1
|
Yang L, Peng B, Gao W, A R, Liu Y, Liang J, Zhu M, Hu H, Lu Z, Pang C, Dai Y, Sun Y. Automated detection of MRI-negative temporal lobe epilepsy with ROI-based morphometric features and machine learning. Front Neurol 2024; 15:1323623. [PMID: 38356879 PMCID: PMC10864571 DOI: 10.3389/fneur.2024.1323623] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Accepted: 01/09/2024] [Indexed: 02/16/2024] Open
Abstract
Objective Temporal lobe epilepsy (TLE) predominantly originates from the anteromedial basal region of the temporal lobe, and its prognosis is generally favorable following surgical intervention. However, TLE often appears negative in magnetic resonance imaging (MRI), making it difficult to quantitatively diagnose the condition solely based on clinical symptoms. There is a pressing need for a quantitative, automated method for detecting TLE. Methods This study employed MRI scans and clinical data from 51 retrospective epilepsy cases, dividing them into two groups: 34 patients in TLE group and 17 patients in non-TLE group. The criteria for defining the TLE group were successful surgical removal of the epileptogenic zone in the temporal lobe and a favorable postoperative prognosis. A standard procedure was used for normalization, brain extraction, tissue segmentation, regional brain partitioning, and cortical reconstruction of T1 structural MRI images. Morphometric features such as gray matter volume, cortical thickness, and surface area were extracted from a total of 20 temporal lobe regions in both hemispheres. Support vector machine (SVM), extreme learning machine (ELM), and cmcRVFL+ classifiers were employed for model training and validated using 10-fold cross-validation. Results The results demonstrated that employing ELM classifiers in conjunction with specific temporal lobe gray matter volume features led to a better identification of TLE. The classification accuracy was 92.79%, with an area under the curve (AUC) value of 0.8019. Conclusion The method proposed in this study can significantly assist in the preoperative identification of TLE patients. By employing this method, TLE can be included in surgical criteria, which could alleviate patient symptoms and improve prognosis, thereby bearing substantial clinical significance.
Collapse
Affiliation(s)
- Lin Yang
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Bo Peng
- Suzhou Institute of Biomedical Engineering, Chinese Academy of Sciences, Suzhou, China
- Jinan Guoke Medical Engineering Technology Development Co., Ltd, Jinan, China
| | - Wei Gao
- Department of Neurosurgery, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Rixi A
- School of Life Science and Technology, Changchun University of Science and Technology, Changchun, China
| | - Yan Liu
- Suzhou Institute of Biomedical Engineering, Chinese Academy of Sciences, Suzhou, China
- Jinan Guoke Medical Engineering Technology Development Co., Ltd, Jinan, China
| | - Jiawei Liang
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
- International Laboratory for Children’s Medical Imaging Research, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
| | - Mo Zhu
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Haiyang Hu
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Zuhong Lu
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
| | - Chunying Pang
- School of Life Science and Technology, Changchun University of Science and Technology, Changchun, China
| | - Yakang Dai
- Suzhou Institute of Biomedical Engineering, Chinese Academy of Sciences, Suzhou, China
- Jinan Guoke Medical Engineering Technology Development Co., Ltd, Jinan, China
| | - Yu Sun
- International Laboratory for Children’s Medical Imaging Research, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
- Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, United Kingdom
| |
Collapse
|
2
|
Yao S, Kendrick KM. Reduced homotopic interhemispheric connectivity in psychiatric disorders: evidence for both transdiagnostic and disorder specific features. PSYCHORADIOLOGY 2022; 2:129-145. [PMID: 38665271 PMCID: PMC11003433 DOI: 10.1093/psyrad/kkac016] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 10/24/2022] [Accepted: 10/28/2022] [Indexed: 04/28/2024]
Abstract
There is considerable interest in the significance of structural and functional connections between the two brain hemispheres in terms of both normal function and in relation to psychiatric disorders. In recent years, many studies have used voxel mirrored homotopic connectivity analysis of resting state data to investigate the importance of connectivity between homotopic regions in the brain hemispheres in a range of neuropsychiatric disorders. The current review summarizes findings from these voxel mirrored homotopic connectivity studies in individuals with autism spectrum disorder, addiction, attention deficit hyperactivity disorder, anxiety and depression disorders, and schizophrenia, as well as disorders such as Alzheimer's disease, mild cognitive impairment, epilepsy, and insomnia. Overall, other than attention deficit hyperactivity disorder, studies across psychiatric disorders report decreased homotopic resting state functional connectivity in the default mode, attention, salience, sensorimotor, social cognition, visual recognition, primary visual processing, and reward networks, which are often associated with symptom severity and/or illness onset/duration. Decreased homotopic resting state functional connectivity may therefore represent a transdiagnostic marker for general psychopathology. In terms of disorder specificity, the extensive decreases in homotopic resting state functional connectivity in autism differ markedly from attention deficit hyperactivity disorder, despite both occurring during early childhood and showing extensive co-morbidity. A pattern of more posterior than anterior regions showing reductions in schizophrenia is also distinctive. Going forward, more studies are needed to elucidate the functions of these homotopic functional connections in both health and disorder and focusing on associations with general psychopathology, and not only on disorder specific symptoms.
Collapse
Affiliation(s)
- Shuxia Yao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Keith M Kendrick
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu 611731, China
| |
Collapse
|