Rectal tumor segmentation method based on improved U-Net model
GAO Haijun1, ZENG Xiangyin2, PAN Dazhi1,3, ZHENG Bochuan1,3
1. School of Mathematics&Information, China West Normal University, Nanchong Sichuan 637009, China; 2. School of Computer Science, China West Normal University, Nanchong Sichuan 637009, China; 3. Institute of Computing Method and Application Software, China West Normal University, Nanchong Sichuan 637009, China
Abstract：In the diagnosis of rectal cancer, if the rectal tumor area can be automatically and accurately segmented from Computed Tomography (CT) images, it will help doctors make a more accurate and rapid diagnosis. Aiming at the problem of rectal tumor segmentation, an automatic segmentation method of rectal tumor based on improved U-Net model was proposed. Firstly, the sub coding modules were embedded in the U-Net model encoder of different levels to improve the feature extraction ability of the model. Secondly, by comparing the optimization performances of different optimizers, the most suitable optimizer was determined to train the model. Finally, data augmentation was performed to the training set to make the model more fully trained, so as to improve the segmentation performance. Experimental results show that compared with U-Net, Y-Net and FocusNetAlpha network models, the segmentation region obtained by the improved model is closer to the real tumor region, and the segmentation performance of this model for small objects is more prominent; at the same time, the proposed model is superior to other three models on three evaluation indexes including precision, recall and Dice coefficient, which can effectively segment the rectal tumor area.
[1] 第七届"泰迪杯"数据挖掘挑战赛——B题:直肠癌淋巴结转移的智能诊断[EB/OL].[2019-04-13].http://www.tipdm.org/u/cms/www/201903/15214944i2k3.pdf. (The Seventh "Teddy Cup" Data Mining Challenge Competition-intelligent diagnosis of lymph node metastasis in rectal cancer[EB/OL].[2020-01-10].http://www.tipdm.org/u/cms/www/201903/15214944i2k3.pdf.) [2] SIEGEL R L, MILLER K D, SAUER A G, et al. Colorectal cancer statistics, 2020[J]. CA:A Cancer Journal for Clinicians, 2020, 70(3):145-164. [3] KOLLIGS F T. Diagnostics and epidemiology of colorectal cancer[J]. Visceral Medicine, 2016, 32(3):158-164. [4] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham:Springer, 2015:234-241. [5] ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++:a nested U-Net architecture for medical image segmentation[C]//Proceedings of the 2018 International Workshop on Deep Learning in Medical Image Analysis, 2018 International Workshop on Multimodal Learning for Clinical Decision, LNCS 11045. Cham:Springer, 2018:3-11.) [6] ALOM M Z, YAKOPCIC C, TAHA T M, et al. Nuclei segmentation with Recurrent Residual convolutional neural networks based U-Net (R2U-Net)[C]//Proceedings of the 2018 IEEE National Aerospace and Electronics Conference. Piscataway:IEEE, 2018:228-233. [7] OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net:Learning where to look for the pancreas[EB/OL].[2019-04-13].https://arxiv.org/pdf/1804.03999.pdf. [8] AZAD R, ASADI-AGHBOLAGHI M, FATHY M, et al. Bi-directional ConvLSTM U-Net with densley connected convolutions[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop. Piscataway:IEEE, 2019:406-415. [9] KAUL C, MANANDHAR S, PEARS N. FocusNet:an attention-based fully convolutional network for medical image segmentation[C]//Proceedings of the IEEE 16th International Symposium on Biomedical Imaging. Piscataway:IEEE, 2019:455-458. [10] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778. [11] LI X, CHEN H, QI X, et al. H-DenseUNet:hybrid densely connected UNet for liver and tumor segmentation from CT volumes[J]. IEEE Transactions on Medical Imaging, 2018, 37(12):2663-2674. [12] MOHAMMED A K, YILDIRIM-YAYILGAN S, FARUP I, et al. Y-Net:a deep convolutional neural network for polyp detection[C]//Proceedings of the 29th British Machine Vision Conference. Durham:BMVA Press, 2018:No.487. [13] KAUL C, PEARS N, MANANDHAR S. Divided we stand:a novel residual group attention mechanism for medical image segmentation[EB/OL].