1
|
Wang X, Luo X, Pan H, Wang X, Xu S, Li H, Lin Z. Performance of hippocampal radiomics models based on T2-FLAIR images in mesial temporal lobe epilepsy with hippocampal sclerosis. Eur J Radiol 2023; 167:111082. [PMID: 37708677 DOI: 10.1016/j.ejrad.2023.111082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2023] [Revised: 07/14/2023] [Accepted: 09/04/2023] [Indexed: 09/16/2023]
Abstract
PURPOSE Preoperative identification of hippocampal sclerosis (HS) is crucial to successful surgery for mesial temporal lobe epilepsy (MTLE). We aimed to investigate the diagnostic performance of hippocampal radiomics models based on T2 fluid-attenuated inversion recovery (FLAIR) images in MTLE with HS. METHODS We analysed 210 cases, including 172 HS pathology-confirmed cases (100 magnetic resonance imaging [MRI]-positive cases [MRI + HS], 72 MRI-negative HS cases [MRI - HS]), and 38 healthy controls (HC). The hippocampus was delineated slice by slice on an oblique coronal plane by a T2-FLAIR sequence, perpendicular to the hippocampus's long axis, to obtain a three-dimensional region of interest. Radiomics were processed using Artificial Intelligence Kit software; logistic regression radiomics models were constructed. The model evaluation indexes included the area under the curve (AUC), accuracy, sensitivity, and specificity. RESULTS The respective AUC, accuracy, sensitivity, and specificity were 0.863, 81.4%, 78.0%, and 84.6% between the MRI - HS and HC groups in the training set and 0.855, 75.0%, 68.2%, and 81.8% in the test set; 0.975, 95.0%, 92.9%, and 98.0% between the MRI + HS and HC groups in the training set and 0.954, 88.7%, 90.0%, and 87.0% in the test set; and 0.912, 84.3%, 83.3%, and 86.5% between the MTLE and HC groups in the training set and 0.854, 79.7%, 80.8%, and 77.3% in the test set. The AUC values of the comparative radiomics models were > 0.85, indicating good diagnostic efficiency. CONCLUSION The hippocampal radiomics models based on T2-FLAIR images can help diagnose MTLE with HS. They can be used as biological markers for MTLE diagnosis.
Collapse
Affiliation(s)
- Xiaoyu Wang
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, Fujian Province, China; Department of Radiology, 900TH Hospital of Joint Logistics Support Force, Fuzhou, Fujian Province, China
| | - Xiaoting Luo
- Department of Radiology, the First Affiliated Hospital of Xiamen University, Xiamen, Fujian Province, China
| | - Haitao Pan
- Department of Radiology, Cangshan Branch of 900TH Hospital of Joint Logistics Support Force, Fuzhou, Fujian Province, China
| | - Xiaoyang Wang
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, Fujian Province, China; Department of Radiology, 900TH Hospital of Joint Logistics Support Force, Fuzhou, Fujian Province, China
| | - Shangwen Xu
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, Fujian Province, China; Department of Radiology, 900TH Hospital of Joint Logistics Support Force, Fuzhou, Fujian Province, China.
| | - Hui Li
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, Fujian Province, China; Department of Radiology, 900TH Hospital of Joint Logistics Support Force, Fuzhou, Fujian Province, China
| | - Zhiping Lin
- GE Healthcare, Guangzhou, Guangdong Province, China
| |
Collapse
|
2
|
Guo K, Wang J, Wang Z, Wang Y, Cui B, Zhao G, Lu J. Morphometric analysis program and quantitative positron emission tomography in presurgical localization in MRI-negative epilepsies: a simultaneous PET/MRI study. Eur J Nucl Med Mol Imaging 2021; 49:1930-1938. [PMID: 34939175 DOI: 10.1007/s00259-021-05657-w] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2021] [Accepted: 12/12/2021] [Indexed: 01/21/2023]
Abstract
PURPOSE To evaluate morphometric analysis program (MAP) and quantitative positron emission tomography (QPET) in epileptogenic zone (EZ) identification using a simultaneous positron emission tomography/magnetic resonance imaging (PET/MRI) system in MRI-negative epilepsies. METHODS Seventy-one localization-related MRI-negative epilepsies who underwent preoperative simultaneous PET/MRI examination and surgical resection were enrolled retrospectively. MAP was performed on a T1-weighted volumetric sequence, and QPET was analyzed using statistical parametric mapping (SPM) with comparison to age- and gender-matched normal controls. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of MAP, QPET, MAP + QPET, and MAP/QPET in EZ localization were assessed. The correlations between surgical outcome and modalities concordant with cortical resection were analyzed. RESULTS Forty-five (63.4%) patients had Engel I seizure outcomes. The sensitivity, specificity, PPV, and NPV of MAP were 64.4%, 69.2%, 78.3%, and 52.9%, respectively. The sensitivity, specificity, PPV, NPV of QPET were 73.3%, 65.4%, 78.6%, and 58.6%, respectively. MAP + QPET, defined as two tests concordant with cortical resection, had reduced sensitivity (53.3%) but increased specificity (88.5%) relative to individual tests. MAP/QPET, defined as one or both tests concordant with cortical resection, had increased sensitivity (86.7%) but reduced specificity (46.2%) relative to individual tests. The regions determined by MAP, QPET, MAP + QPET, or MAP/QPET concordant with cortical resection were significantly associated with the seizure-free outcome. CONCLUSION QPET has a superior sensitivity than MAP, while the combined MAP + QPET obtained from a simultaneous PET/MRI scanner may improve the specificity of the diagnostic tests in EZ localization coupled with the preferable surgical outcome in MRI-negative epilepsies.
