Multimodal classification of Alzheimer's disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decision-making for explainable diagnosis
Multimodal classification of Alzheimer's disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decision-making for explainable diagnosis
The study presents an innovative diagnostic framework that synergises Convolutional Neural Networks (CNNs) with a Multi-feature Kernel Supervised within-class-similar Discriminative Dictionary Learning (MKSCDDL). This integrative methodology is designed to facilitate the precise classification of individuals into categories of Alzheimer's Disease, Mild Cognitive Impairment (MCI), and Cognitively Normal (CN) statuses while also discerning the nuanced phases within the MCI spectrum. Our approach is distinguished by its robustness and interpretability, offering clinicians an exceptionally transparent tool for diagnosis and therapeutic strategy formulation. We use scandent decision trees to deal with the unpredictability and complexity of neuroimaging data. Considering that different people's brain scans are different, this enables the model to make more detailed individualised assessments and explains how the algorithm illuminates the specific neuroanatomical regions that are indicative of cognitive impairment. This explanation is beneficial for clinicians because it gives them concrete ideas for early intervention and targeted care. The empirical review of our model shows that it makes diagnoses with a level of accuracy that is unmatched, with a classification efficacy of 98.27%. This shows that the model is good at finding important parts of the brain that may be damaged by cognitive diseases.
Adarsh, V.
a847847c-cb23-4eb4-b06b-ae6ad7e6fbc6
Gangadharan, G.R.
8bfd2f88-da93-4ecb-b26b-62cd5fd11b58
Fiore, Ugo
115628d4-8528-4731-ae45-9fe118fa88f5
Zanetti, Paolo
099f13c2-37d1-414c-b6d2-f02a1cd43307
20 January 2024
Adarsh, V.
a847847c-cb23-4eb4-b06b-ae6ad7e6fbc6
Gangadharan, G.R.
8bfd2f88-da93-4ecb-b26b-62cd5fd11b58
Fiore, Ugo
115628d4-8528-4731-ae45-9fe118fa88f5
Zanetti, Paolo
099f13c2-37d1-414c-b6d2-f02a1cd43307
Adarsh, V., Gangadharan, G.R., Fiore, Ugo and Zanetti, Paolo
(2024)
Multimodal classification of Alzheimer's disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decision-making for explainable diagnosis.
Scientific Reports, 14 (1), [1774].
(doi:10.1038/s41598-024-52185-2).
Abstract
The study presents an innovative diagnostic framework that synergises Convolutional Neural Networks (CNNs) with a Multi-feature Kernel Supervised within-class-similar Discriminative Dictionary Learning (MKSCDDL). This integrative methodology is designed to facilitate the precise classification of individuals into categories of Alzheimer's Disease, Mild Cognitive Impairment (MCI), and Cognitively Normal (CN) statuses while also discerning the nuanced phases within the MCI spectrum. Our approach is distinguished by its robustness and interpretability, offering clinicians an exceptionally transparent tool for diagnosis and therapeutic strategy formulation. We use scandent decision trees to deal with the unpredictability and complexity of neuroimaging data. Considering that different people's brain scans are different, this enables the model to make more detailed individualised assessments and explains how the algorithm illuminates the specific neuroanatomical regions that are indicative of cognitive impairment. This explanation is beneficial for clinicians because it gives them concrete ideas for early intervention and targeted care. The empirical review of our model shows that it makes diagnoses with a level of accuracy that is unmatched, with a classification efficacy of 98.27%. This shows that the model is good at finding important parts of the brain that may be damaged by cognitive diseases.
Text
s41598-024-52185-2
- Version of Record
More information
e-pub ahead of print date: 20 January 2024
Published date: 20 January 2024
Identifiers
Local EPrints ID: 495870
URI: http://eprints.soton.ac.uk/id/eprint/495870
ISSN: 2045-2322
PURE UUID: e1e2edf5-2596-41cd-9739-a758b2c2a586
Catalogue record
Date deposited: 26 Nov 2024 17:43
Last modified: 27 Nov 2024 03:10
Export record
Altmetrics
Contributors
Author:
V. Adarsh
Author:
G.R. Gangadharan
Author:
Ugo Fiore
Author:
Paolo Zanetti
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
Loading...
View more statistics