视网膜血管分割方法综述
|
摘要
图像分割在图像处理中处于至关重要的地位,分割的效果将直接影响到后续对图像的处理。视网膜血管是人体的重要组成部分,其血管网络形态结构的影响,是心脑血管疾病对血管微循环检查的重要部位。因此,对血管的研究具有实际意义,尤其在临床上的应用更是普及。本文通过对血管分割方法的大量研究,针对当前比较流行的方法进行了阐述。最后对最流行的深度学习算法在医学上的应用进行探索。通过对多种血管分割方法的研究,从而提高眼底病临床诊断的效率与精度,给DR的进一步治疗提供理论依据,进而协助临床眼底病变的早期发现和诊断。
Image segmentation is in a crucial position in image processing, and the effect of segmentation will directly affect the subsequent processing of images. Retinal blood vessels are an important part of the human body, and the influence of the vascular network morphology and structure is an important part of cardiovascular and cerebrovascular diseases for the examination of vascular microcirculation. Therefore, the reasearch of blood vessels has practical significance, especially in clinical applications. In this paper, through a lot of research on the method of blood vessel segmentation, the current popular methods are expounded. Finally, the application of the most popular deep learning algorithms in medicine is explored.Through the research of a large number of blood vessel segmentation methods, the efficiency and accuracy of clinical diagnosis of fundus diseases can be improved, and the theoretical basis for further treatment of DR can be provided to assist in the early detection and diagnosis of clinical fundus lesions.
Image segmentation is in a crucial position in image processing, and the effect of segmentation will directly affect the subsequent processing of images. Retinal blood vessels are an important part of the human body, and the influence of the vascular network morphology and structure is an important part of cardiovascular and cerebrovascular diseases for the examination of vascular microcirculation. Therefore, the reasearch of blood vessels has practical significance, especially in clinical applications. In this paper, through a lot of research on the method of blood vessel segmentation, the current popular methods are expounded. Finally, the application of the most popular deep learning algorithms in medicine is explored.Through the research of a large number of blood vessel segmentation methods, the efficiency and accuracy of clinical diagnosis of fundus diseases can be improved, and the theoretical basis for further treatment of DR can be provided to assist in the early detection and diagnosis of clinical fundus lesions.
引文
[1]梁礼明,盛校棋,郭凯,等.基于改进的U-Net眼底视网膜血管分割[J/OL].计算机应用研究:1-6[2019-03-02].
[2]汪维华,张景中,吴文渊.改进的形态学与Otsu相结合的视网膜血管分割[J/OL].计算机应用研究,2019(08):1-8[2019-01-12].
[3]郑婷月,唐晨,雷振坤.基于全卷积神经网络的多尺度视网膜血管分割[J/OL].光学学报:1-13[2019-01-12].
[4]王娜,傅迎华,蒋念平.基于监督的全卷积神经网络视网膜血管分割[J].软件导刊,2018,17(08):45-48+52.
[5]吴晨玥,易本顺,章云港,等.基于改进卷积神经网络的视网膜血管图像分割[J].光学学报,2018,38(11):133-139.
[6]朱承璋,崔锦恺,邹北骥,等.基于多特征融合和随机森林的视网膜血管分割[J].计算机辅助设计与图形学学报,2017,29(04):584-592.
[7]武劲圆,游国栋,严宇,等.基于图像分割的糖尿病性视网膜病变血管的分析[J].医疗卫生装备,2017,38(06):27-29+40.
[8]冯河洋.视网膜血管图像分割算法的研究[D].西南交通大学,2017.
[9]杨毅.视网膜血管分割与动静脉分类方法研究[D].哈尔滨工业大学,2016.
[10]Chen J,Yang L,Zhang Y,et al.Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation[J].2016.
[11]单玲玉.糖尿病视网膜病变图像的血管提取方法研究[D].武汉工程大学,2015.
[12]闵锋,单玲玉,张彦铎.糖尿病视网膜病变图像的血管分割方法研究[J].华中科技大学学报(自然科学版),2015,43(S1):376-380.
[13]Long J,Shelhamer E,Darrell T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2014,39(4):640-651.
[2]汪维华,张景中,吴文渊.改进的形态学与Otsu相结合的视网膜血管分割[J/OL].计算机应用研究,2019(08):1-8[2019-01-12].
[3]郑婷月,唐晨,雷振坤.基于全卷积神经网络的多尺度视网膜血管分割[J/OL].光学学报:1-13[2019-01-12].
[4]王娜,傅迎华,蒋念平.基于监督的全卷积神经网络视网膜血管分割[J].软件导刊,2018,17(08):45-48+52.
[5]吴晨玥,易本顺,章云港,等.基于改进卷积神经网络的视网膜血管图像分割[J].光学学报,2018,38(11):133-139.
[6]朱承璋,崔锦恺,邹北骥,等.基于多特征融合和随机森林的视网膜血管分割[J].计算机辅助设计与图形学学报,2017,29(04):584-592.
[7]武劲圆,游国栋,严宇,等.基于图像分割的糖尿病性视网膜病变血管的分析[J].医疗卫生装备,2017,38(06):27-29+40.
[8]冯河洋.视网膜血管图像分割算法的研究[D].西南交通大学,2017.
[9]杨毅.视网膜血管分割与动静脉分类方法研究[D].哈尔滨工业大学,2016.
[10]Chen J,Yang L,Zhang Y,et al.Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation[J].2016.
[11]单玲玉.糖尿病视网膜病变图像的血管提取方法研究[D].武汉工程大学,2015.
[12]闵锋,单玲玉,张彦铎.糖尿病视网膜病变图像的血管分割方法研究[J].华中科技大学学报(自然科学版),2015,43(S1):376-380.
[13]Long J,Shelhamer E,Darrell T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2014,39(4):640-651.