陕西科技大学电子信息与人工智能学院;
细胞核精准分割是病理诊断的基础工作，针对目前乳腺癌细胞核图像重叠、粘连严重、边界不清晰等问题，提出了一种改进的残差U型分割模型。该模型在ResUNet模型每层通道连接处根据卷积层深浅不同添加了大小不同的残差路径，减小深浅层卷积间的语义差距，充分进行图像间深、浅层特征信息的融合，有利于细胞核的定位和分割。实验结果显示，该模型在乳腺癌数据集上MIoU,Dice, Acc等评价指标分别达到81%,80%,95%,较ResUNet模型分别提升了1.8%,2.1%,0.6%。在DSB数据集上进行了验证，MIoU,Dice, Acc等评价指标较ResUNet模型分别提升了0.6%,1.6%,0.4%。验证结果表明，该模型具有较好的模型泛化能力和分割准确率，能够提高乳腺癌细胞核分割的精确度，为乳腺疾病诊断提供重要的依据。
| 836 | 5 | 26 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] 刘宗超，李哲轩，张阳，等.2020全球癌症统计报告解读[J].肿瘤综合治疗电子杂志，2021,7(2):1-14.
[2] LYU M,ZHOU S,ZHU Q.Research Progresses of Breast Ultrasound Computer Aided Diagnosis Systems Based on Deep Learning[J].Chinese Journal of Medical Imaging Technology,2020,36(11):1722-1725.
[3] SU H,LIU F J,XIE Y P,et al.Region Segmentation in Histopathological Breast Cancer Images Using Deep Convolutional Neural Network[C]//2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).Brooklyn:IEEE,2015:55-58.
[4] XU J,LUO X,WANG G,et al.A Deep Convolutional Neural Network for Segmenting and Classifying Epithelial and Stromal Regions in Histopathological Images[J].Neurocomputing,2016,191:214-223.
[5] SAHA M,CHAKRABORTY C.Her2Net:A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation[J].IEEE Transactions on Image Processing,2018,27(5):2189-2200.
[6] WANG W J,CHEN J X,ZHAO J,et al.Automated Segmentation of Pulmonary Lobes Using Coordination-guided Deep Neural Networks[C]//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).Venice:IEEE,2019:1353-1357.
[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.Munich:Springer,2015:234-241.
[8] XIAO X,LIAN S,LUO Z M,et al.Weighted Res-UNet for High-quality Retina Vessel Segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education (ITME).Hangzhou:IEEE,2018:327-331.
[9] YI M Y,MENG Q,CHEN W,et al.Towards Accelerating Training of Batch Normalization:A Manifold Perspective[J/OL].(2021-01-08)[2022-05-10].https://arxiv.org/abs/2101.02916.
[10] SANDLER M,HOWARD A,ZHUM L,et al.Mobilenetv2:Inverted Residuals and Linear Bottlenecks[C]//IEEE/CVG Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:4510-4520.
[11] NAYLOR P,LAé M,REYAL F,et al.Nuclei Segmentation in Histopathology Images Using Deep Neural Networks[C]//2017 IEEE 14th International Symposium on Biomedical Imaging(ISBI 2017).Melbourne:IEEE,2017:933-936.
[12] YANG S H,ZHU X L,ZHANG L,et al.Classification and Prediction of Tibetan Medical Syndrome Based on the Improved BP Neural Network[J].IEEE Access,2020,8:31114-31125.
[13] 梁杰，陈嘉豪，张雪芹，等.基于独热编码和卷积神经网络的异常检测[J].清华大学学报(自然科学版),2019,59(7):523-529.
[14] BADRINARAYANAN V,HANDA A,CIPOLLAR.Segnet:A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-wise Labelling[J/OL].(2015-05-27)[2022-05-10].https://arxiv.org/abs/1505.07293.
[15] LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[J/OL].(2014-11-14)[2022-05-13].http://de.arxiv.org/pdf/1411.4038.
[16] SHI J Y,DANG J,CUI M D,et al.Improvement of Damage Segmentation Based on Pixel-level Data Balance Using VGG-Unet[J].Applied Sciences,2021,11(2):518.1-518.17.
[17] GUAN S,KHAN A A,SIKDARS,et al.Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal[J].IEEE Journal of Biomedical and Health Informatics,2020,24(2):568-576.
[18] 李立鹏，师菲蓬，田文博，等.基于残差网络和迁移学习的野生植物图像识别方法[J].无线电工程，2021,51(9):857-863.
基本信息:
DOI：
中图分类号:TP391.41;R737.9
引用信息:
[1]陈立,魏钰欣,刘斌等.基于改进ResUNet的乳腺癌细胞核图像分割[J].无线电工程,2022,52(12):2132-2140.
基金信息:
国家自然科学基金(61871260)~~