Detection of Alzheimer's disease.

Alzheimer's disease is a neurodegenerative disease that affects the brain and cognitive function. AD has a debilitating impact on patients, their families and society, and causes immense distress to caregivers. Alzheimer's disease may have an autoimmune component, but its relevance is unknown. There is no simple model for screening for Alzheimer's disease because the diagnosis of Alzheimer's disease itself is complex. It usually requires expensive and sometimes invasive tests that are not widely available outside of highly specialized clinical settings. AD has different stages: Very mild dementia, mild and moderate. These stages are difficult to identify. This exacerbates very mild cases of dementia, leading to a complete loss of health, memory loss and the inability to carry out daily tasks without the help of others. Early detection of mild cases can help patients prescribe additional medical care to halt the progression of the disease and prevent brain damage. Recently, there has been a great deal of interest in applying Deep Learning (DL) for early detection of AD. Early detection of AD has always been a daunting challenge and one that computer researchers are constantly working on. Multimodal medical imaging information is widely used in computer-aided examination and diagnosis. A good example is that combining information from multimodal medical images enables a more accurate and comprehensive classification and diagnosis of the same Alzheimer's disease. In this study, a multi-scale pooling autoencoder and his RBF-SVM classifier were proposed for detecting Alzheimer's disease. In this study, two of his datasets are considered: Kaggle and ADNI records. The image first undergoes a modified optimal curvelet thresholding to remove noise in the image. Hybrid enhancement method octagonal histogram equalization with black and white stretching is applied to enhance the image. Segment the region using multi-scaling pooling residual autoencoder architecture. Biosensors are novel tools that may help predict the detection of multiple AD biomarkers as early as possible. Early detection is very important in the treatment process. However, early diagnosis of disease by psychological memory testing and neuroimaging has significant limitations. Various techniques have been developed so far to determine AD.  Enzyme Linked Immunosorbent Assay (ELISA)  Western-blot  Mass Spectrometry (MS)  Magnetic Resonance Imaging (MRI),  Position Emission Tomography (PET),  Immunohistochemistry (IHC). Most of the studies using graphene-based biosensors to identify AD biomarkers have been performed in vitro. Therefore, graphene-based biosensors can detect AD biomarkers in vivo and in complex clinical samples. Graphene-based nanosensors have recently received much attention for their accuracy and speed in detecting important AD biomarkers. Recently, new horizons have been opened by using aptamers as recognition units in graphene-based nanosensors.

Journal of Cholesterol and Heart Disease is an open access journal. The main objective of this journal is to cultivate and share clinical research and experimental work done by scientists, scholars.

Authors can submit their manuscripts as an email attachment to Disease@eurorendezvous.org

Kind Regards,
Journal Coordinator
Journal of Cholesterol and heart disease