Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features
Objective: To automatically detect focal cortical dysplasia (FCD) lesion by combining quantitative multimodal surface-based features with machine learning and to assess its clinical value.Methods: Neuroimaging data and clinical information for 74 participants (40 with histologically proven FCD type...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2018.01008/full |
| _version_ | 1811240295129415680 |
|---|---|
| author | Jia-Jie Mo Jian-Guo Zhang Wen-Ling Li Chao Chen Na-Jing Zhou Wen-Han Hu Chao Zhang Yao Wang Xiu Wang Chang Liu Bao-Tian Zhao Jun-Jian Zhou Kai Zhang |
| author_facet | Jia-Jie Mo Jian-Guo Zhang Wen-Ling Li Chao Chen Na-Jing Zhou Wen-Han Hu Chao Zhang Yao Wang Xiu Wang Chang Liu Bao-Tian Zhao Jun-Jian Zhou Kai Zhang |
| author_sort | Jia-Jie Mo |
| collection | DOAJ |
| description | Objective: To automatically detect focal cortical dysplasia (FCD) lesion by combining quantitative multimodal surface-based features with machine learning and to assess its clinical value.Methods: Neuroimaging data and clinical information for 74 participants (40 with histologically proven FCD type II) was retrospectively included. The morphology, intensity and function-based features characterizing FCD lesions were calculated vertex-wise on each cortical surface and fed to an artificial neural network. The classifier performance was quantitatively and qualitatively assessed by performing statistical analysis and conventional visual analysis.Results: The accuracy, sensitivity, specificity of the neural network classifier based on multimodal surface-based features were 70.5%, 70.0%, and 69.9%, respectively, which outperformed the unimodal classifier. There was no significant difference in the detection rate of FCD subtypes (Pearson’s Chi-Square = 0.001, p = 0.970). Cohen’s kappa score between automated detection outcomes and post-surgical resection region was 0.385 (considered as fair).Conclusion: Automated machine learning with multimodal surface features can provide objective and intelligent detection of FCD lesion in pre-surgical evaluation and can assist the surgical strategy. Furthermore, the optimal parameters, appropriate surface features and efficient algorithm are worth exploring. |
| first_indexed | 2024-04-12T13:17:40Z |
| format | Article |
| id | doaj.art-a6e50051eff44f5fb3069a3e2937cbf6 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-12T13:17:40Z |
| publishDate | 2019-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-a6e50051eff44f5fb3069a3e2937cbf62022-12-22T03:31:39ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2019-01-011210.3389/fnins.2018.01008426559Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based FeaturesJia-Jie Mo0Jian-Guo Zhang1Wen-Ling Li2Chao Chen3Na-Jing Zhou4Wen-Han Hu5Chao Zhang6Yao Wang7Xiu Wang8Chang Liu9Bao-Tian Zhao10Jun-Jian Zhou11Kai Zhang12Department of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, The Second Hospital of Hebei Medical University, Shijiazhuang, ChinaKey Laboratory of Complex System Control Theory and Application, Tianjin University of Technology, Tianjin, ChinaDepartment of Pharmacology, Hebei Medical University, Shijiazhuang, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaObjective: To automatically detect focal cortical dysplasia (FCD) lesion by combining quantitative multimodal surface-based features with machine learning and to assess its clinical value.Methods: Neuroimaging data and clinical information for 74 participants (40 with histologically proven FCD type II) was retrospectively included. The morphology, intensity and function-based features characterizing FCD lesions were calculated vertex-wise on each cortical surface and fed to an artificial neural network. The classifier performance was quantitatively and qualitatively assessed by performing statistical analysis and conventional visual analysis.Results: The accuracy, sensitivity, specificity of the neural network classifier based on multimodal surface-based features were 70.5%, 70.0%, and 69.9%, respectively, which outperformed the unimodal classifier. There was no significant difference in the detection rate of FCD subtypes (Pearson’s Chi-Square = 0.001, p = 0.970). Cohen’s kappa score between automated detection outcomes and post-surgical resection region was 0.385 (considered as fair).Conclusion: Automated machine learning with multimodal surface features can provide objective and intelligent detection of FCD lesion in pre-surgical evaluation and can assist the surgical strategy. Furthermore, the optimal parameters, appropriate surface features and efficient algorithm are worth exploring.https://www.frontiersin.org/article/10.3389/fnins.2018.01008/fullfocal cortical dysplasiamachine learningmetabolicmorphologicalquantitative |
| spellingShingle | Jia-Jie Mo Jian-Guo Zhang Wen-Ling Li Chao Chen Na-Jing Zhou Wen-Han Hu Chao Zhang Yao Wang Xiu Wang Chang Liu Bao-Tian Zhao Jun-Jian Zhou Kai Zhang Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features Frontiers in Neuroscience focal cortical dysplasia machine learning metabolic morphological quantitative |
| title | Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features |
| title_full | Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features |
| title_fullStr | Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features |
| title_full_unstemmed | Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features |
| title_short | Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features |
| title_sort | clinical value of machine learning in the automated detection of focal cortical dysplasia using quantitative multimodal surface based features |
| topic | focal cortical dysplasia machine learning metabolic morphological quantitative |
| url | https://www.frontiersin.org/article/10.3389/fnins.2018.01008/full |
| work_keys_str_mv | AT jiajiemo clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT jianguozhang clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT wenlingli clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT chaochen clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT najingzhou clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT wenhanhu clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT chaozhang clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT yaowang clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT xiuwang clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT changliu clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT baotianzhao clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT junjianzhou clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures AT kaizhang clinicalvalueofmachinelearningintheautomateddetectionoffocalcorticaldysplasiausingquantitativemultimodalsurfacebasedfeatures |