Article Preview
Top2. Research Status
Introduction to the research of image processing and artificial intelligence for medical diagnosis, For brain diseases,Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy(Jiang, Wu, Deng et al, 2017).To address these two challenges, a new epileptic EEG recognition method based on a multiview learning framework and fuzzy system modeling is proposed(Jiang, Deng, Chung et al, 2017).Application in disease diagnosis,Clustering with multiview data is becoming a hot topic in data mining, pattern recognition, and machine learning(Jiang et al., 2015).Transfer learning improves learning in the target domain by leveraging knowledge from related domains. Given some target data, the performance of transfer learning is determined by the degree of relevance between the source and target domains(Jiang et al., 2020).Some articles introduce a distributed multitask fuzzy c-means (MT-FCM) clustering algorithm for MR brain image segmentation that can extract knowledge common among different clustering tasks(Jiang et al., 2019).Principles of disease image detection: 1. Plane measurement The MR1 plane measurement method is used to measure the brain structure of patients with Alzheimer's disease(Sudworth et al., 2006). Compared with three-dimensional volume measurement, it is simpler, more convenient, faster, and has more extensive clinical applications. DeLeon et al. performed MRI scans on cadaver specimens of patients with Alzheimer's disease and found that the changes in the width of the temporal horn of the lateral ventricle can reflect the degree of hippocampal atrophy to a certain extent, and can also understand the degree of atrophy of the medial temporal lobe and the entire temporal lobe(Shuwei, 2011). Tanabe et al. used MRI to measure the brain parenchyma, gray matter, brain sulcus, etc., and found that all indicators between the dementia group and the normal elderly control group have a large overlap. Therefore, the sulcus measurement results can indicate the presence of dementia, but cannot accurately distinguish Alzheimer's disease patients and normal elderly. In view of this, it may be more appropriate to choose hippocampal structure and lateral ventricle temporal horn width as identification indicators(Sarojadevi, 2014). Therefore, it is currently more inclined to use MRI three-dimensional measurement methods to study the changes in brain structure of Alzheimer's disease patients. In patients with Alzheimer's disease, functional magnetic resonance imaging scan signal intensity increases and the range expands when some brain areas of Alzheimer's disease undergo cognitive activation(Nedz’ved & Ablameiko, 1998). Functional magnetic resonance imaging studies have found that in patients with mild cognitive impairment who develop Alzheimer’s disease, the right hippocampus has a large range of brain gyrus increased signal strength during the coding phase of the memory test, which may be Alzheimer’s Pathological compensatory response in patients with Zheimer's disease. Johnson et al. conducted a cognitive activation test on patients with Alzheimer's disease and found that the greater the atrophy of the left inferior frontal gyrus, the larger the activated area and the stronger the signal(Shih, 2009). In this regard, he believes that for patients with memory problems, part of the surviving normal nerve tissue can replace the tissue that has been diseased, so that the signal strength of the activated brain area increases and the range expands.