08 基于边缘检测的乳腺癌细胞核分割预测图融合算法

闫伟鑫;吕晓琪;谷宇;

• 1:内蒙古科技大学信息工程学院内蒙古自治区模式识别与智能处理重点实验室

• 2:内蒙古工业大学信息工程学院

• 
  

摘要(Abstract)：

目前针对病理学图像中的乳腺癌细胞核分割研究中，乳腺癌细胞核分割结果中存在边缘欠分割，过分割等问题.由此提出了一种基于边缘检测的分割预测图融合算法(UDE-M),该算法主要为两个步骤，一是通过U-Net, DeepLab V3对数据集进行训练获取分割预测图，二是通过算法中的逻辑判别规则进行融合获取最终的分割结果.研究结果表明：UDE-M算法Accuracy值达到了92.5%, Precision值达到了77.3%,Recall达到了83.8%,F1分数值达到了80.4%,相比于U-Net和DeepLab V3以及文中组成的FDE-M模型和SDE-M模型，能够更加有效对乳腺癌细胞核进行分割.

关键词(KeyWords)： 乳腺癌;边缘检测;细胞核分割;预测图融合

基金项目(Foundation): 国家自然科学基金资助项目(62001255,61771266,61841204);; 内蒙古自治区科技计划资助项目(2019GG138);; 中央引导地方科技发展资金资助项目(2021ZY0004);; 内蒙古自治区自然科学资助项目(2019MS06003,2015MS0604);; 内蒙古自治区高等学校科学研究基金资助项目(NJZY145);; 教育部“春晖计划”合作科研资助项目：“基于Hessian选择性增强滤波及粒子群参数优化支持向量机的影像大数据肺癌辅助检测诊断技术研究”(教外司留[2019]1383号)

作者(Authors): 闫伟鑫;吕晓琪;谷宇;

DOI: 10.16559/j.cnki.2095-2295.2023.01.008

参考文献(References)：

• [1] YANG X,LI H,ZHOU X.Nuclei segmentation using marker-controlled watershed,tracking using mean-shift,and Kalman filter in time-lapse microscopy[J].IEEE Transactions on Circuits and Systems I:Regular Papers,2006,53(11):2405.

• [2] ZHOU X,LIU K Y,BRADLEY P,et al.Towards automated cellular image segmentation for RNAi genome-wide screening[C]//International conference on medical image computing and computer-assisted intervention.Berlin,Heidelberg:Springer,2005:885.

• [3] ZHAO L,LI K,WANG M,et al.Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF[J].Computers in Biology and Medicine,2016,71:46.

• [4] NOIRCLERC N,MARLIERE S,BAKHTI A,et al.Impact of a micro-net mesh technology covering stent on coronary microvascular dysfunction in patients with high thrombus burden[J].Catheterization and Cardiovascular Interventions,2022,99(2):397.

• [5] 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.Cham:Springer,2019:682.

• [6] ZHOU Z,SODHA V,Rahman Siddiquee M M,et al.Models genesis:Generic autodidactic models for 3d medical image analysis[C]//International conference on medical image computing and computer-assisted intervention.Cham:Springer,2019:384.

• [7] 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.Cham:Springer,2015:234.

• [8] WANG Y,SUN S,YU J,et al.Skin lesion segmentation using atrous convolution via DeepLab V3[J].arXiv preprint arXiv:1807.08891,2018.

• [9] KUMAR M.Nuclear energy strategies in the UK and Finland:a critical evaluation on current and future prospective[J].International Journal of Nuclear Governance,Economy and Ecology,2014,4(2):115.

• [10] LV L,LU J,ZHAO T,et al.A CD8+ T Cell-related genes expression signature predicts prognosis and the efficacy of immunotherapy in breast cancer[J].Journal of Mammary Gland Biology and Neoplasia,2022,27(1):53.

• [11] WANG Y,JIA Y,TIAN Y,et al.Deep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoring[J].Expert Systems with Applications,2022,200:117013.

• [12] SHELHAMER E,LONG J,DARRELL T,et al.Fully convolutional networks for semantic segmentation[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2017,39(4):640.

• [13] BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481.

• [14] O’REILLY E A,GUBBINS L,SHARMA S,et al.The fate of chemoresistance in triple negative breast cancer (TNBC)[J].BBA Clinical,2015,3:257.