AD-EHS: Alzheimer's disease severity detection using efficient hybrid image segmentation. (November 2022)

• Record Type: Journal Article
• Authors: Gopinadhan, Archana; Prasanna G．, Angeline; S．, Anbarasu
• Is Part Of: Advances in engineering software. Volume 173(2022)
• Publication Date: 2022-11
• Subjects: AD -- AD-EHS -- Deformable model -- HFLD -- MRI -- Segmentation; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103234
• Languages: English
• ISSNs: 0965-9978

Abstract

HIGHLIGHTS: In Alzheimer's disease (AD), memory and cognitive abilities deteriorate, affecting the capacity to do basic activities. Aberrant amyloid and tau protein accumulation in and around brain cells is believed to cause it. Amyloid deposits create plaques surrounding brain cells, whereas tau deposits form tangles inside brain cells. The plagues and tangles harm healthy brain cells, causing shrinkage. The segmentation has been done with the hybrid fuzzy logic deformable model. Abstract: In Alzheimer's disease (AD), memory and cognitive abilities deteriorate, affecting the capacity to do basic activities. Aberrant amyloid and tau protein accumulation in and around brain cells is believed to cause it. Amyloid deposits create plaques surrounding brain cells, whereas tau deposits form tangles inside brain cells. The plagues and tangles harm healthy brain cells, causing shrinkage. This damage seems to occur in the hippocampus, a brain region involved in memory formation. There are presently no methods that provide the most accurate outcomes. The current techniques do not identify AD early. The proposed AD-EHS method achieves the best segmentation using a hybrid fuzzy deformable model (HFLD). The MRI datasets have collected and removed noise using the spatial domain filtering method. Adaptive histogram equalization is used to enhance the MRI images. The segmentation has been done with the hybrid fuzzy logic deformable model. Segmentation has been shown to have a significant influence on characterization. Feature selection has been demonstrated for two performance metrics: reducing processing complexity and increasing the classifier's theoretical capacity. According to the experimental study, the severity of AD in participants was determined using hybrid image segmentation. The proposed model archives the segmentation accuracy of 83.47%.