Joint shape matching for overlapping cytoplasm segmentation in cervical smear images

We present a novel and effective approach to segmenting overlapping cytoplasm of cells in cervical smear images. Instead of simply combining individual cytoplasm shape information with the intensity or color information for the segmentation, our approach aims at simultaneously matching an accurate s...

全面介紹

Saved in:
書目詳細資料
Main Authors: SONG, Youyi, QIN, Jing, LEI, Baiying, HE, Shengfeng, CHOI, Kup-Sze
格式: text
語言:English
出版: Institutional Knowledge at Singapore Management University 2019
主題:
在線閱讀:https://ink.library.smu.edu.sg/sis_research/8563
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Singapore Management University
語言: English
id sg-smu-ink.sis_research-9566
record_format dspace
spelling sg-smu-ink.sis_research-95662024-01-18T02:30:03Z Joint shape matching for overlapping cytoplasm segmentation in cervical smear images SONG, Youyi QIN, Jing LEI, Baiying HE, Shengfeng CHOI, Kup-Sze We present a novel and effective approach to segmenting overlapping cytoplasm of cells in cervical smear images. Instead of simply combining individual cytoplasm shape information with the intensity or color information for the segmentation, our approach aims at simultaneously matching an accurate shape template for each cytoplasm in a whole clump. There are two main technical contributions. First, we present a novel shape similarity measure that supports shape template matching without clump splitting, allowing us to leverage more shape information, not only from the cytoplasm itself but also from the whole clump. Second, we propose an effective objective function for joint shape template matching based on our shape similarity measure; unlike individual matching, our method is able to exploit more shape constraints. We extensively evaluate our method on two typical cervical smear data sets. Experimental results show that our method outperforms the state-of-the-art methods in term of segmentation accuracy. 2019-04-11T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/8563 info:doi/10.1109/ISBI.2019.8759259 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Cervical smear images Color information Effective approaches Objective function ; Segmentation accuracy Shape information State-of-the-art methods Technical contribution Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Cervical smear images
Color information
Effective approaches
Objective function
; Segmentation accuracy
Shape information
State-of-the-art methods
Technical contribution
Databases and Information Systems
spellingShingle Cervical smear images
Color information
Effective approaches
Objective function
; Segmentation accuracy
Shape information
State-of-the-art methods
Technical contribution
Databases and Information Systems
SONG, Youyi
QIN, Jing
LEI, Baiying
HE, Shengfeng
CHOI, Kup-Sze
Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
description We present a novel and effective approach to segmenting overlapping cytoplasm of cells in cervical smear images. Instead of simply combining individual cytoplasm shape information with the intensity or color information for the segmentation, our approach aims at simultaneously matching an accurate shape template for each cytoplasm in a whole clump. There are two main technical contributions. First, we present a novel shape similarity measure that supports shape template matching without clump splitting, allowing us to leverage more shape information, not only from the cytoplasm itself but also from the whole clump. Second, we propose an effective objective function for joint shape template matching based on our shape similarity measure; unlike individual matching, our method is able to exploit more shape constraints. We extensively evaluate our method on two typical cervical smear data sets. Experimental results show that our method outperforms the state-of-the-art methods in term of segmentation accuracy.
format text
author SONG, Youyi
QIN, Jing
LEI, Baiying
HE, Shengfeng
CHOI, Kup-Sze
author_facet SONG, Youyi
QIN, Jing
LEI, Baiying
HE, Shengfeng
CHOI, Kup-Sze
author_sort SONG, Youyi
title Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
title_short Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
title_full Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
title_fullStr Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
title_full_unstemmed Joint shape matching for overlapping cytoplasm segmentation in cervical smear images
title_sort joint shape matching for overlapping cytoplasm segmentation in cervical smear images
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/8563
_version_ 1789483266164654080