CT图像处理中肝脏分割技术研究进展
|
摘要
医学图像处理(image processing)技术在医学疾病诊疗领域具有越来越重要的作用,可以很好的解决癌症早筛中病症不明显诊断困难的难题,通过图像处理技术可以对疾病进行精确的确诊。其中器官分割是图像处理技术的基础技术,其分割结果直接影像更深入的图像处理。本文介绍CT图像处理中肝脏分割技术的研究进展,包括基于无监督、弱监督学习的分割算法和基于监督学习的分割算法两大方面,并介绍了近年迅速发展的人工智能技术在医疗领域中的应用,尤其是人工智能在CT图像分割领域中的应用进展,同时展望了人工智能在医学影像学中的应用前景。
Medical image processing technology more and more important in disease diagnosis and treatment. It is a good solution to the problem that the early screening of cancer is not obviously diagnosed. The image processing technology can accurately diagnose the disease. Among them,organ segmentation is the basic technology of image processing technology,and its segmentation results directly image deeper image processing. This paper presents the research progress of liver segmentation technology in CT image processing, including segmentation algorithm based on unsupervised, weak supervised learning and segmentation algorithm based on supervised learning, and introduces the rapid development of artificial intelligence technology in the medical field in recent years. The application,especially the application of artificial intelligence in the field of CT image segmentation, and prospects for the application of artificial intelligence in medical imaging were introduced.
Medical image processing technology more and more important in disease diagnosis and treatment. It is a good solution to the problem that the early screening of cancer is not obviously diagnosed. The image processing technology can accurately diagnose the disease. Among them,organ segmentation is the basic technology of image processing technology,and its segmentation results directly image deeper image processing. This paper presents the research progress of liver segmentation technology in CT image processing, including segmentation algorithm based on unsupervised, weak supervised learning and segmentation algorithm based on supervised learning, and introduces the rapid development of artificial intelligence technology in the medical field in recent years. The application,especially the application of artificial intelligence in the field of CT image segmentation, and prospects for the application of artificial intelligence in medical imaging were introduced.
引文
[1]陈自谦.大型医学影像设备质量控制与质量管理的现状与思考[J].中国医疗设备,2018,33(10):1-6,18.
[2]Chlebus G,Schenk A,Moltz J H,et al. Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing[J]. Sci Rep,2018,8(1):15497.
[3]Li X,Chen H,Qi X,et al. H-DenseUNet:Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes[J]. IEEE Trans Med Imaging,2018,37(12):2663-2674.
[4]Wang Z,Zhang C,Jiao T, et al. Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images[J].J Healthc Eng,2018,2018:6797102.
[5]Zou H,Xue H,Tao Y. Liver Three-Dimensional Reconstruction Accurately Predicts Remnant Liver Volume for HBV-Related Hepatocellular Carcinoma Prior to Hepatectomy[J]. Indian Journal of Surgery,2017(5):1-6.
[6]廖苗,赵于前,曾业战,等.基于图割和边缘行进的肝脏CT序列图像分割[J].电子与信息学报,2016,38(6):1552-1556.
[7]Wu W,Zhou Z,Wu S,et al. Automatic Liver Segmentation on Volumetric CT Images Using Supervoxel-Based Graph Cuts[J].Computational and Mathematical Methods in Medicine,2016,2016:1-14.
[8]Abbas Q. Segmentation of differential structures on computed tomography images for diagnosis lung-related diseases[J]. Biomedical Signal Processing&Control,2017,33:325-334.
[9]宋晓,贾松浩,黄晓阳,等.肝脏分割的种子点自动获取方法[J].系统仿真学报,2013,25(9):2075-2078.
[10]彭丰平,鲍苏苏,曾碧卿.基于自适应区域生长算法的肝脏分割[J].计算机工程与应用,2010,46(33):198-200.
[11]Miao L,Zhao YQ,Wei W,et al. Efficient liver segmentation in CT images based on graph cuts and bottleneck detection[J]. Physica Medica,2016,32(11):1383.
[12]Zheng Y,Ai D,Mu J,et al. Automatic liver segmentation based on appearance and context information[J]. Biomedical Engineering Online,2017,16(1):16.
[13]Iglesias JE,Sabuncu MR. Multi-atlas segmentation of biomedical images:A survey[J]. Medical Image Analysis,2015,24(1):205-219.
