Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm
Introduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong associat...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-02-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2021.613967/full |
| _version_ | 1818877862901448704 |
|---|---|
| author | Juan Pablo Princich Juan Pablo Princich Patricio Andres Donnelly-Kehoe Alvaro Deleglise Mariana Nahir Vallejo-Azar Guido Orlando Pascariello Pablo Seoane Pablo Seoane Jose Gabriel Veron Do Santos Santiago Collavini Santiago Collavini Santiago Collavini Alejandro Hugo Nasimbera Alejandro Hugo Nasimbera Silvia Kochen |
| author_facet | Juan Pablo Princich Juan Pablo Princich Patricio Andres Donnelly-Kehoe Alvaro Deleglise Mariana Nahir Vallejo-Azar Guido Orlando Pascariello Pablo Seoane Pablo Seoane Jose Gabriel Veron Do Santos Santiago Collavini Santiago Collavini Santiago Collavini Alejandro Hugo Nasimbera Alejandro Hugo Nasimbera Silvia Kochen |
| author_sort | Juan Pablo Princich |
| collection | DOAJ |
| description | Introduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong association between severity of histopathological anomalies and hippocampal volumes was reported using MR volumetry with a higher diagnostic yield than visual examination alone. Interpretation of volumetry results is challenging due to inherent methodological differences and to the reported variability of hippocampal volume. Furthermore, normal morphometric differences are recognized in diverse populations that may need consideration. To address this concern, we highlighted procedural discrepancies including atlas definition and computation of total intracranial volume that may impact volumetry results. We aimed to quantify diagnostic performance and to propose reference values for hippocampal volume from two well-established techniques: FreeSurfer v.06 and volBrain-HIPS.Methods: Volumetry measures were calculated using clinical T1 MRI from a local population of 61 healthy controls and 57 epilepsy patients with confirmed unilateral hippocampal sclerosis. We further validated the results by a state-of-the-art machine learning classification algorithm (Random Forest) computing accuracy and feature relevance to distinguish between patients and controls. This validation process was performed using the FreeSurfer dataset alone, considering morphometric values not only from the hippocampus but also from additional non-hippocampal brain regions that could be potentially relevant for group classification. Mean reference values and 95% confidence intervals were calculated for left and right hippocampi along with hippocampal asymmetry degree to test diagnostic accuracy.Results: Both methods showed excellent classification performance (AUC:> 0.914) with noticeable differences in absolute (cm3) and normalized volumes. Hippocampal asymmetry was the most accurate discriminator from all estimates (AUC:1~0.97). Similar results were achieved in the validation test with an automatic classifier (AUC:>0.960), disclosing hippocampal structures as the most relevant features for group differentiation among other brain regions.Conclusion: We calculated reference volumetry values from two commonly used methods to accurately identify patients with temporal epilepsy and hippocampal sclerosis. Validation with an automatic classifier confirmed the principal role of the hippocampus and its subregions for diagnosis. |
| first_indexed | 2024-12-19T14:05:02Z |
| format | Article |
| id | doaj.art-1264f87304a84fb1817132f3b7c67848 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-12-19T14:05:02Z |
| publishDate | 2021-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-1264f87304a84fb1817132f3b7c678482022-12-21T20:18:20ZengFrontiers Media S.A.Frontiers in Neurology1664-22952021-02-011210.3389/fneur.2021.613967613967Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification AlgorithmJuan Pablo Princich0Juan Pablo Princich1Patricio Andres Donnelly-Kehoe2Alvaro Deleglise3Mariana Nahir Vallejo-Azar4Guido Orlando Pascariello5Pablo Seoane6Pablo Seoane7Jose Gabriel Veron Do Santos8Santiago Collavini9Santiago Collavini10Santiago Collavini11Alejandro Hugo Nasimbera12Alejandro Hugo Nasimbera13Silvia Kochen14ENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaHospital de Pediatría J.P Garrahan, Departamento de Neuroimágenes, Buenos Aires, ArgentinaCentro Internacional Franco Argentino de Ciencias de la Información y de Sistemas (CIFASIS) - Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Grupo de Procesamiento de Señales Multimedia - División Neuroimágenes, Universidad Nacional de Rosario, Rosario, ArgentinaInstituto de Fisiología y Biofísica B. Houssay (IFIBIO), Consejo Nacional de Investigaciones Científicas y Técnicas, Departamento de Fisiología y Biofísica, Universidad de Buenos Aires, Buenos Aires, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaCentro Internacional Franco Argentino de Ciencias de la Información y de Sistemas (CIFASIS) - Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Grupo de Procesamiento de Señales Multimedia - División Neuroimágenes, Universidad Nacional de Rosario, Rosario, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaHospital J.M Ramos Mejía, Centro de Epilepsia, Buenos Aires, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaInstituto de investigación en Electrónica, Control y Procesamiento de Señales (LEICI), Universidad Nacional