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

切換: 標籤 | MARC模式 | ISBD

Machine Learning for Anatomical Stru...

Bui, Vy Cong Bich.

FindBook

Google Book

Amazon

博客來

Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images./
作者:	Bui, Vy Cong Bich.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	152 p.
附註:	Source: Dissertations Abstracts International, Volume: 81-12, Section: B.
Contained By:	Dissertations Abstracts International81-12B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27958908
ISBN:	9798645478582

Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images.
Bui, Vy Cong Bich.

Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 152 p.

Source: Dissertations Abstracts International, Volume: 81-12, Section: B.

Thesis (Ph.D.)--The Catholic University of America, 2020.

This item must not be sold to any third party vendors.

Contrast enhanced cardiac computed tomography angiography (CTA) is an important imaging modality for assessing the morphology of the heart and coronary arteries for diagnosing cardiovascular disease. Accurate heart segmentation in cardiac CTA images is an important task for quantitative assessment of aorta, myocardium, and different cardiac chambers. However, manual segmentation is time-consuming, prone to errors and variations between observers while automatic segmentation is very challenging due to large shape variations in the cardiac anatomy among different subjects, indistinct boundaries between substructures of the heart (e.g. right ventricle and right atrium) or between the heart and surrounding tissues (e.g. liver, ribs, sternum) and long processing time may not be efficient in clinical practice. This dissertation provides a new method that uses machine learning based approach to improve the accuracy and efficiency of the commonly used multi-atlas and deep neural network based approaches for 17 different cardiac and non-cardiac structures segmentation in cardiac CTA images. Specifically, an automatic framework combining multi-atlas and corrective segmentation to identify several cardiovascular and intrathoracic structures from cardiac CTA images is proposed. The proposed multi-atlas based framework significantly improves the segmentation accuracy without suffering from high computational burden existed in conventional multi-atlas based approach. In addition, large amounts of annotated data are required for deep neural networks to produce reliable results. This is a common limitation in deep learning-based approach, especially in medical field as the annotated data required efforts by domain experts and it can be very challenging and time consuming when multiple labels are desired in 3D volumetric data. To tackle this limitation, the proposed multi-atlas based framework can be used to generate reliable segmentations with less annotated samples to serve as training data for deep learning methods.This work would allow much less expert supervision while providing comparable high-quality automatic segmentation results which is also more suitable for 3D CTA volume data and large-scale studies. Furthermore, the automated methods should be more consistent and faster than manual labeling methods.

ISBN: 9798645478582Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Cardiac computed tomography angiography

Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images.
LDR:03578nmm a2200373 4500 001 2269587
005 20200911122850.5
008 220629s2020 ||||||||||||||||| ||eng d
020 $a 9798645478582
035 $a (MiAaPQ)AAI27958908
035 $a AAI27958908
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bui, Vy Cong Bich. $3 3546924
245 1 0 $a Machine Learning for Anatomical Structures Segmentation of Contrast-Enhanced Cardiac Computed Tomography Images.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 152 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-12, Section: B.
500 $a Advisor: Chang, Lin-Ching.
502 $a Thesis (Ph.D.)--The Catholic University of America, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Contrast enhanced cardiac computed tomography angiography (CTA) is an important imaging modality for assessing the morphology of the heart and coronary arteries for diagnosing cardiovascular disease. Accurate heart segmentation in cardiac CTA images is an important task for quantitative assessment of aorta, myocardium, and different cardiac chambers. However, manual segmentation is time-consuming, prone to errors and variations between observers while automatic segmentation is very challenging due to large shape variations in the cardiac anatomy among different subjects, indistinct boundaries between substructures of the heart (e.g. right ventricle and right atrium) or between the heart and surrounding tissues (e.g. liver, ribs, sternum) and long processing time may not be efficient in clinical practice. This dissertation provides a new method that uses machine learning based approach to improve the accuracy and efficiency of the commonly used multi-atlas and deep neural network based approaches for 17 different cardiac and non-cardiac structures segmentation in cardiac CTA images. Specifically, an automatic framework combining multi-atlas and corrective segmentation to identify several cardiovascular and intrathoracic structures from cardiac CTA images is proposed. The proposed multi-atlas based framework significantly improves the segmentation accuracy without suffering from high computational burden existed in conventional multi-atlas based approach. In addition, large amounts of annotated data are required for deep neural networks to produce reliable results. This is a common limitation in deep learning-based approach, especially in medical field as the annotated data required efforts by domain experts and it can be very challenging and time consuming when multiple labels are desired in 3D volumetric data. To tackle this limitation, the proposed multi-atlas based framework can be used to generate reliable segmentations with less annotated samples to serve as training data for deep learning methods.This work would allow much less expert supervision while providing comparable high-quality automatic segmentation results which is also more suitable for 3D CTA volume data and large-scale studies. Furthermore, the automated methods should be more consistent and faster than manual labeling methods.
590 $a School code: 0043.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Medical imaging. $3 3172799
653 $a Cardiac computed tomography angiography
653 $a Deep learning
653 $a Image segmentation
653 $a Machine learning
653 $a Multi-atlas segmentation
690 $a 0984
690 $a 0800
690 $a 0574
710 2 $a The Catholic University of America. $b Electrical Engineering and Computer Science. $3 1682582
773 0 $t Dissertations Abstracts International $g 81-12B.
790 $a 0043
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27958908