Secondary Logo

Journal Logo

Advanced Search

This month's editor's favorite is Shih and associates “Machine Learning Quantitative Analysis of FDG PET Images of Medial Temporal Lobe Epilepsy Patients​".  The authors presented a robust quantitative algorithm for the lateralization of epileptogenic foci by applying machine learning of 18F-FDG PET data in patients who underwent surgery for medial temporal lobe epilepsy (MTLE).

Three clinicians identified the side of MTLE epileptogenesis by visual inspection. The surgical side was accepted as the epileptogenic side. Two parcellation paradigms and corresponding atlases (Automated Anatomical Labeling and FreeSurfer (aparc + aseg) were used to extract the normalized PET uptake of the standard brain ROIs. The lateralization index of the MTLE-associated regions in either hemisphere was calculated and analyzed by machine learning to establish a model for classifying the side of MTLE epileptogenesis.

Ninety-three patients were retrospectively selected for training and validation, and another 11 patients were used for testing. The hit rate of lateralization by visual analysis was 75.3%. Among the 23 patients whose MTLE side of epileptogenesis was incorrectly determined or for whom no conclusion was reached by visual analysis, the Automated Anatomical Labeling and aparc + aseg programs parcellated the associated ROIs on the correctly lateralized MTLE side in 100.0% and 82.6% respectively. In the testing set, lateralization accuracy was 100% in the 2 paradigms.

The authors concluded that the visual analysis of 18F-FDG PET to lateralize MTLE epileptogenesis showed a lower hit rate compared with machine-assisted interpretation. While reviewing 18F-FDG PET images of MTLE patients, they propose that considering the regions associated with MTLE resulted in better performance than limiting analysis to hippocampal regions.

Current Issue

Show: