Contents I. Introduction
Epilepsy is a chronic disease caused by the abnormal discharge of neurons in the brain, which leads to transient brain dysfunction. It often occurs in young adults and greatly affects the life of the patient if not treated in time [1]. Focal epilepsy with contact disruption is the most common complex partial form in adults. For the diagnosis of epilepsy, various modalities are used. The EEG is the reference examination to identify epileptic seizures and their types. However, EEG cannot detect the location and microstructural changes of epileptogenic foci. MRI provides structural images with good spatial resolution and is particularly useful for studying hippocampal anatomy in vivo and providing information about hippocampal sclerosis [3][4]. Positron emission tomography (PET) extracts functional and metabolic information and can be used for early diagnosis of the disease [5], which is a drug-resistant epilepsy, many cases of which require surgical treatment with precise diagnosis of the epileptogenic focus. In the case of temporal lobe epilepsy TLE, it has been shown that the majority of seizures can be predicted with high accuracy based on information from the hippocampus [3],[4],[7],[8]. The majority of patients display hippocampal sclerosis, which is characterized by neuronal loss [9]. Quantitative manual efforts necessitate the outline of individual coronal images and are time-consuming [3] [10]. Automated segmentation algorithms are thus of special interest.
