the embedded images and compared with ground truth lesions. The performance of NLDR methods was evaluated by calculating the Dice similarity (DS) index between the observed and identified active lesions in embedded images. Results: LLE and Isomap, were applied to 40 MS patients, achieving median DS scores of 0.74 ± 0.1 and 0.78 ± 0.09, respectively, outperforming current state-of-the-art methods. Conclusions: NLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool.https://www.mdpi.com/2075-4418/14/6/632multiple sclerosisdimensionality reductionmultiparametric MRIlesion segmentation |
| spellingShingle | Jason Uwaeze Ponnada A. Narayana Arash Kamali Vladimir Braverman Michael A. Jacobs Alireza Akhbardeh Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning Diagnostics multiple sclerosis dimensionality reduction multiparametric MRI lesion segmentation |
| title | Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning |
| title_full | Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning |
| title_fullStr | Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning |
| title_full_unstemmed | Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning |
| title_short | Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning |
| title_sort | automatic active lesion tracking in multiple sclerosis using unsupervised machine learning |
| topic | multiple sclerosis dimensionality reduction multiparametric MRI lesion segmentation |
| url | https://www.mdpi.com/2075-4418/14/6/632 |
| work_keys_str_mv | AT jasonuwaeze automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning AT ponnadaanarayana automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning AT arashkamali automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning AT vladimirbraverman automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning AT michaelajacobs automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning AT alirezaakhbardeh automaticactivelesiontrackinginmultiplesclerosisusingunsupervisedmachinelearning |