Collapse
Affiliation(s)
- Kun Guo
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, 100053, China
| | - Jingjuan Wang
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, 100053, China
| | - Zhenming Wang
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, 100053, China
| | - Yihe Wang
- Department of Neurosurgery, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Bixiao Cui
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, 100053, China
| | - Guoguang Zhao
- Department of Neurosurgery, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Jie Lu
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, 100053, China. .,Key Laboratory of Magnetic Resonance Imaging and Brain Informatics, Beijing, China.
| |
Collapse
|
3
|
Mo J, Zhao B, Adler S, Zhang J, Shao X, Ma Y, Sang L, Hu W, Zhang C, Wang Y, Wang X, Liu C, Zhang K. Quantitative assessment of structural and functional changes in temporal lobe epilepsy with hippocampal sclerosis. Quant Imaging Med Surg 2021; 11:1782-1795. [PMID: 33936964 DOI: 10.21037/qims-20-624] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
Background Magnetic resonance imaging (MRI) changes in hippocampal sclerosis (HS) could be subtle in a significant proportion of mesial temporal lobe epilepsy (mTLE) patients. In this study, we aimed to document the structural and functional changes in the hippocampus and amygdala seen in HS patients. Methods Quantitative features of the hippocampus and amygdala were extracted from structural MRI data in 66 mTLE patients and 28 controls. Structural covariance analysis was undertaken using volumetric data from the amygdala and hippocampus. Functional connectivity (FC) measured using resting intracranial electroencephalography (EEG) was analyzed in 22 HS patients and 16 non-HS disease controls. Results Hippocampal atrophy was present in both MRI-positive and MRI-negative HS groups (Mann-Whitney U: 7.61, P<0.01; Mann-Whitney U: 6.51, P<0.01). Amygdala volumes were decreased in the patient group (Mann-Whitney U: 2.92, P<0.05), especially in MRI-negative HS patients (Mann-Whitney U: 2.75, P<0.05). The structural covariance analysis showed the normalized volumes of the amygdala and hippocampus were tightly coupled in both controls and HS patients (ρSpearman =0.72, P<0.01). FC analysis indicated that HS patients had significantly increased connectivity (Student's t: 2.58, P=0.03) within the hippocampus but decreased connectivity between the hippocampus and amygdala (Student's t: 3.33, P=0.01), particularly for MRI-negative HS patients. Conclusions Quantitative structural changes, including hippocampal atrophy and temporal pole blurring, are present in both MRI-positive and MRI-negative HS patients, suggesting the potential usefulness of incorporating quantitative analyses into clinical practice. HS is characterized by increased intra-hippocampal EEG synchronization and decreased coupling between the hippocampus and amygdala.
Collapse
Affiliation(s)
- Jiajie Mo
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Baotian Zhao
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Sophie Adler
- Developmental Neurosciences, UCL Great Ormond Street Institute of Child Health, University College London, London, UK
| | - Jianguo Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Xiaoqiu Shao
- China National Clinical Research Center for Neurological Diseases, Beijing, China.,Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Yanshan Ma
- Department of Neurosurgery, Beijing Fengtai Hospital, Beijing, China
| | - Lin Sang
- Department of Neurosurgery, Beijing Fengtai Hospital, Beijing, China
| | - Wenhan Hu
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Chao Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Yao Wang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Xiu Wang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Chang Liu
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Kai Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| |
Collapse
|