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

Deep Generative Machine Learning to ...

Mendez Mora, Mauro,

FindBook

Google Book

Amazon

博客來

Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research // Mauro Mendez Mora.
作者:	Mendez Mora, Mauro,
面頁冊數:	1 electronic resource (114 pages)
附註:	Source: Masters Abstracts International, Volume: 84-12.
Contained By:	Masters Abstracts International84-12.
標題:	Medical imaging. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30247325
ISBN:	9798379763411

Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research /
Mendez Mora, Mauro,

Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research /Mauro Mendez Mora. - 1 electronic resource (114 pages)

Source: Masters Abstracts International, Volume: 84-12.

Research on rare diseases is often not considered by the artificial intelligence (AI) field due to data scarcity. Hemophilia is a rare genetic bleeding disorder that affects blood clotting. Hemophiliacs often suffer from bleeding into the joint space (hemarthrosis) that causes pain and ultimately damage. Ultrasound imaging is used for non-invasive hemarthrosis assessment. Early detection using AI is key to improve treatment efficacy and access to care. This thesis proposes a novel generation framework that includes domain knowledge from an external dataset, decreasing missing information in rare cases. By dividing the problem in content and context generation, our enriched synthetic ultrasound showed no significant differences from real data; improved model performance, especially at smaller sample sizes; outperformed a previously accepted model in synthetic quality; and provided a robust model for hemarthrosis detection. Our framework facilitates AI research in the study of rare diseases and the prototyping of AI-driven clinical solutions.

English

ISBN: 9798379763411Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Artificial simulation

Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research /
LDR:02488nmm a22004333i 4500 001 2428686
005 20250414022003.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798379763411
035 $a (MiAaPQD)AAI30247325
035 $a AAI30247325
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Mendez Mora, Mauro, $e author. $0 (orcid)0000-0002-5418-7005 $3 3816064
245 1 0 $a Deep Generative Machine Learning to Create Synthetic 2D Ultrasound Images for Rare Disease Research / $c Mauro Mendez Mora.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (114 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: Masters Abstracts International, Volume: 84-12.
500 $a Advisors: Tyrrell, Pascal Committee members: Brudno, Michael; Moody, Alan.
502 $b M.Sc. $c University of Toronto (Canada) $d 2023.
520 $a Research on rare diseases is often not considered by the artificial intelligence (AI) field due to data scarcity. Hemophilia is a rare genetic bleeding disorder that affects blood clotting. Hemophiliacs often suffer from bleeding into the joint space (hemarthrosis) that causes pain and ultimately damage. Ultrasound imaging is used for non-invasive hemarthrosis assessment. Early detection using AI is key to improve treatment efficacy and access to care. This thesis proposes a novel generation framework that includes domain knowledge from an external dataset, decreasing missing information in rare cases. By dividing the problem in content and context generation, our enriched synthetic ultrasound showed no significant differences from real data; improved model performance, especially at smaller sample sizes; outperformed a previously accepted model in synthetic quality; and provided a robust model for hemarthrosis detection. Our framework facilitates AI research in the study of rare diseases and the prototyping of AI-driven clinical solutions.
546 $a English
590 $a School code: 0779
650 4 $a Medical imaging. $3 3172799
650 4 $a Medicine. $3 641104
653 $a Artificial simulation
653 $a Generative models
653 $a Hemarthrosis
653 $a Hemophilia
653 $a Ultrasound imaging
690 $a 0574
690 $a 0800
690 $a 0564
710 2 $a University of Toronto (Canada). $b Medical Science. $e degree granting institution. $3 3816065
720 1 $a Tyrrell, Pascal $e degree supervisor.
773 0 $t Masters Abstracts International $g 84-12.
790 $a 0779
791 $a M.Sc.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30247325