Prediction of Alzheimer's progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series data

Simple item page
dc.contributor.authorRahim, Nasir
dc.contributor.authorEl-Sappagh, Shaker
dc.contributor.authorAli, Sajid
dc.contributor.authorMuhammad, Khan
dc.contributor.authorDel Ser, Javier
dc.contributor.authorAbuhmed, Tamer
dc.contributor.institutionIA
dc.date.accessioned2024-09-06T10:55:03Z
dc.date.available2024-09-06T10:55:03Z
dc.date.issued2023-04
dc.descriptionPublisher Copyright: © 2022 Elsevier B.V.
dc.description.abstractAlzheimer's disease (AD) is a neurological illness that causes cognitive impairment and has no known treatment. The premise for delivering timely therapy is the early diagnosis of AD before clinical symptoms appear. Mild cognitive impairment is an intermediate stage in which cognitively normal patients can be distinguished from those with AD. In this study, we propose a hybrid multimodal deep-learning framework consisting of a 3D convolutional neural network (3D CNN) followed by a bidirectional recurrent neural network (BRNN). The proposed 3D CNN captures intra-slice features from each 3D magnetic resonance imaging (MRI) volume, whereas the BRNN module identifies the inter-sequence patterns that lead to AD. This study is conducted based on longitudinal 3D MRI volumes collected over a six-months time span. We further investigate the effect of fusing MRI with cross-sectional biomarkers, such as patients’ demographic and cognitive scores from their baseline visit. In addition, we present a novel explainability approach that helps domain experts and practitioners to understand the end output of the proposed multimodal. Extensive experiments reveal that the accuracy, precision, recall, and area under the receiver operating characteristic curve of the proposed framework are 96%, 99%, 92%, and 96%, respectively. These results are based on the fusion of MRI and demographic features and indicate that the proposed framework becomes more stable when exposed to a more complete set of longitudinal data. Moreover, the explainability module provides extra support for the progression claim by more accurately identifying the brain regions that domain experts commonly report during diagnoses.en
dc.description.sponsorshipThis research was supported by the Ministry of Science and ICT (MSIT), Korea , under the ICT Creative Consilience Program ( IITP-2021–2020–0–01821 ), supervised by the Institute for Information & communications Technology Planning & Evaluation (IITP), and the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2021R1A2C1011198).
dc.description.statusPeer reviewed
dc.format.extent26
dc.identifier.citationRahim , N , El-Sappagh , S , Ali , S , Muhammad , K , Del Ser , J & Abuhmed , T 2023 , ' Prediction of Alzheimer's progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series data ' , Information Fusion , vol. 92 , pp. 363-388 . https://doi.org/10.1016/j.inffus.2022.11.028
dc.identifier.doi10.1016/j.inffus.2022.11.028
dc.identifier.issn1566-2535
dc.identifier.urihttps://hdl.handle.net/11556/4942
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85144325712&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofInformation Fusion
dc.relation.projectIDInstitute for Information & communications Technology Planning & Evaluation
dc.relation.projectIDMinistry of Science, ICT and Future Planning, MSIP, IITP-2021–2020–0–01821
dc.relation.projectIDNational Research Foundation of Korea, NRF, 2021R1A2C1011198
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywords3D CNN
dc.subject.keywordsAD progression detection
dc.subject.keywordsExplainable AI
dc.subject.keywordsMultimodal information fusion
dc.subject.keywordsTime-series data analysis
dc.subject.keywordsSoftware
dc.subject.keywordsSignal Processing
dc.subject.keywordsInformation Systems
dc.subject.keywordsHardware and Architecture
dc.titlePrediction of Alzheimer's progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series dataen
dc.typejournal article
Files