[14]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 A Publication of the IEEE Signal Processing Society, 2015,24(12):5315.
[15]Dou Q,Yu L,Chen H,et al. 3D deeply supervised network for automated segmentation of volumetric medical images[J]. Medical Image Analysis,2017,41:40.
[16]Lecun Y,Bengio Y,Hinton G. Deep learning[J]. Nature,2015,521(7553):436.
[17]Christ PF,Elshaer M EA,Ettlinger F,et al. Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworksand3DConditionalRandomFields[C]//InternationalConferenceonMedicalImageComputing&Computer-assisted Intervention,2016.
[18]Milletari F,Ahmadi SA,Kroll C,et al. Hough-CNN:Deep learning for segmentation of deep brain regions in MRI and ultrasound[J]. Computer Vision&Image Understanding,2017:S1019489652.
[19]孙明建,徐军,马伟,等.基于新型深度全卷积网络的肝脏CT影像三维区域自动分割[J].中国生物医学工程学报,2018,37(4):385-393.
[20]Hu P,Wu F,Peng J,et al. Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution[J]. Physics in Medicine&Biology,2016,61(24):8676.
[2]Chlebus G,Schenk A,Moltz J H,et al. Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing[J]. Sci Rep,2018,8(1):15497.
[3]Li X,Chen H,Qi X,et al. H-DenseUNet:Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes[J]. IEEE Trans Med Imaging,2018,37(12):2663-2674.
[4]Wang Z,Zhang C,Jiao T, et al. Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images[J].J Healthc Eng,2018,2018:6797102.
[5]Zou H,Xue H,Tao Y. Liver Three-Dimensional Reconstruction Accurately Predicts Remnant Liver Volume for HBV-Related Hepatocellular Carcinoma Prior to Hepatectomy[J]. Indian Journal of Surgery,2017(5):1-6.
[6]廖苗,赵于前,曾业战,等.基于图割和边缘行进的肝脏CT序列图像分割[J].电子与信息学报,2016,38(6):1552-1556.
[7]Wu W,Zhou Z,Wu S,et al. Automatic Liver Segmentation on Volumetric CT Images Using Supervoxel-Based Graph Cuts[J].Computational and Mathematical Methods in Medicine,2016,2016:1-14.
[8]Abbas Q. Segmentation of differential structures on computed tomography images for diagnosis lung-related diseases[J]. Biomedical Signal Processing&Control,2017,33:325-334.
[9]宋晓,贾松浩,黄晓阳,等.肝脏分割的种子点自动获取方法[J].系统仿真学报,2013,25(9):2075-2078.
[10]彭丰平,鲍苏苏,曾碧卿.基于自适应区域生长算法的肝脏分割[J].计算机工程与应用,2010,46(33):198-200.
[11]Miao L,Zhao YQ,Wei W,et al. Efficient liver segmentation in CT images based on graph cuts and bottleneck detection[J]. Physica Medica,2016,32(11):1383.
[12]Zheng Y,Ai D,Mu J,et al. Automatic liver segmentation based on appearance and context information[J]. Biomedical Engineering Online,2017,16(1):16.
[13]Iglesias JE,Sabuncu MR. Multi-atlas segmentation of biomedical images:A survey[J]. Medical Image Analysis,2015,24(1):205-219.
[14]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 A Publication of the IEEE Signal Processing Society, 2015,24(12):5315.
[15]Dou Q,Yu L,Chen H,et al. 3D deeply supervised network for automated segmentation of volumetric medical images[J]. Medical Image Analysis,2017,41:40.
[16]Lecun Y,Bengio Y,Hinton G. Deep learning[J]. Nature,2015,521(7553):436.
[17]Christ PF,Elshaer M EA,Ettlinger F,et al. Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworksand3DConditionalRandomFields[C]//InternationalConferenceonMedicalImageComputing&Computer-assisted Intervention,2016.
[18]Milletari F,Ahmadi SA,Kroll C,et al. Hough-CNN:Deep learning for segmentation of deep brain regions in MRI and ultrasound[J]. Computer Vision&Image Understanding,2017:S1019489652.
[19]孙明建,徐军,马伟,等.基于新型深度全卷积网络的肝脏CT影像三维区域自动分割[J].中国生物医学工程学报,2018,37(4):385-393.
[20]Hu P,Wu F,Peng J,et al. Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution[J]. Physics in Medicine&Biology,2016,61(24):8676.