具有仿射不变性的视网膜图像配准方法
|
摘要
为解决眼底照相机视角发生变化的视网膜图像的配准问题,提出一种具有仿射不变性的局部特征配准方法.首先通过寻找连通的血管交点对应的最小包围矩形得到仿射不变的各向异性图像结构;然后通过旋转、采样和压缩操作将各向异性的图像结构变为含不同角度因素的各向同性的图像结构;最后使用尺度不变特征变换算法在各向同性的图像结构上提取特征点,并对特征点坐标进行匹配.在包含83组视网膜图像的私有样本集中的实验结果表明,该方法的均方根误差为1.247±0.251像素,能很好地解决视角和尺度变化问题.
In order to solve the registration problem of retinal images with changes in the angle of view of the fundus camera, a local feature registration method with affine invariance is proposed. First, an affine-invariant anisotropic image structure is obtained by computing the minimal boundary rectangle of the connected domain corresponding to the vascular intersection point. Then, the anisotropic image structure is transformed into an isotropic image structure with different angular factors by rotating, sampling, and compression. Finally, using the feature invariant feature transform algorithm to extract feature points on the isotropic image structure, and the feature point coordinates are matched. The experimental results in a private sample set containing 83 groups of retinal images show that the root mean square error of the method is 1.247±0.251 pixels, which can solve the problem of perspective and scale change well.
In order to solve the registration problem of retinal images with changes in the angle of view of the fundus camera, a local feature registration method with affine invariance is proposed. First, an affine-invariant anisotropic image structure is obtained by computing the minimal boundary rectangle of the connected domain corresponding to the vascular intersection point. Then, the anisotropic image structure is transformed into an isotropic image structure with different angular factors by rotating, sampling, and compression. Finally, using the feature invariant feature transform algorithm to extract feature points on the isotropic image structure, and the feature point coordinates are matched. The experimental results in a private sample set containing 83 groups of retinal images show that the root mean square error of the method is 1.247±0.251 pixels, which can solve the problem of perspective and scale change well.
引文
[1]Mishra B,Pati U C,Sinha U.Modified demons registration for highly deformed medical images[C]//Proceedings of the 3rd International Conference on Image Information Processing.Los Alamitos:IEEE Computer Society Press,2016:152-156
[2]Sanchez-Galeana C,Bowd C,Blumenthal E Z,et al.Using optical imaging summary data to detect glaucoma[J].Ophthalmology,2001,108(10):1812-1818
[3]Brown M,Lowe D G.Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision,2007,74(1):59-73
[4]Lester H,Arridge S R.A survey of hierarchical non-linear medical image registration[J].Pattern Recognition,1999,32(1):129-149
[5]Barker S,Michael D J.Semi-supervised method for training multiple pattern recognition and registration tool models:United States,9659236[P].2017-05-23
[6]Ma J Y,Zhou H B,Zhao J,et al.Robust feature matching for remote sensing image registration via locally linear transforming[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(12):6469-6481
[7]Ferrante E,Paragios N.Slice-to-volume medical image registration:a survey[J].Medical Image Analysis,2017,39:101-123
[8]Liu J,Yin F S,Zhang Z,et al.AGLAIA:a-levelset based automatic cup-to-disc ratio measurement for glaucoma diagnosis from fundus image[J].Investigative Ophthalmology and Visual Science,2012,53(14):647
[9]Lee J A,Cheng J,Xu G Z,et al.Registration of color and OCTfundus images using low-dimensional step pattern analysis[C]//Proceedings of the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer,2015:214-221
[10]Haber E,Modersitzki J.Intensity gradient based registration and fusion of multi-modal images[C]//Proceedings of the 9th International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer,2006:726-733
[11]Hill D L,Batchelor P G,Holden M,et al.Medical image registration[J].Physics in Medicine and Biology,2001,46(3):R1-45
[12]Zitova B,Flusser J.Image registration methods:a survey[J].Image and Vision Computing,2003,21(11):977-1000
[13]Cideciyan A V.Registration of ocular fundus images:an algorithm using cross-correlation of triple invariant image descriptors[J].IEEE Engineering in Medicine and Biology Magazine,1995,14(1):52-58
[14]Matsopoulos G K,Mouravliansky N A,Delibasis K K,et al.Automatic retinal image registration scheme using global optimization techniques[J].IEEE Transactions on Information Technology in Biomedicine,1999,3(1):47-60
[15]Chen L,Huang X T,Tian J.Retinal image registration using topological vascular tree segmentation and bifurcation structures[J].Biomedical Signal Processing and Control,2015,16:22-31
[16]Morel J M,Yu G S.ASIFT:a new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469
[17]Miri M S,Abràmoff M D,Kwon Y H,et al.Multimodal registration of SD-OCT volumes and fundus photographs using histograms of oriented gradients[J].Biomedical Optics Express,2016,7(12):5252-5267
[18]Lowe D G.Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110
[19]Morel J M,Yu G S.Is SIFT scale invariant?[J].Inverse Problems and Imaging,2011,5(1):115-136
[20]Yu M,Yang H C,Deng K Z,et al.Registrating oblique images by integrating affine and scale-invariant features[J].International Journal of Remote Sensing,2018,39(10):3386-3405
[21]Lindeberg T.Feature detection with automatic scale selection[J].International Journal of Computer Vision,1998,30(2):79-116
[22]Lindeberg T,G?rding J.Shape-adapted smoothing in estimation of 3-D shape cues from affine distortions of local 2-D brightness structure[J].Image and Vision Computing,1997,15(6):415-434
