Related Experiment Video
Updated: Jul 6, 2025
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Cortical atrophy in early-stage patients with anti-NMDA receptor encephalitis: a machine-learning MRI study with
1Department of Neurology, West China Hospital of Sichuan University, 37 GuoXue Alley, Chengdu 610041, China.
Abstract:
Conventional brain magnetic resonance imaging (MRI) of anti-N-methyl-D-aspartate-receptor encephalitis (NMDARE) is non-specific, thus showing little differential diagnostic value, especially for MRI-negative patients. To characterize patterns of structural alterations and facilitate the diagnosis of MRI-negative NMDARE patients, we build two support vector machine models (NMDARE versus healthy controls [HC] model and NMDARE versus viral encephalitis [VE] model) based on radiomics features extracted from brain MRI. A total of 109 MRI-negative NMDARE patients in the acute phase, 108 HCs and 84 acute MRI-negative VE cases were included for training. Another 29 NMDARE patients, 28 HCs and 26 VE cases were included for validation. Eighty features discriminated NMDARE patients from HCs, with area under the receiver operating characteristic curve (AUC) of 0.963 in validation set. NMDARE patients presented with significantly lower thickness, area, and volume and higher mean curvature than HCs. Potential atrophy predominately presented in the frontal lobe (cumulative weight = 4.3725, contribution rate of 29.86%), and temporal lobe (cumulative weight = 2.573, contribution rate of 17.57%). The NMDARE versus VE model achieved certain diagnostic power, with AUC of 0.879 in validation set. Our research shows potential atrophy across the entire cerebral cortex in acute NMDARE patients, and MRI machine learning model has a potential to facilitate the diagnosis MRI-negative NMDARE.
Insights
Machine learning models applied to brain MRI radiomics can identify anti-N-methyl-D-aspartate-receptor encephalitis (NMDARE) in patients with normal imaging. This approach reveals cortical atrophy and aids in diagnosing NMDARE, even when MRI is initially negative.
Area of Science:
- Neuroimaging
- Artificial Intelligence in Medicine
- Neurology
Background:
- Conventional brain MRI for anti-N-methyl-D-aspartate-receptor encephalitis (NMDARE) lacks specificity, posing diagnostic challenges, particularly in MRI-negative cases.
- Identifying reliable imaging biomarkers is crucial for early and accurate diagnosis of NMDARE, especially when standard MRI findings are absent.
Purpose of the Study:
- To develop and validate machine learning models using radiomics features from brain MRI to differentiate NMDARE patients from healthy controls (HC) and viral encephalitis (VE) cases.
- To characterize structural alterations in MRI-negative NMDARE patients and assess the diagnostic potential of radiomics-based models.
Main Methods:
- Support vector machine (SVM) models were trained and validated using radiomics features extracted from brain MRI scans of NMDARE patients, HCs, and VE patients.
- The study included 109 NMDARE, 108 HC, and 84 VE cases for training, and 29 NMDARE, 28 HC, and 26 VE cases for validation.
- Eighty radiomics features were identified that distinguished NMDARE from HCs, and the NMDARE versus VE model was also evaluated.
Main Results:
- The NMDARE versus HC model achieved a high diagnostic performance with an area under the receiver operating characteristic curve (AUC) of 0.963 in the validation set.
- NMDARE patients exhibited significantly reduced cortical thickness, area, and volume, along with increased mean curvature compared to HCs, predominantly in the frontal and temporal lobes.
- The NMDARE versus VE model demonstrated diagnostic utility with an AUC of 0.879 in the validation set.
Conclusions:
- Radiomics analysis of brain MRI can detect subtle structural changes, such as widespread cortical atrophy, in acute NMDARE patients, even with initially normal MRI.
- Machine learning models utilizing radiomics features show significant potential to improve the diagnostic accuracy for MRI-negative NMDARE, aiding differential diagnosis from other encephalitides.
