TY - JOUR
T1 - Structure convolutional extreme learning machine and case-based shape template for HCC nucleus segmentation
AU - Li, Siqi
AU - Jiang, Huiyan
AU - Yao, Yu dong
AU - Pang, Wenbo
AU - Sun, Qingjiao
AU - Kuang, Li
N1 - Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2018/10/27
Y1 - 2018/10/27
N2 - Accurate segmentation of hepatocellular carcinoma (HCC) nuclei is of great importance in automatic pathologic diagnosis. This paper proposes structure convolutional extreme learning machine (SC-ELM) and case-based shape template (CBST) methods for HCC nucleus segmentation, which could tackle complex nucleus scenarios including adhesion or overlap. First, SC-ELM is developed for global segmentation of pathology images, which is used for coarse segmentation. Then, each connected region is considered as a nucleus clump and a probability model with three energy functions is proposed for contour refinement of nucleus clumps. Finally, for complex nucleus clumps, the CBST method combined with pixel-based classification is utilized for unclear or lost boundary inference. Experimentations with 127 liver pathology images demonstrate the performance advantages of our proposed method as compared with related work.
AB - Accurate segmentation of hepatocellular carcinoma (HCC) nuclei is of great importance in automatic pathologic diagnosis. This paper proposes structure convolutional extreme learning machine (SC-ELM) and case-based shape template (CBST) methods for HCC nucleus segmentation, which could tackle complex nucleus scenarios including adhesion or overlap. First, SC-ELM is developed for global segmentation of pathology images, which is used for coarse segmentation. Then, each connected region is considered as a nucleus clump and a probability model with three energy functions is proposed for contour refinement of nucleus clumps. Finally, for complex nucleus clumps, the CBST method combined with pixel-based classification is utilized for unclear or lost boundary inference. Experimentations with 127 liver pathology images demonstrate the performance advantages of our proposed method as compared with related work.
KW - Boundary inference
KW - Case-based shape template
KW - Nucleus segmentation
KW - Structure convolutional extreme learning machine
UR - http://www.scopus.com/inward/record.url?scp=85047248145&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047248145&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2018.05.013
DO - 10.1016/j.neucom.2018.05.013
M3 - Article
AN - SCOPUS:85047248145
SN - 0925-2312
VL - 312
SP - 9
EP - 26
JO - Neurocomputing
JF - Neurocomputing
ER -