Machine Learning Applications on Neuroimaging for Diagnosis and Prognosis of Epilepsy: A Review

Machine learning is playing an increasingly important role in medical image analysis, spawning new advances in the clinical application of neuroimaging. There have been some reviews of machine learning and epilepsy before, but they mainly focused on electrophysiological signals such as electroencephalography(EEG) or stereo electroencephalography(SEEG), while ignoring the potential of neuroimaging in epilepsy research. Neuroimaging has its important advantages in confirming the range of epileptic region, which means a lot in presurgical evaluation and assessment after surgery. However, EEG is difficult to locate the epilepsy lesion region in the brain. In this review, we emphasize the interaction between neuroimaging and machine learning in the context of the epilepsy diagnosis and prognosis. We start with an overview of typical neuroimaging modalities used in epilepsy clinics, MRI, DTI, fMRI, and PET. Then, we introduce three approaches for applying machine learning methods to neuroimaging data: i) the two-step compositional approach combining feature engineering and machine learning classifiers, ii) the end-to-end approach, which is usually toward deep learning, and iii) the hybrid approach using the advantages of the two methods. Subsequently, the application of machine learning on epilepsy neuroimaging, such as segmentation, localization and lateralization tasks, as well as tasks directly related to diagnosis and prognosis are introduced in detail. Finally, we discuss the current achievements, challenges, and potential future directions in this field, hoping to pave the way for computer-aided diagnosis and prognosis of epilepsy.