边界加权的甲状腺癌病理图像细胞核分割方法

doi:10.19665/j.issn1001-2400.20230501

Abstract

Abstract:

Thyroid cancer is one of the most rapidly growing malignancies among all solid cancers.Pathological diagnosis is the gold standard for doctors to diagnose tumors,and nuclear segmentation is a key step in the automatic analysis of pathological images.Aiming at the low segmentation performance of existing segmentation methods on the nuclear boundary of the cell nucleus in the thyroid carcinoma pathological image,we propose an improved U-Net method based on boundary weighting for nuclear segmentation.This method uses the designed boundary weighting module,which can make the segmentation network pay more attention to the boundary of the nuclear.At the same time,in order to avoid the proposed network paying too much attention to the boundary and ignoring the main part of the nucleus,which leads to the failure for some lightly stained nuclei segmentation,we design a segmentation network to enhance the foreground area and suppresses the background area in the upsampling stage.In addition,we build a dataset for nuclear segmentation of thyroid carcinoma pathologic images named VIP-TCHis-Seg dataset.Our method achieves the Dice coefficient(Dice) of 85.26% and the pixel accuracy(PA) of 95.89% on self-built TCHis-Seg dataset,and achieves the Dice coefficient(Dice) of 81.03% and the pixel accuracy(PA) of 94.63% on common dataset MoNuSeg.Experimental results show that our method can achieve the best performance on both Dice and PA as well as effectively improve the segmentation accuracy of the network at the boundary compared with other methods.

Key words: papillary thyroid carcinoma, image segmentation, UNet, boundary weighting, foreground enhancement

CLC Number:

TP181

HAN Bing,GAO Lu,GAO Xinbo,CHEN Weiming. Nuclear segmentation method for thyroid carcinoma pathologic images based on boundary weighting[J].Journal of Xidian University, 2023, 50(5): 75-86.

