東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Biomarker-Aware Geometric Deep Learn...

Chen, Yanxi,

Linked to FindBook

Google Book

Amazon

博客來

Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease // Yanxi Chen.
Author:	Chen, Yanxi,
Description:	1 electronic resource (89 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
Contained By:	Dissertations Abstracts International86-11B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32000446
ISBN:	9798314876763

Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease /
Chen, Yanxi,

Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease /Yanxi Chen. - 1 electronic resource (89 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: B.

Alzheimer's disease (AD) presents complex structural and pathological changes in the brain that are difficult to fully characterize using any single modality. This dissertation develops and evaluates integrative machine learning frameworks that fuse structural MRI, blood-based biomarkers (BBBMs), and generative modeling to enhance diagnosis and pathology mapping in AD. This dissertation proposes a hybrid sparse coding and dictionary learning approach that combines hippocampal morphometry features from MRI with plasma Aβ42/40 ratios, significantly improving the accuracy of brain amyloid positivity prediction across multiple datasets. Then, a novel geometric deep learning architecture is introduced that is tailored to tetrahedral mesh representations of the brain. By leveraging a transformer-based model informed by Gaussian process-based anatomical landmarking, this method effectively encodes volumetric structural information and BBBMs to improve AD classification performance and interpretability. Finally, this study addresses the challenge of limited PET scan availability by designing a cross-modality generative model, Plasma-CycleGAN, that synthesizes PET-equivalent amyloid pathology maps from MRI, conditioned on BBBMs. The model generates PET images with enhanced structural fidelity and clinically relevant signal distributions. Together, these contributions demonstrate how geometric learning and biomarker integration can jointly advance both diagnostic performance and practical utility in AD research, offering scalable frameworks for future multimodal neuroimaging applications.

English

ISBN: 9798314876763Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Alzheimer's disease

Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease /
LDR:03096nmm a22004573i 4500 001 2432705
005 20250731101916.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798314876763
035 $a (MiAaPQD)AAI32000446
035 $a AAI32000446
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Chen, Yanxi, $e author. $3 3822029
245 1 0 $a Biomarker-Aware Geometric Deep Learning for Alzheimer's Disease / $c Yanxi Chen.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (89 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
500 $a Advisors: Wang, Yalin Committee members: Wang, Junwen; Li, Baoxin; Wu, Teresa; Yang, Yingzhen.
502 $b Ph.D. $c Arizona State University $d 2025.
520 $a Alzheimer's disease (AD) presents complex structural and pathological changes in the brain that are difficult to fully characterize using any single modality. This dissertation develops and evaluates integrative machine learning frameworks that fuse structural MRI, blood-based biomarkers (BBBMs), and generative modeling to enhance diagnosis and pathology mapping in AD. This dissertation proposes a hybrid sparse coding and dictionary learning approach that combines hippocampal morphometry features from MRI with plasma Aβ42/40 ratios, significantly improving the accuracy of brain amyloid positivity prediction across multiple datasets. Then, a novel geometric deep learning architecture is introduced that is tailored to tetrahedral mesh representations of the brain. By leveraging a transformer-based model informed by Gaussian process-based anatomical landmarking, this method effectively encodes volumetric structural information and BBBMs to improve AD classification performance and interpretability. Finally, this study addresses the challenge of limited PET scan availability by designing a cross-modality generative model, Plasma-CycleGAN, that synthesizes PET-equivalent amyloid pathology maps from MRI, conditioned on BBBMs. The model generates PET images with enhanced structural fidelity and clinically relevant signal distributions. Together, these contributions demonstrate how geometric learning and biomarker integration can jointly advance both diagnostic performance and practical utility in AD research, offering scalable frameworks for future multimodal neuroimaging applications.
546 $a English
590 $a School code: 0010
650 4 $a Computer science. $3 523869
650 4 $a Biomedical engineering. $3 535387
650 4 $a Neurosciences. $3 588700
650 4 $a Medical imaging. $3 3172799
653 $a Alzheimer's disease
653 $a Blood-based biomarker
653 $a Plasma-CycleGAN
653 $a Geometric deep learning
653 $a Sparse coding
653 $a Tetrahedral mesh
690 $a 0984
690 $a 0574
690 $a 0541
690 $a 0317
710 2 $a Arizona State University. $b Computer Science. $e degree granting institution. $3 3815405
720 1 $a Wang, Yalin $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11B.
790 $a 0010
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32000446