[2020-03-17].https://arxiv.org/pdf/1912.02079.pdf. [14] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis, 2017, 42:60-88. [15] TAJBAKHSH N, JEYASEELAN L, LI Q, et al. Embracing imperfect datasets:a review of deep learning solutions for medical image segmentation[J]. Medical Image Analysis, 2020, 63:No.101693. [16] TAGHANAKI S A, ABHISHEK K, COHEN J P, et al. Deep semantic segmentation of natural and medical images:a review[EB/OL].[2020-03-17].https://arxiv.org/pdf/1910.07655.pdf. [17] IRVING B, CIFOR A, PAPIEŻ B W, et al. Automated colorectal tumour segmentation in DCE-MRI using supervoxel neighbourhood contrast characteristics[C]//Proceedings of the 2014 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 8673. Cham:Springer, 2014:609-616. [18] VAN HEESWIJK M M, LAMBREGTS D M J, VAN GRIETHUYSEN J J M, et al. Automated and semiautomated segmentation of rectal tumor volumes on diffusion-weighted MRI:can it replace manual volumetry?[J]. International Journal of Radiation Oncology Biology Physics, 2016, 94(4):824-831. [19] SOOMRO M H, GIUNTA G, LAGHI A, et al. Segmenting MR images by level-set algorithms for perspective colorectal cancer diagnosis[C]//Proceedings of the 2017 European Congress on Computational Methods in Applied Sciences and Engineering, LNCVB 27. Cham:Springer, 2017:396-406. [20] 冉昭,简俊明,王蒙蒙,等. 基于全卷积神经网络的直肠癌肿瘤磁共振影像自动分割方法[J].北京生物医学工程, 2019, 38(5):465-471. (RAN Z, JIAN J M, WANG M M, et al. Automatic segmentation method based on full convolution neural network for rectal cancer tumors in magnetic resonance image[J]. Beijing Biomedical Engineering, 2019, 38(5):465-471.) [21] 段杰,崔志明,沈艺,等. 一种改进FCN的肝脏肿瘤CT图像分割方法[J]. 图形学报, 2020, 41(1):100-107. (DUAN J, CUI Z M, SHEN Y, et al. A CT image segmentation method for liver tumor by an improved FCN[J]. Journal of Graphics, 2020, 41(1):100-107.) [22] TREBESCHI S, VAN GRIETHUYSEN J J M, LAMBREGTS D M J, et al. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR[J]. Scientific Reports,2017, 7(1):No.5301. [23] WANG J, LU J, QIN G, et al. Technical note:a deep learning-based auto segmentation of rectal tumors in MR images[J]. Medical Physics, 2018, 45(6):2560-2564. [24] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO:common objects in context[C]//Proceedings of 2014 European Conference on Computer Vision, LNCS 8693. Cham:Springer, 2014:740-755. [25] DUBEY S R, CHAKRABORTY S, ROY S K, et al. diffGrad:an optimization method for convolutional neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019(Early Access):1-12. [26] SUTSKEVER I, MARTENS J, DAHL G, et al. On the importance of initialization and momentum in deep learning[C]//Proceedings of the 30th International Conference on Machine Learning. New York:JMLR.org, 2013:1139-1147. [27] ZEILER D Z. ADADELTA:an adaptive learning rate method[EB/OL].[2020-03-17].https://arxiv.org/pdf/1212.5701.pdf. [28] DUCHI J, HAZAN E, SINGER Y. Adaptive subgradient methods for online learning and stochastic optimization[J]. The Journal of Machine Learning Research, 2011, 12:2121-2159. [29] HINTON G, SRIVASTAVA N, SWERSKY K. Neural networks for machine learning:lecture 6a overview of mini-batch gradient descent[EB/OL].[2020-03-17].https://www.cs.toronto.edu/~hinton/coursera/lecture6/lec6.pdf. [30] REDDI S J, KALE S, KUMAR S. On the convergence of Adam and beyond[EB/OL].[2020-03-17].https://arxiv.org/pdf/1904.09237.pdf. [31] KINGMA D P, BA J L. Adam:a method for stochastic optimization[EB/OL].[2020-03-17].https://arxiv.org/pdf/1412.6980.pdf.
2020, Vol. 40 