Figures/Tables 18

References 26

[1]	FITZMAURICE C, ALLEN C, BARBER R M, et al. Global,Regional,and National Cancer Incidence,Mortality,Years of Life Lost,Years Lived with Disability,and Disability-Adjusted Life-Years for 32 Cancer Groups,1990 to 2015:A Systematic Analysis for the Global Burden of Disease Study[J]. JAMA Oncology, 2017, 3(4):524-548. doi: 10.1001/jamaoncol.2016.5688
[2]	LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-Based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324. doi: 10.1109/5.726791
[3]	RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Heidelberg:Springer, 2015:234-241.
[4]	ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++:A Nested U-Net Architecture for Medical Image Segmentation[C]//International Workshop on Deep Learning in Medical Image Analysis,Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Heidelberg:Springer, 2018:3-11.
[5]	HUANG H, LIN L, TONG R, et al. UNet 3+:A Full-Scale Connected UNet for Medical Image Segmentation[C]// IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Piscataway:IEEE, 2020:1055-1059.
[6]	ZHANG Z, LIU Q, WANG Y. Road Extraction by Deep Residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5):749-753. doi: 10.1109/LGRS.2018.2802944
[7]	JHA D, SMEDSRUD P H, RIEGLER M A, et al. ResUnet++:An Advanced Architecture for Medical Image Segmentation[C]// IEEE International Symposium on Multimedia (ISM). Piscataway:IEEE, 2019:225-230.
[8]	HU J, SHEN L, SUN G. Squeeze-and-Excitation Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:7132-7141.
[9]	CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking Atrous Convolution for Semantic Image Segmentation (2022)[J/OL].[2022-7-6]. https://arxiv.org/abs/1706.05587.
[10]	杨晓莉, 蔺素珍. 一种注意力机制的多波段图像特征级融合方法[J]. 西安电子科技大学学报, 2020, 47(1):120-127.
	YANG Xiaoli, LIN Suzhen. Method for Multi-Band Image Feature-Level Fusion Based on the Attention Mechanism[J]. Journal of Xidian University, 2020, 47(1):120-127.
[11]	回海生, 张雪英, 吴泽林, 等. 一种主辅路径注意力补偿的脑卒中病灶分割方法[J]. 西安电子科技大学学报, 2021, 48(4):200-208.
	HUI Haisheng, ZHANG Xueying, WU Zelin, et al. Method for Stroke Lesion Segmentation Using the Primary-Auxiliary Path Attention Compensation Network[J]. Journal of Xidian University, 2021, 48(4):200-208.
[12]	马思珂, 赵萌, 石凡, 等. 注意力驱动的细胞团簇细胞核分割算法[J]. 西安电子科技大学学报, 2022, 49(2):198-206.
	MA Sike, ZHAO Meng, SHI Fan, et al. Attention Driven Nuclei Segmentation Method for Cell Clusters[J]. Journal of Xidian University, 2022, 49(2):198-206.
[13]	FU H, CHENG J, XU Y, et al. Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation[J]. IEEE Transactions on Medical Imaging, 2018, 37(7):1597-1605. doi: 10.1109/TMI.2018.2791488 pmid: 29969410
[14]	QIN X, ZHANG Z, HUANG C, et al. U2-Net:Going Deeper with Nested U-Structure for Salient Object Detection[J]. Pattern Recognition, 2020, 106:107404. doi: 10.1016/j.patcog.2020.107404
[15]	GAO Y, ZHOU M, METAXAS D N. UTNet:A Hybrid Transformer Architecture for Medical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Heidelberg:Springer, 2021:61-71.
[16]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[J]. Advancesin Neural Information Processing Systems, 2017,30.
[17]	WU T, TANG S, ZHANG R, et al. CGnet:A Light-Weight Context Guided Network for Semantic Segmentation[J]. IEEE Transactions on Image Processing, 2020, 30:1169-1179. doi: 10.1109/TIP.83
[18]	CHEN H, QI X, YU L, et al. DCAN:Deep Contour-Aware Networks for Accurate Gland Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2487-2496.
[19]	ZENG Z, XIE W, ZHANG Y, et al. RIC-Unet:An Improved Neural Network Based on UNet for Nuclei Segmentation in Histology Images[J]. IEEE Access, 2019, 7:21420-21428. doi: 10.1109/ACCESS.2019.2896920
[20]	ODA H, ROTH H R, CHIBA K, et al. BESNet:Boundary-Enhanced Segmentation of Cells in Histopathological Images[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Heidelberg:Springer, 2018:228-236.
[21]	ZHOU Y, ONDER O F, DOU Q, et al. CIA-Net:Robust Nuclei Instance Segmentation with Contour-Aware Information Aggregation[C]//International Conference on Information Processing in Medical Imaging. Heidelberg:Springer, 2019:682-693.
[22]	NAYLOR P, LAE M, REYAL F, et al. Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map[J]. IEEE Transactions on Medical Imaging, 2018, 38(2):448-459. doi: 10.1109/TMI.42
[23]	CHENG F, CHEN C, WANG Y, et al. Learning Directional Feature Maps for Cardiac MRI Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Heidelberg:Springer, 2020:108-117.
[24]	HAN B, ZHANG M, GAO X, et al. Automatic Classification Method of Thyroid Pathological Images Using Multiple Magnification Factors[J]. Neurocomputing, 2021, 460:231-242. doi: 10.1016/j.neucom.2021.07.024
[25]	RUSSELL B, TORRALBA A, MURPHY K, et al. LabelMe:a Database and Web-Based Tool for Image Annotation[J]. International Journal of Computer Vision, 2008, 77(1):157-173. doi: 10.1007/s11263-007-0090-8
[26]	KUMAR N, VERMA R, SHARMA S, et al. A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology[J]. IEEE Transactions on Medical Imaging, 2017, 36(7):1550-1560. doi: 10.1109/TMI.2017.2677499 pmid: 28287963

	图像数量/张	细胞核数量/个
不含有癌变细胞图像	116	8 093
含有癌变细胞图像	108	8 920
共计	224	17 013

k	Dice	PA
1	78.49	89.11
3	79.23	90.03
5	85.26	95.89
7	81.53	92.65

α	β	Dice/%	PA/%
1.0	0.0	82.19	92.07
0.9	0.1	82.47	92.14
0.8	0.2	82.34	91.39
0.7	0.3	84.98	94.54
0.6	0.4	85.26	95.89
0.5	0.5	84.76	95.72
0.4	0.6	82.91	93.63
0.3	0.7	80.66	91.30
0.2	0.8	80.70	90.24
0.1	0.9	76.01	85.16
0.0	1.0	69.52	82.83