[23]You X G,Peng Q M,Yuan Y,et al.Segmentation of retinal blood vessels using the radial projection and semi-supervised approach[J].Pattern Recognition,2011,44(10/11):2314-2324
[24]Nakashima J,Yamauchi Y,Kijima S,et al.Finding submodularity hidden in symmetric difference[OL].[2018-07-05].http://cn.arxiv.org/pdf/1712.08721
[25]Li W,Shi Z L,Yin J.A fully affine invariant feature detector[C]//Proceedings of the 21st International Conference on Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2012:2768-2771
[26]Muja M,Lowe D G.Fast approximate nearest neighbors with automatic algorithm configuration[C]//Proceedings of the 4th VISAPP International Conference on Computer Vision Theory and Applications.Heidelberg:Springer,2009:331-340
[27]Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395
[28]Chen J,Tian J,Lee N,et al.A partial intensity invariant feature descriptor for multimodal retinal image registration[J].IEEETransactions on Biomedical Engineering,2010,57(7):1707-1718
[29]Tsai C L,Li C Y,Yang G H,et al.The edge-driven dual-bootstrap iterative closest point algorithm for registration of multimodal fluorescein angiogram sequence[J].IEEETransactions on Medical Imaging,2010,29(3):636-649
[2]Sanchez-Galeana C,Bowd C,Blumenthal E Z,et al.Using optical imaging summary data to detect glaucoma[J].Ophthalmology,2001,108(10):1812-1818
[3]Brown M,Lowe D G.Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision,2007,74(1):59-73
[4]Lester H,Arridge S R.A survey of hierarchical non-linear medical image registration[J].Pattern Recognition,1999,32(1):129-149
[5]Barker S,Michael D J.Semi-supervised method for training multiple pattern recognition and registration tool models:United States,9659236[P].2017-05-23
[6]Ma J Y,Zhou H B,Zhao J,et al.Robust feature matching for remote sensing image registration via locally linear transforming[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(12):6469-6481
[7]Ferrante E,Paragios N.Slice-to-volume medical image registration:a survey[J].Medical Image Analysis,2017,39:101-123
[8]Liu J,Yin F S,Zhang Z,et al.AGLAIA:a-levelset based automatic cup-to-disc ratio measurement for glaucoma diagnosis from fundus image[J].Investigative Ophthalmology and Visual Science,2012,53(14):647
[9]Lee J A,Cheng J,Xu G Z,et al.Registration of color and OCTfundus images using low-dimensional step pattern analysis[C]//Proceedings of the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer,2015:214-221
[10]Haber E,Modersitzki J.Intensity gradient based registration and fusion of multi-modal images[C]//Proceedings of the 9th International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer,2006:726-733
[11]Hill D L,Batchelor P G,Holden M,et al.Medical image registration[J].Physics in Medicine and Biology,2001,46(3):R1-45
[12]Zitova B,Flusser J.Image registration methods:a survey[J].Image and Vision Computing,2003,21(11):977-1000
[13]Cideciyan A V.Registration of ocular fundus images:an algorithm using cross-correlation of triple invariant image descriptors[J].IEEE Engineering in Medicine and Biology Magazine,1995,14(1):52-58
[14]Matsopoulos G K,Mouravliansky N A,Delibasis K K,et al.Automatic retinal image registration scheme using global optimization techniques[J].IEEE Transactions on Information Technology in Biomedicine,1999,3(1):47-60
[15]Chen L,Huang X T,Tian J.Retinal image registration using topological vascular tree segmentation and bifurcation structures[J].Biomedical Signal Processing and Control,2015,16:22-31
[16]Morel J M,Yu G S.ASIFT:a new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469
[17]Miri M S,Abràmoff M D,Kwon Y H,et al.Multimodal registration of SD-OCT volumes and fundus photographs using histograms of oriented gradients[J].Biomedical Optics Express,2016,7(12):5252-5267
[18]Lowe D G.Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110
[19]Morel J M,Yu G S.Is SIFT scale invariant?[J].Inverse Problems and Imaging,2011,5(1):115-136
[20]Yu M,Yang H C,Deng K Z,et al.Registrating oblique images by integrating affine and scale-invariant features[J].International Journal of Remote Sensing,2018,39(10):3386-3405
[21]Lindeberg T.Feature detection with automatic scale selection[J].International Journal of Computer Vision,1998,30(2):79-116
[22]Lindeberg T,G?rding J.Shape-adapted smoothing in estimation of 3-D shape cues from affine distortions of local 2-D brightness structure[J].Image and Vision Computing,1997,15(6):415-434
[23]You X G,Peng Q M,Yuan Y,et al.Segmentation of retinal blood vessels using the radial projection and semi-supervised approach[J].Pattern Recognition,2011,44(10/11):2314-2324
[24]Nakashima J,Yamauchi Y,Kijima S,et al.Finding submodularity hidden in symmetric difference[OL].[2018-07-05].http://cn.arxiv.org/pdf/1712.08721
[25]Li W,Shi Z L,Yin J.A fully affine invariant feature detector[C]//Proceedings of the 21st International Conference on Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2012:2768-2771
[26]Muja M,Lowe D G.Fast approximate nearest neighbors with automatic algorithm configuration[C]//Proceedings of the 4th VISAPP International Conference on Computer Vision Theory and Applications.Heidelberg:Springer,2009:331-340
[27]Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395
[28]Chen J,Tian J,Lee N,et al.A partial intensity invariant feature descriptor for multimodal retinal image registration[J].IEEETransactions on Biomedical Engineering,2010,57(7):1707-1718
[29]Tsai C L,Li C Y,Yang G H,et al.The edge-driven dual-bootstrap iterative closest point algorithm for registration of multimodal fluorescein angiogram sequence[J].IEEETransactions on Medical Imaging,2010,29(3):636-649