de La Plata-Consejo Nacional de Investigaciones Científicas y Técnicas, La Plata, ArgentinaInstituto de Ingeniería y Agronomía, Universidad Nacional Arturo Jauretche, Florencio Varela, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaHospital J.M Ramos Mejía, Centro de Epilepsia, Buenos Aires, ArgentinaENyS (Estudios en Neurociencias y Sistemas Complejos), Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional Arturo Jauretche y Hospital El Cruce, Florencio Varela, ArgentinaIntroduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong association between severity of histopathological anomalies and hippocampal volumes was reported using MR volumetry with a higher diagnostic yield than visual examination alone. Interpretation of volumetry results is challenging due to inherent methodological differences and to the reported variability of hippocampal volume. Furthermore, normal morphometric differences are recognized in diverse populations that may need consideration. To address this concern, we highlighted procedural discrepancies including atlas definition and computation of total intracranial volume that may impact volumetry results. We aimed to quantify diagnostic performance and to propose reference values for hippocampal volume from two well-established techniques: FreeSurfer v.06 and volBrain-HIPS.Methods: Volumetry measures were calculated using clinical T1 MRI from a local population of 61 healthy controls and 57 epilepsy patients with confirmed unilateral hippocampal sclerosis. We further validated the results by a state-of-the-art machine learning classification algorithm (Random Forest) computing accuracy and feature relevance to distinguish between patients and controls. This validation process was performed using the FreeSurfer dataset alone, considering morphometric values not only from the hippocampus but also from additional non-hippocampal brain regions that could be potentially relevant for group classification. Mean reference values and 95% confidence intervals were calculated for left and right hippocampi along with hippocampal asymmetry degree to test diagnostic accuracy.Results: Both methods showed excellent classification performance (AUC:> 0.914) with noticeable differences in absolute (cm3) and normalized volumes. Hippocampal asymmetry was the most accurate discriminator from all estimates (AUC:1~0.97). Similar results were achieved in the validation test with an automatic classifier (AUC:>0.960), disclosing hippocampal structures as the most relevant features for group differentiation among other brain regions.Conclusion: We calculated reference volumetry values from two commonly used methods to accurately identify patients with temporal epilepsy and hippocampal sclerosis. Validation with an automatic classifier confirmed the principal role of the hippocampus and its subregions for diagnosis.https://www.frontiersin.org/articles/10.3389/fneur.2021.613967/fullepilepsyvolumetryhippocampal sclerosisrandom forest classifierMRI |
| spellingShingle | Juan Pablo Princich Juan Pablo Princich Patricio Andres Donnelly-Kehoe Alvaro Deleglise Mariana Nahir Vallejo-Azar Guido Orlando Pascariello Pablo Seoane Pablo Seoane Jose Gabriel Veron Do Santos Santiago Collavini Santiago Collavini Santiago Collavini Alejandro Hugo Nasimbera Alejandro Hugo Nasimbera Silvia Kochen Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm Frontiers in Neurology epilepsy volumetry hippocampal sclerosis random forest classifier MRI |
| title | Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm |
| title_full | Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm |
| title_fullStr | Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm |
| title_full_unstemmed | Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm |
| title_short | Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm |
| title_sort | diagnostic performance of mri volumetry in epilepsy patients with hippocampal sclerosis supported through a random forest automatic classification algorithm |
| topic | epilepsy volumetry hippocampal sclerosis random forest classifier MRI |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2021.613967/full |
| work_keys_str_mv | AT juanpabloprincich diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT juanpabloprincich diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT patricioandresdonnellykehoe diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT alvarodeleglise diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT mariananahirvallejoazar diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT guidoorlandopascariello diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT pabloseoane diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT pabloseoane diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT josegabrielverondosantos diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT santiagocollavini diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT santiagocollavini diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT santiagocollavini diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT alejandrohugonasimbera diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT alejandrohugonasimbera diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm AT silviakochen diagnosticperformanceofmrivolumetryinepilepsypatientswithhippocampalsclerosissupportedthrougharandomforestautomaticclassificationalgorithm |