Deep MRI Segmentation: A Convolutional Method Applied to Alzheimer Disease Detection

Abstract

The learning techniques have a particular need especially for the detection of invisible brain diseases. Learningbased methods rely on MRI medical images to reconstruct a solution for detecting aberrant values or areas in the human brain. In this article, we present a method that automatically performs segmentation of the brain to detect brain damage and diagnose Alzheimer's disease (AD). In order to take advantages of the benefits of 3D and reduce complexity and computational costs, we present a 2.5D method for locating brain inflammation and detecting their classes. Our proposed system is evaluated on a set of public data. Preliminary results indicate the reliability and effectiveness of our Alzheimer's Disease Detection System and demonstrate that our method is beyond current knowledge of Alzheimer's disease diagnosis.

Recommended implementation of quantitative susceptibility mapping for clinical research in the brain: A consensus of the ISMRM electro‐magnetic tissue properties study group

“…Alternatives to BET include standard template-based brain-extraction. 123 Deep learning-based segmentation, a rapidly developing field, [124][125][126][127] may also be considered.…”

An End-to-End 3D ConvLSTM-based Framework for Early Diagnosis of Alzheimer's Disease from Full-Resolution Whole-Brain sMRI Scans

“…The fourth layer is a Dense layer. A Rectified Linear Unit (ReLU) activation function is used to help the model consider non-linear effects and interactions, as it demonstrates faster training as well as better results than sigmoid function [17].…”

“…Selecting the GPU hardware acceleration and high RAM setups of the PRO version of Google Colab cloud service 5 , we used Keras to train our model end-to-end for 40 epochs with a mini-batch size of 4 and a learning rate of 0.001 using the Stochastic Gradient Descent (SGD) optimizer. During training, the optimization based on a stochastic gradient is fundamental to minimize the loss function while ensuring better efficiency [17]. We set categorical cross entropy as loss function.…”

Application of fiber loop ringdown spectroscopy technique for a new approach to beta-amyloid monitoring for Alzheimer Disease’s early detection

“…ELISA and neuroimaging have been the common methods to study on detection of Aβ42 and other biomarkers [16,17]. Besides, numerous other techniques/methods have been improved for Aβ42 quantification such as fluorescent microscopy, quantum dot nanoprobes, nanomaterials, mass spectrometry, immobilized metal affinity chromatography and meta-analysis, Positron Emission Tomography (PET), Photon and Single-Photon Emission Computed Tomography, Regular and Functional Magnetic Resonance Imaging (MRI) [18][19][20][21][22]. Laboratory tests include genetic tests, biomarker detections, and CSF analysis [23].…”