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

by   Jie Yuan, et al.

Machine learning is playing an increasing important role in medical image analysis, spawning new advances in neuroimaging clinical applications. However, previous work and reviews were mainly focused on the electrophysiological signals like EEG or SEEG; the potential of neuroimaging in epilepsy research has been largely overlooked despite of its wide use in clinical practices. In this review, we highlight the interactions between neuroimaging and machine learning in the context of the epilepsy diagnosis and prognosis. We firstly outline typical neuroimaging modalities used in epilepsy clinics, e.g MRI, DTI, fMRI and PET. We then introduce two approaches to apply machine learning methods to neuroimaging data: the two-step compositional approach which combines feature engineering and machine learning classifier, and the end-to-end approach which is usually toward deep learning. Later a detailed review on the machine learning tasks on epileptic images is presented, such as segmentation, localization and lateralization tasks, as well as the tasks directly related to the diagnosis and prognosis. In the end, we discuss current achievements, challenges, potential future directions in the field, with the hope to pave a way to computer-aided diagnosis and prognosis of epilepsy.


page 2

page 4

page 10


Machine Learning Methods for Histopathological Image Analysis: A Review

Histopathological images (HIs) are the gold standard for evaluating some...

Ten years of image analysis and machine learning competitions in dementia

Machine learning methods exploiting multi-parametric biomarkers, especia...

Machine learning techniques for the Schizophrenia diagnosis: A comprehensive review and future research directions

Schizophrenia (SCZ) is a brain disorder where different people experienc...

Machine Learning Applications for Therapeutic Tasks with Genomics Data

Thanks to the increasing availability of genomics and other biomedical d...

Risk of Training Diagnostic Algorithms on Data with Demographic Bias

One of the critical challenges in machine learning applications is to ha...

Computer-Aided Assessment of Catheters and Tubes on Radiographs: How Good is Artificial Intelligence for Assessment?

Catheters are the second most common abnormal finding on radiographs. Th...

Deep Learning in Cardiology

The medical field is creating large amount of data that physicians are u...

Please sign up or login with your details

Forgot password? Click here to reset