AbstractObjective To resolve the issue of poor automatic segmentation of the bowel in women with pelvic tumors, a Dense V-Network model was established, trained and evaluated to accurately and automatically delineate the bowel of female patients with pelvic tumors. Methods Dense Net and V-Net network models were combined to develop a Dense V-Network algorithm for automatic segmentation of 3D CT images. CT data were collected from 160 patients with cervical cancer, 130 of which were randomly selected as the training set to adjust the model parameters, and the remaining 30 were used as test set to evaluate the effect of automatic segmentation. Results Eight parameters including Dice similarity coefficient (DSC) were utilized to quantitatively evaluate the segmentation effect. The DSC value, JD,ΔV, SI, IncI, HD (cm), MDA (mm), and DC (mm) of the small intestine were 0.86±0.03,0.25±0.04,0.10±0.07,0.88±0.05,0.85±0.05,2.98±0.61,2.40±0.45 and 4.13±1.74, which were better than those of any other single algorithm. Conclusion Dense V-Network algorithm proposed in this paper can deliver accurate segmentation of the bowel organs. It can be applied in clinical practice after slight revision by physicians.
Fund:Digital Diagnosis and Treatment Equipment Development (2016YFC0105715);National Natural Science Foundation of China (61671204)
Corresponding Authors:
Ju Zhongjian, Email:15801234725@163.com
Cite this article:
Wu Qingnan,Guo Wen,Wang Jinyuan et al. Research on automatic segmentation of female bowel based on Dense V-Network neural network[J]. Chinese Journal of Radiation Oncology, 2020, 29(9): 790-795.
Wu Qingnan,Guo Wen,Wang Jinyuan et al. Research on automatic segmentation of female bowel based on Dense V-Network neural network[J]. Chinese Journal of Radiation Oncology, 2020, 29(9): 790-795.
[1] Wang Y, Kong W, Lv N, et al. Incidence of radiation enteritis in cervical cancer patients treated with definitive radiotherapy versus adjuvant radiotherapy[J]. J Cancer Res Ther, 2018, 14(8):120. DOI:10.4103/0973-1482.163762. [2] Nguyen NP, Antoine JE, Dutta S, et al. Current concepts in radiation enteritis and implications for future clinical trials[J]. Cancer, 2010, 95(5):1151-1163. DOI:10.1002/cncr.10766. [3] Kazemifar S, Balagopal A, Nguyen D, et al. Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning[J]. Biomed Phys Engin Expr, 2018, 4(5). DOI:10.1088/2057-1976/aad100. [4] Li D, Zang P, Chai X, et al. Automatic multiorgan segmentation in CT images of the male pelvis using region-specific hierarchical appearance cluster models[J]. Med Phys, 2016, 43(10):5426. DOI:10.1118/1.4962468. [5] Gao Y, Shao Y, Lian J, et al. Accurate segmentation of ct male pelvic organs via regression-based deformable models and multi-task random forests[J]. IEEE Trans Med Imaging, 2016, 35(6):1532-1543. DOI:10.1109/TMI.2016.2519264. [6] 孙宇晨, 张晓智, 李毅. 自动轮廓勾画软件构建图谱库在宫颈癌放疗中应用探讨[J]. 中华放射肿瘤学杂志, 2017, 26(10):1167-1172. DOI:10.3760/cma.j.issn.1004-4221.2017.10.013. Su YC, Zhang XZ, Li Y, et al. Discussion on the application of automatic contour drawing software to construct atlas in radiotherapy of cervical cancer[J]. Chin J Radiat Oncol, 2017, 26(10):1167-1172. DOI:10.3760/cma.j.issn.1004-4221.2017.10.013. [7] Balagopal A, Kazemifar S, Nguyen D, et al. Fully automated organ segmentation in male pelvic CT images[J]. Phys Med Biol, 2018, 63(24):245015. DOI:10.1088/1361-6560/aaf11c. [8] Bonmati E, Hu Y, Sindhwani N, et al. Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalizing neural network[J]. J Med Imaging, 2018, 5(2):021206. DOI:10.1117/1. JMI.5.2.021206. [9] Debats OA, Litjens GJ, Barentsz JO, et al. Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images[J]. Med Phys, 2011, 38(11):6178-6187. DOI:10.1118/1.3654162. [10] Brandao P, Zisimopoulos O, Mazomenos E, et al. Towards a computed-aided diagnosis system in colonoscopy:automatic polyp segmentation using convolution neural networks[J]. J Med Robot Res, 2018(1):1-13. DOI:10.1142/S2424905X18400020. [11] Dou Q, Yu L, Chen H, et al. 3D deeply supervised network for automated segmentation of volumetric medical images[J]. Med Imag Anal, 2017, 41(10):40-54. DOI:10.1016/j.media.2017.05.001. [12] Lu Y, Chen I, Kashani R, et al. SU-C-BRA-01:Interactive auto-segmentation for bowel in online adaptive MRI-guided radiation therapy by using a multi-region labeling algorithm[J]. Med Phys, 2016, 43(6):3320-3321. DOI:10.1118/1.4955562. [13] Zhang W, Liu J, Yao J, et al. Mesenteric vasculature-guided small bowel segmentation on 3-D CT[J]. IEEE Trans Med Imaging, 2013, 32(11):2006-2021. DOI:10.1109/TMI.2013.2271487. [14] Men K, Dai JR, Li YX. Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks[J]. Med Phys, 2017, 44(12):6377. DOI:10.1002/mp.12602. [15] Pan W, Qin J, Xiang X, et al. A smart mobile diagnosis system for citrus diseases based on densely connected convolutional networks[J]. IEEE Access, 2019, 7(99):87534-87542. DOI:10.1109/ACCESS.2019.2924973. [16] Khened M, Alex V, Krishnamurthi G. Fully convolutional multi-scale residual densenets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers[J]. Med Image Anal, 2018, 51(1):21-45. DOI:10.1016/j.media.2018.10.004. [17] Jégou S, Drozdzal M, Vazquez D, et al. The one hundred layers tiramisu:fully convolutional densenets for semantic segmentation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Stanford:IEEE, 2016:1175-1183. DOI:10.1109/CVPRW.2017.156. [18] Milletari F, Navab N, Ahmadi SA. V-Net:Fully convolutional neural networks for volumetric medical image segmentation[C]// Fourth International Conference on 3D Vision. Stanford:IEEE, 2016:565-571. DOI:10.1109/3dV.2016.79. [19] Casamitjana A, Catà M, Sánchez I, et al. Cascaded V-Net using ROI masks for brain tumor segmentation[C]// International MICCAI Brainlesion Workshop. Switzerland:Springer, 2017:381-391. DOI:10.1007/978-3-319-75238-9_33. [20] Zietman A, Elrassi I, Gaffney DK, et al. Pelvic normal tissue contouring guidelines for radiation therapy:a Radiation Therapy Oncology Group consensus panel atlas[J]. Int J Radiat Oncol Biol Phys, 2012, 83(3):e353-e362. DOI:10.1016/j.ijrobp.2012.01.023. [21] Daisne JF, Blumhofer A. Atlas-based automatic segmentation of head and neck organs at risk and nodal target volumes:a clinical validation[J]. Radiat Oncol, 2013, 8(1):154-154. DOI:10.1186/1748-717X-8-154. [22] Salleh SS, Aziz NAA, Mohamad D, et al. Combining mahalanobis and jaccard to improve shape similarity measurement in sketch recognition[C]// Uksim International Conference on Computer Modelling & Simulation. Cambridge:IEEE, 2011:319-324. DOI:10.1109/UKSIM.2011.67. [23] Macchia ml, Fellin F, Amichetti M, et al. Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer[J]. Radiat Oncol, 2012, 7(1):160. DOI:10.1186/1748-717X-7-160. [24] Wu Q, Wu XF, Li XW, et al. A modified image matching algorithm based on robust Hausdorff distance[J]. High Technol Lett, 2014, 20(01):29-33. DOI:10.3772/j.issn.1006-6748.2014.01.005. [25] Gao C, Li P, Zhang Y, et al. People counting based on head detection combining Adaboost and CNN in crowded surveillance environment[J]. Neurocomputing, 2016, 208(1):108-116.
2020, Vol. 29 
