TY - JOUR
T1 - SEENS
T2 - Nuclei segmentation in Pap smear images with selective edge enhancement
AU - Zhao, Meng
AU - Wang, Hao
AU - Han, Ying
AU - Wang, Xiaokang
AU - Dai, Hong Ning
AU - Sun, Xuguo
AU - Zhang, Jin
AU - Pedersen, Marius
N1 - Funding Information:
This document is the results of the research project funded by the National Science Foundation of China (Grant Nos. 61703304, 61906133 and U1509207), R & D Plan in Key Field of Guangdong Province (Grant No. 2019B010109001), Major Science and Technology Projects of Tianjin (Grant No. 18ZXZNGX00150) and is carried out with the support of ERCIM ‘Alain Bensoussan’ Fellowship Programme ”.
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2021/1
Y1 - 2021/1
N2 - Accurate nuclei segmentation, as an indispensable basis and core link for multi-cell cervical image analysis, plays an important role in automatic pre-cancer detection. However, poor image quality due to the uneven staining, complex backgrounds and overlapped cell clusters poses a great challenge in nuclei segmentation. In this paper, we propose a new Selective-Edge-Enhancement-based Nuclei Segmentation method (SEENS). In the proposed method, selective search is integrated with mathematical operators to segment whole slide cervical images into small regions of interest (ROI) while automatically avoiding repeated segmentation as well as eliminating non-nuclei regions. In addition, an edge enhancement method based on the canny operator and mathematical morphology is presented to extract edge information as a weight to enhance the nucleus edge selectively. As a result, the enhanced ROI is then segmented by the Chan–Vese model with a higher accuracy. We evaluate our method with 18 whole slide images for a total of 395 cell nuclei. Experimental results demonstrate that SEENS achieves higher accuracy in cervical nuclei segmentation. Notably our method performs particularly better in low-contrast scenarios than baselines.
AB - Accurate nuclei segmentation, as an indispensable basis and core link for multi-cell cervical image analysis, plays an important role in automatic pre-cancer detection. However, poor image quality due to the uneven staining, complex backgrounds and overlapped cell clusters poses a great challenge in nuclei segmentation. In this paper, we propose a new Selective-Edge-Enhancement-based Nuclei Segmentation method (SEENS). In the proposed method, selective search is integrated with mathematical operators to segment whole slide cervical images into small regions of interest (ROI) while automatically avoiding repeated segmentation as well as eliminating non-nuclei regions. In addition, an edge enhancement method based on the canny operator and mathematical morphology is presented to extract edge information as a weight to enhance the nucleus edge selectively. As a result, the enhanced ROI is then segmented by the Chan–Vese model with a higher accuracy. We evaluate our method with 18 whole slide images for a total of 395 cell nuclei. Experimental results demonstrate that SEENS achieves higher accuracy in cervical nuclei segmentation. Notably our method performs particularly better in low-contrast scenarios than baselines.
KW - Canny operator
KW - Chan-Vese model
KW - Nuclei segmentation
KW - Selective edge enhancement
KW - Selective search
UR - http://www.scopus.com/inward/record.url?scp=85088977208&partnerID=8YFLogxK
U2 - 10.1016/j.future.2020.07.045
DO - 10.1016/j.future.2020.07.045
M3 - Journal article
AN - SCOPUS:85088977208
SN - 0167-739X
VL - 114
SP - 185
EP - 194
JO - Future Generation Computer Systems
JF - Future Generation Computer Systems
ER -