<address id="xrvvb"><listing id="xrvvb"></listing></address>

          <form id="xrvvb"></form>

          <address id="xrvvb"></address>

          華中科技大學學報(自然科學版) 2020, Vol. 48 Issue (9): 76-81 DOI10.13245/j.hust.200913

          欄目:電子與信息工程
          用于腹部CT肝臟分割的邊界監督模型
          于凌濤 a , 王鵬程 a , 張 瑩 b , 夏永強 a
          a. 哈爾濱工程大學機電工程學院,黑龍江 哈爾濱 150001
          b. 哈爾濱醫科大學附屬第二醫院血液內科,黑龍江 哈爾濱150081
          摘要 針對肝臟分割影像中模糊的肝臟邊界,提出了一種新穎的用于腹部CT肝臟分割的邊界監督模型.該模型包括肝臟區域分割模塊和邊界分割模塊,其中邊界分割模塊使用肝臟邊界進行監督訓練,輸出精準的肝臟邊界.模型將肝臟區域分割輸出與邊界分割輸出融合在一起,得到最終的肝臟分割預測.肝臟區域分割模塊與邊界分割模塊分別設置了相應的損失函數進行監督訓練.模型使用腹部器官分割挑戰提供的數據集進行了消融實驗并與先進模型進行了評估.結果證明該方法的有效性和優異性,提出的邊界分割模塊有助于保留肝臟的邊緣信息,提高了肝臟分割的性能.
          關鍵詞 醫學圖像分析 ;腹部肝臟器官分割 ;肝臟分割 ;深度學習 ;邊界監督 ;融合損失函數
          Boundary supervision network for abdominal CT liver segmentation
          YU Lingtao a , WANG Pengcheng a , ZHANG Ying b , XIA Yongqiang a
          a. College of Mechanical and Electrical Engineering,Harbin Engineering University,Harbin 150001,China
          b. Department of Hematology,The Second Affiliated Hospital of Harbin Medical University,Harbin 150081,China
          Abstract The difficulty of liver segmentation mainly focuses on the blurred liver boundary in the image.Aiming at this challenge,a novel boundary supervision model for abdominal CT liver segmentation was proposed.The model included a liver region segmentation module and a boundary segmentation module.The boundary segmentation module used liver boundaries for supervised training and outputs accurate liver boundaries.The liver region segmentation module and the boundary segmentation module respectively set corresponding loss functions for supervised training.The model was subjected to ablation experiments on the data set provided by CHAOS challenge and evaluated with advanced models.The results prove the effectiveness and superiority of our method.The boundary segmentation module proposed helps to preserve the edge information of the liver and improves the performance of liver segmentation.
          Keywords medical image analysis ; abdominal liver organ segmentation ; liver segmentation ; deep learning ; boundary supervision ; fusion loss function
          基金資助黑龍江省自然科學基金資助項目(LH2019F016)

          中圖分類號TP391
          文獻標志碼A
          文章編號1671-4512(2020)09-0076-06
          參考文獻
          [1] GIBSON E,GIGANTI F,HU Y,et al.Automatic multi-organ segmentation on abdominal CT with dense V-networks[J].IEEE Transactions on Medical Imaging,2018,37(8):1822-1834.
          [2] ROTH H R,SHEN C,ODA H,et al.Deep learning and its application to medical image segmentation[J].Medical Imaging Technology,2018,36(2):63-71.
          [3] BEICHEL R,BAUER C,BORNIK A,et al.Liver segmentation in CT data:a segmentation refinement approach[C]// Proc of MICCAI Workshop on 3D Segmentation in the Clinic:A Grand Challenge.Berlin:Springer,2007:235-245.
          [4] DAWANT B M,LI R,LENNON B,et al.Semi-automatic segmentation of the liver and its evaluation on the MICCAI 2007 grand challenge data set[C]// Proc of MICCAI Workshop on 3D Segmentation in the Clinic:A Grand Challenge.Berlin:Springer,2007:215-221.
          [5] SLAGMOLEN P,ELEN A,SEGHERS D,et al.Atlas based liver segmentation using nonrigid registration with a B-spline transformation model[C]// Proc of MICCAI Workshop on 3D Segmentation in the Clinic:A Grand Challenge.Berlin:Springer,2007:197-206.
          [6] LI G,CHEN X,SHI F,et al.Automatic liver segmentation based on shape constraints and deformable graph cut in CT images[J].IEEE Transactions on Image Processing,2015,24(12):5315-5329.
          [7] CERROLAZA J J,REYES M,SUMMERS R M,et al.Automatic multi-resolution shape modeling of multiorgan structures[J].Medical Image Analysis,2015,25(1):S1361841515000535.
          [8] XU Z,BURKE R P,LEE C P,et al.Efficient abdominal segmentation on clinically acquired CT with SIMPLE context learning[J].Medical Imaging Analysis,2015,24(1):18-27.
          [9] HU P,WU F,PENG J,et al.Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets[J].International Journal of Computer Assisted Radiology and Surgery,2017,12(3):399-411.
          [10] CHEN X,ZHANG R,YAN P.Feature fusion encoder decoder network for automatic liver lesion segmentation[DB/OL].[2019-03-28].https://arxiv.org/abs/1903. 11834.
          [11] ZHOU X,TAKAYAMA R,WANG S,et al.Automated segmentation of 3D anatomical structures on CT images by using a deep convolutional network based on end-to-end learning approach[C]// Proc of Medical Imaging 2017:Image Processing.Orlando:SPIE Medical Imaging,2017:1013324.
          [12] LANDMAN B A,BOBO M F,HUO Y,et al.Fully convolutional neural networks improve abdominal organ segmentation[C]// Proc of Medical Imaging 2018:Image Processing.Houston:SPIE Medical Imaging,2018:105742V.
          [13] JIANG H,SHI T,BAI Z,et al.AHCNet:an application of attention mechanism and hybrid connection for liver tumor segmentation in CT volumes[J].IEEE Access,2019,7:24898-24909.
          [14] CHEN H,QI X,YU L,et al.DCAN:deep contour-aware networks for accurate gland segmentation[C]// Proc of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2016:2487-2496.
          [15] SHEN H,WANG R,ZHANG J,et al.Boundary-aware fully convolutional network for brain tumor segmentation[C]// Proc of Medical Image Computing and Computer-Assisted Intervention-MICCAI 2017.Quebec:Springer,2017:10434.
          [16] XU X,ZHOU F,LIU B,et al.Multiple organ localization in CT image using triple-branch fully convolutional networks[J].IEEE Access,2019,7:98083-98093.
          [17] RONNEBERGER O,FISHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]// Proc of International Conference on Medical Image Computing and Computer-Assisted Intervention-MICCAI.Munich:Springer,2015:234-241.
          [18] XIE S,TU Z.Holistically-nested edge detection [J].International Journal of Computer Vision,2017,125(1-3):3-18.
          [19] SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.
          [20] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[DB/ OL].[2015-04-10].https://arxiv.org/abs/1409.1556.
          文獻來源
          于凌濤, 王鵬程, 張 瑩, 夏永強. 用于腹部CT肝臟分割的邊界監督模型[J]. 華中科技大學學報(自然科學版), 2020, 48(9): 76-81
          DOI:10.13245/j.hust.200913
          澳门盘口