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

FindBook

Google Book

Amazon

博客來

Multi-Compartment Segmentation in Renal Transplant Pathology.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Multi-Compartment Segmentation in Renal Transplant Pathology./
作者:	Krishna Murali, Leema Krishna.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	31 p.
附註:	Source: Masters Abstracts International, Volume: 82-09.
Contained By:	Masters Abstracts International82-09.
標題:	Medical imaging. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28314272
ISBN:	9798582509592

Multi-Compartment Segmentation in Renal Transplant Pathology.
Krishna Murali, Leema Krishna.

Multi-Compartment Segmentation in Renal Transplant Pathology. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 31 p.

Source: Masters Abstracts International, Volume: 82-09.

Thesis (M.S.)--State University of New York at Buffalo, 2021.

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

With the rapid development in different image staining protocols, machine learning algorithms in detection and segmentation in histopathological images, AI-based tools to assist in the diagnosis and evaluation of digital slides have gained popularity. Historically, classical histology staining method, such as Periodic acid-Schiff (PAS) and hematoxylin and eosin (H&E), has been the gold standard for tissue evaluation and assessment by pathologists. Recently, fluorescence-based multiplex immunohistochemistry (mIHC) method enables to quantify simultaneous localization of multiple proteins in tissue. This information is beneficial to segment multiple structures in a biopsy section further assisting in clinical diagnosis. However, this method is limited by cost and time to conduct tissue staining and imaging. To accelerate diagnosis and achieve an accurate evaluation of tissue slides with routinely used histology agents (such as, PAS), we have implemented a deep learning-based pipeline that performs unified segmentation of multiple compartments on the histopathology tissue slide using fluorescence image as the ground-truth. We demonstrate the performance of our pipeline by computationally segmenting multiple compartments in renal transplant biopsies, namely, cell nuclei, interstitial fibrosis, distal tubules, proximal tubules, endothelial cells, and leukocytes. We observed that proximal tubule, cell nuclei, distal tubule and, interstitial fibrosis are best identified by the network with few misclassifications. Our work can be extended for other renal structures as well as tissue types. In the transplant pathology domain, our results have implications in studying acute and chronic changes in renal transplant allografts.

ISBN: 9798582509592Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Deep Learning

Multi-Compartment Segmentation in Renal Transplant Pathology.
LDR:02895nmm a2200385 4500 001 2346126
005 20220613065108.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798582509592
035 $a (MiAaPQ)AAI28314272
035 $a AAI28314272
040 $a MiAaPQ $c MiAaPQ
100 1 $a Krishna Murali, Leema Krishna. $3 3685173
245 1 0 $a Multi-Compartment Segmentation in Renal Transplant Pathology.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 31 p.
500 $a Source: Masters Abstracts International, Volume: 82-09.
500 $a Advisor: Sarder, Pinaki.
502 $a Thesis (M.S.)--State University of New York at Buffalo, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a With the rapid development in different image staining protocols, machine learning algorithms in detection and segmentation in histopathological images, AI-based tools to assist in the diagnosis and evaluation of digital slides have gained popularity. Historically, classical histology staining method, such as Periodic acid-Schiff (PAS) and hematoxylin and eosin (H&E), has been the gold standard for tissue evaluation and assessment by pathologists. Recently, fluorescence-based multiplex immunohistochemistry (mIHC) method enables to quantify simultaneous localization of multiple proteins in tissue. This information is beneficial to segment multiple structures in a biopsy section further assisting in clinical diagnosis. However, this method is limited by cost and time to conduct tissue staining and imaging. To accelerate diagnosis and achieve an accurate evaluation of tissue slides with routinely used histology agents (such as, PAS), we have implemented a deep learning-based pipeline that performs unified segmentation of multiple compartments on the histopathology tissue slide using fluorescence image as the ground-truth. We demonstrate the performance of our pipeline by computationally segmenting multiple compartments in renal transplant biopsies, namely, cell nuclei, interstitial fibrosis, distal tubules, proximal tubules, endothelial cells, and leukocytes. We observed that proximal tubule, cell nuclei, distal tubule and, interstitial fibrosis are best identified by the network with few misclassifications. Our work can be extended for other renal structures as well as tissue types. In the transplant pathology domain, our results have implications in studying acute and chronic changes in renal transplant allografts.
590 $a School code: 0656.
650 4 $a Medical imaging. $3 3172799
650 4 $a Artificial intelligence. $3 516317
650 4 $a Pathology. $3 643180
650 4 $a Biomedical engineering. $3 535387
653 $a Deep Learning
653 $a Immunofluorescence
653 $a Machine Learning
653 $a Segmentation
653 $a Renal transplant
690 $a 0574
690 $a 0800
690 $a 0571
690 $a 0541
710 2 $a State University of New York at Buffalo. $b Biomedical Engineering. $3 3191314
773 0 $t Masters Abstracts International $g 82-09.
790 $a 0656
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28314272