東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Graph Deep Learning for Multimodal N...

Qu, Gang,

FindBook

Google Book

Amazon

博客來

Graph Deep Learning for Multimodal Neuroimaging Study /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Graph Deep Learning for Multimodal Neuroimaging Study // Gang Qu.
作者:	Qu, Gang,
面頁冊數:	1 electronic resource (153 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
標題:	Bioengineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31292438
ISBN:	9798383201930

Graph Deep Learning for Multimodal Neuroimaging Study /
Qu, Gang,

Graph Deep Learning for Multimodal Neuroimaging Study /Gang Qu. - 1 electronic resource (153 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

This dissertation presents an advanced foray into neuroimaging, utilizing graph deep learning (GDL) methodologies to elucidate the complex functional organization of the human brain. Emphasizing the pivotal role of multimodal studies in neuroscience, we demonstrate the transformative potential of these approaches in understanding cerebral functionality.Central to this exploration is the application of Geometric Deep Learning, with a particular emphasis on Graph Neural Networks (GNNs). This innovative approach addresses the challenges inherent in traditional neuroimaging methods. The thesis delineates the development and application of sophisticated graph models, such as subject-to-subject graphs, functional connectivity graphs, and the Gated Graph Transformer (GGT). These models are strategically employed to enhance predictive analytics, focusing on cognitive assessment and neural biomarker discovery. The investigation further explores the amalgamation of diverse imaging modalities and paradigms, accentuating their essential contribution to a holistic understanding of human cognition and brain development, which augments predictive precision and facilitates the identification of crucial biomarkers, thereby enriching our comprehension of brain dynamics.Empirically validated through comprehensive simulations and analysis of extensive neuroimaging datasets, the findings of this research not only align with but also expand upon the existing body of neurological research. In adherence to the principles of open science, the methodologies and tools crafted in this research are conscientiously disseminated, guaranteeing reproducibility and fostering continued scholarly inquiry.In conclusion, this dissertation represents a substantial scholarly advancement in neuroimaging, evidencing the profound capability of graph deep learning to unravel the complexities of cerebral function. It lays a robust groundwork for future multimodal and multiparadigm neuroimaging research explorations.

English

ISBN: 9798383201930Subjects--Topical Terms:

657580
Bioengineering.
Subjects--Index Terms:

Graph deep learning

Graph Deep Learning for Multimodal Neuroimaging Study /
LDR:03500nmm a22004573i 4500 001 2429345
005 20250430100804.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383201930
035 $a (MiAaPQD)AAI31292438
035 $a AAI31292438
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Qu, Gang, $e author. $3 3817141
245 1 0 $a Graph Deep Learning for Multimodal Neuroimaging Study / $c Gang Qu.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (153 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: 86-01, Section: B.
500 $a Advisors: Wang, Yu-Ping Committee members: Gaver, Donald P.; Brown, Jonathon Q.; Ding, Zhengming.
502 $b Ph.D. $c Tulane University $d 2024.
520 $a This dissertation presents an advanced foray into neuroimaging, utilizing graph deep learning (GDL) methodologies to elucidate the complex functional organization of the human brain. Emphasizing the pivotal role of multimodal studies in neuroscience, we demonstrate the transformative potential of these approaches in understanding cerebral functionality.Central to this exploration is the application of Geometric Deep Learning, with a particular emphasis on Graph Neural Networks (GNNs). This innovative approach addresses the challenges inherent in traditional neuroimaging methods. The thesis delineates the development and application of sophisticated graph models, such as subject-to-subject graphs, functional connectivity graphs, and the Gated Graph Transformer (GGT). These models are strategically employed to enhance predictive analytics, focusing on cognitive assessment and neural biomarker discovery. The investigation further explores the amalgamation of diverse imaging modalities and paradigms, accentuating their essential contribution to a holistic understanding of human cognition and brain development, which augments predictive precision and facilitates the identification of crucial biomarkers, thereby enriching our comprehension of brain dynamics.Empirically validated through comprehensive simulations and analysis of extensive neuroimaging datasets, the findings of this research not only align with but also expand upon the existing body of neurological research. In adherence to the principles of open science, the methodologies and tools crafted in this research are conscientiously disseminated, guaranteeing reproducibility and fostering continued scholarly inquiry.In conclusion, this dissertation represents a substantial scholarly advancement in neuroimaging, evidencing the profound capability of graph deep learning to unravel the complexities of cerebral function. It lays a robust groundwork for future multimodal and multiparadigm neuroimaging research explorations.
546 $a English
590 $a School code: 0235
650 4 $a Bioengineering. $3 657580
650 4 $a Computer science. $3 523869
650 4 $a Neurosciences. $3 588700
650 4 $a Biomedical engineering. $3 535387
653 $a Graph deep learning
653 $a Multi-modal
653 $a Neuroimaging
653 $a Functional magnetic resonance imaging
653 $a Functional connectivity
653 $a Multimodal neuroimaging
690 $a 0202
690 $a 0984
690 $a 0317
690 $a 0541
710 2 $a Tulane University. $b Biomedical Engineering. $e degree granting institution. $3 3817142
720 1 $a Wang, Yu-Ping $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 0235
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31292438