國立虎尾科技大學 |

Medical Note and Image Processing with Physical Models and Deep Learning Techniques.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Medical Note and Image Processing with Physical Models and Deep Learning Techniques./
Author:	Zhou, Hanyue.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
Description:	142 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
Contained By:	Dissertations Abstracts International83-09B.
Subject:	Artificial intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28970485
ISBN:	9798209887522

Medical Note and Image Processing with Physical Models and Deep Learning Techniques.
Zhou, Hanyue.

Medical Note and Image Processing with Physical Models and Deep Learning Techniques. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 142 p.

Source: Dissertations Abstracts International, Volume: 83-09, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2022.

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

We aim to perform medical note comprehension and medical image processing, with an ultimate goal of cross-domain aggregation into a cooperative disease management system. The dissertation focuses on the initial technical development of each domain utilizing both physical modeling and deep learning methods. Medical notes and images taken from patients during their clinical visits are essential for patient care management. In this thesis, natural language processing techniques are developed for patient private information removal from medical reports, and image processing techniques are developed for semantic segmentation on different imaging modalities to achieve higher accuracy and enhanced structural integrity of the segmentation. Moreover, we demonstrate the importance of the manual labels used as the ground truth for supervised learning and assessment in the biomedical applications, and further propose a refinement scheme to improve label quality. Future directions would be integrating the complementary text and image information into a single robust system.

ISBN: 9798209887522Subjects--Topical Terms:

559380
Artificial intelligence.
Subjects--Index Terms:

Deep learning

Medical Note and Image Processing with Physical Models and Deep Learning Techniques.
LDR:02247nam a2200373 4500 001 1104580
005 20230619080054.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798209887522
035 $a (MiAaPQ)AAI28970485
035 $a AAI28970485
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhou, Hanyue. $3 1413441
245 1 0 $a Medical Note and Image Processing with Physical Models and Deep Learning Techniques.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 142 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
500 $a Advisor: Fan, Zhaoyang;Ruan, Dan.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a We aim to perform medical note comprehension and medical image processing, with an ultimate goal of cross-domain aggregation into a cooperative disease management system. The dissertation focuses on the initial technical development of each domain utilizing both physical modeling and deep learning methods. Medical notes and images taken from patients during their clinical visits are essential for patient care management. In this thesis, natural language processing techniques are developed for patient private information removal from medical reports, and image processing techniques are developed for semantic segmentation on different imaging modalities to achieve higher accuracy and enhanced structural integrity of the segmentation. Moreover, we demonstrate the importance of the manual labels used as the ground truth for supervised learning and assessment in the biomedical applications, and further propose a refinement scheme to improve label quality. Future directions would be integrating the complementary text and image information into a single robust system.
590 $a School code: 0031.
650 4 $a Artificial intelligence. $3 559380
650 4 $a Medical imaging. $3 1180167
650 4 $a Information technology. $3 559429
653 $a Deep learning
653 $a Image processing
653 $a NLP
690 $a 0800
690 $a 0574
690 $a 0489
710 2 $a University of California, Los Angeles. $b Bioengineering 0288. $3 1413442
773 0 $t Dissertations Abstracts International $g 83-09B.
790 $a 0031
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28970485