边界加权模块	前景增强模块	Dice	PA
是	否	80.25	90.61
否	是	83.71	95.19
是	是	85.26	95.89

不同损失函数	Dice	PA
文中损失函数	85.26	95.89
二元交叉熵损失函数	82.28	93.90

Nuclear segmentation method for thyroid carcinoma pathologic images based on boundary weighting

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 18

References 26

Related Articles 15

Metrics

Comments

Recommended 10

方法	Dice	PA
U-Net^[3]	79.01	91.70
U-Net 3+^[5]	80.02	93.91
DCAN^[18]	80.69	92.35
RIC-Unet^[19]	81.03	92.49
BESNet^[20]	82.74	93.21
CIA-Net^[21]	83.35	93.68
CGNet^[17]	83.48	93.75
UTNet^[15]	83.64	93.59
文中方法	85.26	95.89

方法	Dice	PA
U-Net^[3]	74.78	87.22
U-Net 3+^[5]	75.96	90.17
DCAN^[18]	78.09	91.56
RIC-Unet^[19]	78.18	91.98
CGNet^[17]	78.76	92.65
BESNet^[20]	79.25	92.79
UTNet^[15]	79.27	92.42
CIA-Net^[21]	80.61	94.10
文中方法	81.03	94.63

[1]	ZHOU Peng,YANG Jun. Semantic segmentation of remote sensing images based on neural architecture search [J]. Journal of Xidian University, 2021, 48(5): 47-57.
[2]	LIU Zhiqiang,ZHANG Mingjin,CHI Yuan,LI Yunsong. Hardware Trojan detection algorithm based on deep learning [J]. Journal of Xidian University, 2019, 46(6): 37-45.
[3]	WU Chengmao;SHANGGUAN Ruoyu. Neutrosophic fuzzy clustering segmentation algorithm based on HMRF [J]. Journal of Xidian University, 2017, 44(6): 103-108+121.
[4]	WANG Yunfei;BI Duyan;LIU Huawei;LIU Ling;ZHAO Xiaolin. Locally-restricted regular clustering superpixel algorithm [J]. Journal of Xidian University, 2016, 43(3): 95-100.
[5]	GAN Lu;WU Yan;WANG Fan. Unsupervised SAR image segmentation using TMF and belief propagation [J]. J4, 2015, 42(6): 49-55.
[6]	ZHANG Zejun;SHUI Penglang. SAR images segmentation algorithm using chain coding grid in G⁰ distribution [J]. J4, 2015, 42(5): 48-54.
[7]	WANG Weiwei;YANG Gongpeng;Lü Chang;YANG Yanqi. New image segmentation model based on the level set method [J]. J4, 2013, 40(6): 39-45+91.
[8]	ZHANG Wenjuan;FENG Xiangchu. Image super-pixels segmentation method based on the non-convex low-rank and sparse constraints [J]. J4, 2013, 40(5): 86-91.
[9]	WANG Yunfei;BI Duyan;HUANG Fei. Improved isoperimetric algorithm for image segmentation [J]. J4, 2012, 39(2): 87-94+212.
[10]	MA Miao;LIANG Jianhui;GUO Min. SAR image thresholding segmentation based on the bacteria foraging algorithm [J]. J4, 2011, 38(6): 152-158+178.
[11]	CUI Yanpeng；HU Jianwei；YANG Shaoquan；ZHU Yan. SAR image automatic segmentation based on DT-GrowCut [J]. J4, 2011, 38(3): 150-154.
[12]	LIU Jianlei;FENG Dazheng. Non-homogenous image segmentation with global optimization [J]. J4, 2011, 38(2): 66-71.
[13]	XU Jianjun;GAO Shan;BI Duyan;CHEN You. A novel image segmentation algorithm [J]. J4, 2011, 38(1): 8-15.
[14]	LIU Han-qiang;JIAO Li-cheng;ZHAO Feng. SAR image multilevel segmentation based on local similarity measure [J]. J4, 2010, 37(6): 1071-1076.
[15]	LIU Qing;XU Lu-ping;MA Yi-de;SU Zhe;WANG Yong. Automated image segmentation using the ULPCNN model with ultra-fuzzy entropy [J]. J4, 2010, 37(5): 817-824.