TY - GEN
T1 - Improved Brain MRI Segmentation for Early Detection of Alzheimer's Disease using Overlaying Analysis and Thresholding
AU - Shetty, Jayashree
AU - Manjula Shenoy, K.
AU - Kolekar, Sucheta V.
AU - Prabhu, M. Mukhyaprana
AU - Bhardwaj, Siddh
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Alzheimer's disease (AD) with memory loss and cognitive decline as symptoms of the neuro-degenerative condition, damages the brain. The novel approach is proposed for detecting regions of the brain affected by AD using overlaying analysis and thresholding techniques. The current overlaying analysis methods lack accurate thresholding, which leads to a loss of pixel data, indicating highly varied segregation of brain regions. The usage of efficiently identifying disparities in pixel values between multiple digital images through computational analysis is highlighted in the proposed work. We also discuss the challenges and limitations of current image analysis methods, including issues related to misaligned scans and under-thresholding. A new function to find absolute pixel differences on brain Magnetic Resonance Imaging (MRI) scans, segregate the brain into multiple affected regions, and identify those affected by Very Mild Dementia Alzheimer's is applied. The segregated regions are then overlapped and compared with healthy brain regions to observe differences in structural and functional properties. The approach can accurately identify affected regions of the brain and provide valuable information for the diagnosis and prognosis of AD. The model contributes to the ongoing efforts to develop effective and non-invasive methods for detecting and tracking the progression of AD and highlights the potential of observing MRI scan differences using overlapping analysis as a powerful tool in neuroimaging research.
AB - Alzheimer's disease (AD) with memory loss and cognitive decline as symptoms of the neuro-degenerative condition, damages the brain. The novel approach is proposed for detecting regions of the brain affected by AD using overlaying analysis and thresholding techniques. The current overlaying analysis methods lack accurate thresholding, which leads to a loss of pixel data, indicating highly varied segregation of brain regions. The usage of efficiently identifying disparities in pixel values between multiple digital images through computational analysis is highlighted in the proposed work. We also discuss the challenges and limitations of current image analysis methods, including issues related to misaligned scans and under-thresholding. A new function to find absolute pixel differences on brain Magnetic Resonance Imaging (MRI) scans, segregate the brain into multiple affected regions, and identify those affected by Very Mild Dementia Alzheimer's is applied. The segregated regions are then overlapped and compared with healthy brain regions to observe differences in structural and functional properties. The approach can accurately identify affected regions of the brain and provide valuable information for the diagnosis and prognosis of AD. The model contributes to the ongoing efforts to develop effective and non-invasive methods for detecting and tracking the progression of AD and highlights the potential of observing MRI scan differences using overlapping analysis as a powerful tool in neuroimaging research.
UR - http://www.scopus.com/inward/record.url?scp=85174800820&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174800820&partnerID=8YFLogxK
U2 - 10.1109/INDISCON58499.2023.10270543
DO - 10.1109/INDISCON58499.2023.10270543
M3 - Conference contribution
AN - SCOPUS:85174800820
T3 - 2023 IEEE 4th Annual Flagship India Council International Subsections Conference: Computational Intelligence and Learning Systems, INDISCON 2023
BT - 2023 IEEE 4th Annual Flagship India Council International Subsections Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th IEEE Annual Flagship India Council International Subsections Conference, INDISCON 2023
Y2 - 5 August 2023 through 7 August 2023
ER -