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

New Deep Learning Based Approaches f...

Yang, Lin.

FindBook

Google Book

Amazon

博客來

New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems./
作者:	Yang, Lin.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	129 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-08, Section: B.
Contained By:	Dissertations Abstracts International80-08B.
標題:	Bioinformatics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13836469
ISBN:	9780438836556

New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems.
Yang, Lin.

New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 129 p.

Source: Dissertations Abstracts International, Volume: 80-08, Section: B.

Thesis (Ph.D.)--University of Notre Dame, 2018.

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

Image segmentation is a fundamental problem in biomedical image analysis. In recent years, deep learning methods have emerged and continued to prosper as powerful tools for natural scene image segmentation. While biomedical image segmentation is in close relation to natural scene image segmentation, general deep learning methods for natural scene images may not work well on biomedical applications because of two unique properties of biomedical images. First, biomedical images can be true 3D volumetric images, which post significant challenges on computational approaches and computation resources, while most natural scene images are 2D images. Second, only trained biomedical experts can annotate biomedical images well, which makes it quite expensive and difficult to obtain sufficient training data. In this dissertation, we develop new deep learning based approaches specifically targeting these two unique properties of biomedical images. To achieve accurate segmentation on 3D biomedical images, we propose a new ensemble learning framework to unify the merits of 2D and 3D deep learning models. To reduce the annotation burden for biomedical images, we propose novel methods to (1) improve the effectiveness of manual annotation by suggesting the most useful object samples to annotate and (2) improve the efficiency of manual annotation by allowing inexact rough labeling. Extensive experiments on various biomedical image segmentation datasets show that our methods can achieve state-of-art performance while reducing significant amounts of annotation efforts.

ISBN: 9780438836556Subjects--Topical Terms:

553671
Bioinformatics.
Subjects--Index Terms:

Annotation

New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems.
LDR:02833nmm a2200361 4500 001 2275403
005 20210209133254.5
008 220723s2018 ||||||||||||||||| ||eng d
020 $a 9780438836556
035 $a (MiAaPQ)AAI13836469
035 $a AAI13836469
040 $a MiAaPQ $c MiAaPQ
100 1 $a Yang, Lin. $3 1259477
245 1 0 $a New Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 129 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-08, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
502 $a Thesis (Ph.D.)--University of Notre Dame, 2018.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
506 $a This item is not available from ProQuest Dissertations & Theses.
520 $a Image segmentation is a fundamental problem in biomedical image analysis. In recent years, deep learning methods have emerged and continued to prosper as powerful tools for natural scene image segmentation. While biomedical image segmentation is in close relation to natural scene image segmentation, general deep learning methods for natural scene images may not work well on biomedical applications because of two unique properties of biomedical images. First, biomedical images can be true 3D volumetric images, which post significant challenges on computational approaches and computation resources, while most natural scene images are 2D images. Second, only trained biomedical experts can annotate biomedical images well, which makes it quite expensive and difficult to obtain sufficient training data. In this dissertation, we develop new deep learning based approaches specifically targeting these two unique properties of biomedical images. To achieve accurate segmentation on 3D biomedical images, we propose a new ensemble learning framework to unify the merits of 2D and 3D deep learning models. To reduce the annotation burden for biomedical images, we propose novel methods to (1) improve the effectiveness of manual annotation by suggesting the most useful object samples to annotate and (2) improve the efficiency of manual annotation by allowing inexact rough labeling. Extensive experiments on various biomedical image segmentation datasets show that our methods can achieve state-of-art performance while reducing significant amounts of annotation efforts.
590 $a School code: 0165.
650 4 $a Bioinformatics. $3 553671
650 4 $a Computer science. $3 523869
653 $a Annotation
653 $a Deep learning
653 $a Image segmentation
690 $a 0715
690 $a 0984
710 2 $a University of Notre Dame. $b Computer Science and Engineering. $3 3553652
773 0 $t Dissertations Abstracts International $g 80-08B.
790 $a 0165
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13836469