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

Robust Electrode Displacement Elasto...

Pohlman, Robert M.

FindBook

Google Book

Amazon

博客來

Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning./
作者:	Pohlman, Robert M.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	318 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-11, Section: B.
Contained By:	Dissertations Abstracts International82-11B.
標題:	Medical imaging. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28495999
ISBN:	9798738622854

Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning.
Pohlman, Robert M.

Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 318 p.

Source: Dissertations Abstracts International, Volume: 82-11, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2021.

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

Hepatocellular carcinoma (HCC) is the 6th most common cancer worldwide with the 3rd highest mortality rate. Although mortality with all other cancers have declined over the last decade, the age-adjusted death-rate for HCC in the United States surged between 2000-2016 by 43% in men and 40% in women, with an estimated 42,000 new liver cancer diagnosis in 2018. A common procedure to increase liver cancer patient survival rates is surgical resection, yet many patients are nonviable candidates due to other liver co-morbidities. Minimally invasive microwave ablation (MWA) is becoming an important alternative, providing similar results to surgical resection with fewer complications. For MWA to provide these excellent results, accurate imaging of tumors before and after ablation is essential to ensure adequate tissue necrosis. Although contrast enhanced computed tomography (CECT) is most often relied upon for this task, ultrasound-based elasticity imaging provides an excellent alternative due to its real-time, cost-effective, and non-ionizing imaging advantage. Conventional B-mode is unfit to provide necessary delineation, but electrode displacement elastography (EDE) has demonstrated high contrast and contrast-to-noise imaging of liver ablations at all depths. However, EDE still retains some limitations from becoming a comparable imaging modality to CECT in the clinical setting. The primary goal of this research is to utilize machine-learning concepts to improve EDE liver ablation delineation and decrease image noise as well as providing clinicians with feedback on ablated region size and location. Results have demonstrated feasibility of this proposed work and verify that our approach has merit. The first aim of this project utilized dictionary representations on displacement estimates demonstrating significant reduction of noise in strain tensor images without negatively influencing boundary delineation. Our second aim tracked ablation dimensions over clinician perturbations during EDE and accounted for physiological motion that can degrade ablation size and contrast consistency. Finally, we utilized the ellipsoidal shape of ablations to autonomously locate and segment strain tensor images with active contour snakes. Together this project is a major stepping-stone to bridging the gap between ultrasound and CECT imaging modalities for monitoring and differential imaging of MWA procedures.

ISBN: 9798738622854Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Image Processing

Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning.
LDR:03613nmm a2200373 4500 001 2281657
005 20210920103610.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798738622854
035 $a (MiAaPQ)AAI28495999
035 $a AAI28495999
040 $a MiAaPQ $c MiAaPQ
100 1 $a Pohlman, Robert M. $3 3560339
245 1 0 $a Robust Electrode Displacement Elastography Imaging for Microwave Liver Ablation Using Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 318 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-11, Section: B.
500 $a Advisor: Varghese, Tomy.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Hepatocellular carcinoma (HCC) is the 6th most common cancer worldwide with the 3rd highest mortality rate. Although mortality with all other cancers have declined over the last decade, the age-adjusted death-rate for HCC in the United States surged between 2000-2016 by 43% in men and 40% in women, with an estimated 42,000 new liver cancer diagnosis in 2018. A common procedure to increase liver cancer patient survival rates is surgical resection, yet many patients are nonviable candidates due to other liver co-morbidities. Minimally invasive microwave ablation (MWA) is becoming an important alternative, providing similar results to surgical resection with fewer complications. For MWA to provide these excellent results, accurate imaging of tumors before and after ablation is essential to ensure adequate tissue necrosis. Although contrast enhanced computed tomography (CECT) is most often relied upon for this task, ultrasound-based elasticity imaging provides an excellent alternative due to its real-time, cost-effective, and non-ionizing imaging advantage. Conventional B-mode is unfit to provide necessary delineation, but electrode displacement elastography (EDE) has demonstrated high contrast and contrast-to-noise imaging of liver ablations at all depths. However, EDE still retains some limitations from becoming a comparable imaging modality to CECT in the clinical setting. The primary goal of this research is to utilize machine-learning concepts to improve EDE liver ablation delineation and decrease image noise as well as providing clinicians with feedback on ablated region size and location. Results have demonstrated feasibility of this proposed work and verify that our approach has merit. The first aim of this project utilized dictionary representations on displacement estimates demonstrating significant reduction of noise in strain tensor images without negatively influencing boundary delineation. Our second aim tracked ablation dimensions over clinician perturbations during EDE and accounted for physiological motion that can degrade ablation size and contrast consistency. Finally, we utilized the ellipsoidal shape of ablations to autonomously locate and segment strain tensor images with active contour snakes. Together this project is a major stepping-stone to bridging the gap between ultrasound and CECT imaging modalities for monitoring and differential imaging of MWA procedures.
590 $a School code: 0262.
650 4 $a Medical imaging. $3 3172799
650 4 $a Electrical engineering. $3 649834
650 4 $a Biomedical engineering. $3 535387
650 4 $a Artificial intelligence. $3 516317
653 $a Image Processing
653 $a Machine Learning
653 $a Signal Processing
653 $a Ultrasound
690 $a 0574
690 $a 0544
690 $a 0541
690 $a 0800
710 2 $a The University of Wisconsin - Madison. $b Electrical Engineering. $3 2095968
773 0 $t Dissertations Abstracts International $g 82-11B.
790 $a 0262
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28495999