Semi-supervised Nuclei Segmentation Based on Consistency Regularization Constraint
SHU Jianhua1, NIAN Fudong2, LÜ Gang2
1. School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei 230012 2. School of Advanced Manufacturing Engineering, Hefei University, Hefei 230601
Abstract：Aiming at the high cost of medical image data acquisition with high quality annotation, a semi-supervised nuclei segmentation algorithm based on consistency regularization constraint is proposed. Firstly, two master and slave networks with the same structure are constructed, and the same random initialization parameters are assigned to them. Then, the labeled and unlabeled training data are randomly selected to input into the master and slave networks. Regularization term is utilized to constrain the training of master and slave networks to keep the output results consistent. The parameters of master network are optimized by gradient descent method, and the parameters of the slave network are optimized by the exponential moving average of the parameters of master network in each iteration batches. Experiments on public datasets verify the effectiveness of the proposed algorithm.
[1] GENG Q C, ZHOU Z, CAO X C. Survey of Recent Progress in Semantic Image Segmentation with CNNs. Science China(Information Sciences), 2018, 61(5): 107-124. [2] ANWAR S M, MAJID M, QAYYUM A, et al. Medical Image Ana-lysisUsingConvolutionalNeuralNetworks: A Review[C/OL]. [2020-03-12]. https://link.springer.com/article/10.1007/s10916-018-1088-1. [3] KOHLI M D, SUMMERS R M, GEIS J R. Medical Image Data and Datasets in the Era of Machine Learning-Whitepaper from the 2016 C-MIMI Meeting Dataset Session. Journal of Digital Imaging, 2017, 30(4): 392-399. [4] YOU X G, PENG Q M, YUAN Y, et al. Segmentation of Retinal Blood Vessels Using the Radial Projection and Semi-supervised Approach. Pattern Recognition, 2011, 44(10/11): 2314-2324. [5] PORTELA N M, CAVALCANTI G D C, REN T I. Semi-supervised Clustering for MR Brain Image Segmentation. Expert Systems with Applications, 2014, 41(4): 1492-1497. [6] GU L, ZHENG Y Q, BISE R, et al. Semi-supervised Learning for Biomedical Image Segmentation via Forest Oriented Super Pixels(Voxels) // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2017: 702-710. [7] JAISAKTHI S M, CHANDRABOSE A, MIRUNALINI P. Automatic Skin Lesion Segmentation Using Semi-supervised Learning Technique[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1703.04301v1.pdf. [8] BAI W J, OKTAY O, SINCLAIR M, et al. Semi-supervised Lear-ning for Network-Based Cardiac MR Image Segmentation // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2017: 253-260. [9] SEDAI S, MAHAPATRA D, HEWAVITHARANAGE S, et al. Se-mi-supervised Segmentation of Optic Cup in Retinal Fundus Images Using Variational Autoencoder // Proc of the International Confe-rence on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2017: 75-82. [10] NIE D, GAO Y Z, WANG L, et al. ASDNet: Attention Based Semi-supervised Deep Networks for Medical Image Segmentation // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2018: 370-378. [11] CHARTSIAS A, JOYCE T, PAPANASTASIOU G, et al. Factorised Spatial Representation Learning: Application in Semi-supe-rvised Myocardial Segmentation // Proc of the International Confe-rence on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2018: 490-498. [12] ZHOU Y Y, WANG Y, TANG P, et al. Semi-supervised 3D Abdominal Multi-organ Segmentation via Deep Multi-planar Co-training // Proc of the IEEE Winter Conference on Applications of Computer Vision. Washington, USA: IEEE, 2019: 121-140. [13] PENG J Z, ESTRADA G, PEDERSOLI M, et al. Deep Co-trai-ning for Semi-supervised Image Segmentation[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1903.11233.pdf. [14] BORTSOVA G, DUBOST F, HOGEWEG L, et al. Semi-supervised Medical Image Segmentation via Learning Consistency under Transformations // Proc of the International Conference on Medical ImageComputingandComputer-AssistedIntervention.Berlin, Germany: Springer, 2019: 810-818. [15] LI X M, YU L Q, CHEN H, et al. Transformation-Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1903.00348.pdf. [16] SAJJADI M, JAVANMARDI M, TASDIZEN T. Regularization with Stochastic Transformations and Perturbations for Deep Semi-supervised Learning[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1606.04586.pdf. [17] LAINE S, AILA T. Temporal Ensembling for Semi-supervised Learning[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1610.02242.pdf. [18] RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2015: 234-241. [19] ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1912.05074.pdf. [20] KINGMA D P, BA J. Adam: A Method for Stochastic Optimization[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1412.6980.pdf. [21] HUNG W C, TSAI Y H, LIOU Y T, et al. Adversarial Learning for Semi-supervised Semantic Segmentation[C/OL]. [2020-03-12]. https://arxiv.org/pdf/1802.07934.pdf.
2020, Vol. 33 
