Limits...
Analysis of Fundus Fluorescein Angiogram Based on the Hessian Matrix of Directional Curvelet Sub-bands and Distance Regularized Level Set Evolution.

Soltanipour A, Sadri S, Rabbani H, Akhlaghi MR - J Med Signals Sens (2015 Jul-Sep)

Bottom Line: In order to extract blood vessel centerlines, the algorithm of vessel extraction starts with the analysis of directional images resulting from sub-bands of fast discrete curvelet transform (FDCT) in the similar directions and different scales.The final vessel segmentation is obtained using a simple region growing algorithm iteratively, which merges centerline images with the contents of images resulting from modified top-hat transform followed by bit plane slicing.The experimental results show the accuracy more than 93% for vessel segmentation and more than 87% for OD boundary extraction.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran.

ABSTRACT
This paper presents a new procedure for automatic extraction of the blood vessels and optic disk (OD) in fundus fluorescein angiogram (FFA). In order to extract blood vessel centerlines, the algorithm of vessel extraction starts with the analysis of directional images resulting from sub-bands of fast discrete curvelet transform (FDCT) in the similar directions and different scales. For this purpose, each directional image is processed by using information of the first order derivative and eigenvalues obtained from the Hessian matrix. The final vessel segmentation is obtained using a simple region growing algorithm iteratively, which merges centerline images with the contents of images resulting from modified top-hat transform followed by bit plane slicing. After extracting blood vessels from FFA image, candidates regions for OD are enhanced by removing blood vessels from the FFA image, using multi-structure elements morphology, and modification of FDCT coefficients. Then, canny edge detector and Hough transform are applied to the reconstructed image to extract the boundary of candidate regions. At the next step, the information of the main arc of the retinal vessels surrounding the OD region is used to extract the actual location of the OD. Finally, the OD boundary is detected by applying distance regularized level set evolution. The proposed method was tested on the FFA images from angiography unit of Isfahan Feiz Hospital, containing 70 FFA images from different diabetic retinopathy stages. The experimental results show the accuracy more than 93% for vessel segmentation and more than 87% for OD boundary extraction.

No MeSH data available.


Related in: MedlinePlus

(a-c) Related to fundus fluorescein angiogram images from angiography unit of Isfahan Fiez Hospital. From top to bottom, they are the original image, vessel centerlines, final vessel segmentation and ground truth image, respectively
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4528352&req=5

Figure 22: (a-c) Related to fundus fluorescein angiogram images from angiography unit of Isfahan Fiez Hospital. From top to bottom, they are the original image, vessel centerlines, final vessel segmentation and ground truth image, respectively

Mentions: Our proposed algorithm for vessel segmentation was tested on the FFA images of size 576 × 720 pixels from angiography unit of Isfahan Feiz Hospital which consist 30 images for normal retinas and 40 images of abnormal retinas. These images can be downloaded from https://sites.google.com/site/hosseinrabbanikhorasgani/datasets-1/fundus-fluore scein-angiogram-photographs-of-diabetic-patients or http://misp.mui.ac.ir/en/Fundus%20Fluorescent%20Angiography%20Images. Since, our proposed algorithm for vessel segmentation was tested on the FFA images from several patients in different types of diabetic retinopathy in Isfahan Feiz hospital; in order to compare the proposed algorithm with other methods, our vessel extraction algorithm was tested on the green channel of DRIVE database to evaluate the performance of proposed algorithm. The experiments show that the proposed algorithm is more robust for detecting thin and low contrast vessels. The results of the proposed algorithm for vessel segmentation are shown in Figures 21 and 22, for a few samples of the fundus and FFA images of above mentioned databases, respectively. The proposed curvelet-based vessel extraction algorithm according to left column of the functional block diagram in Figure 1 is performed by MATLAB version 8 and the computational time is <2 min on 4.4 GHz processor CORE i5. In this paper, FDCT via wrapping is applied in 5 scales and 16 directions is defined in the second scales, which makes 32 directions in 3rd and 4th scales and 64 directions in 5th scale to produce directional images.


Analysis of Fundus Fluorescein Angiogram Based on the Hessian Matrix of Directional Curvelet Sub-bands and Distance Regularized Level Set Evolution.

Soltanipour A, Sadri S, Rabbani H, Akhlaghi MR - J Med Signals Sens (2015 Jul-Sep)

(a-c) Related to fundus fluorescein angiogram images from angiography unit of Isfahan Fiez Hospital. From top to bottom, they are the original image, vessel centerlines, final vessel segmentation and ground truth image, respectively
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4528352&req=5

Figure 22: (a-c) Related to fundus fluorescein angiogram images from angiography unit of Isfahan Fiez Hospital. From top to bottom, they are the original image, vessel centerlines, final vessel segmentation and ground truth image, respectively
Mentions: Our proposed algorithm for vessel segmentation was tested on the FFA images of size 576 × 720 pixels from angiography unit of Isfahan Feiz Hospital which consist 30 images for normal retinas and 40 images of abnormal retinas. These images can be downloaded from https://sites.google.com/site/hosseinrabbanikhorasgani/datasets-1/fundus-fluore scein-angiogram-photographs-of-diabetic-patients or http://misp.mui.ac.ir/en/Fundus%20Fluorescent%20Angiography%20Images. Since, our proposed algorithm for vessel segmentation was tested on the FFA images from several patients in different types of diabetic retinopathy in Isfahan Feiz hospital; in order to compare the proposed algorithm with other methods, our vessel extraction algorithm was tested on the green channel of DRIVE database to evaluate the performance of proposed algorithm. The experiments show that the proposed algorithm is more robust for detecting thin and low contrast vessels. The results of the proposed algorithm for vessel segmentation are shown in Figures 21 and 22, for a few samples of the fundus and FFA images of above mentioned databases, respectively. The proposed curvelet-based vessel extraction algorithm according to left column of the functional block diagram in Figure 1 is performed by MATLAB version 8 and the computational time is <2 min on 4.4 GHz processor CORE i5. In this paper, FDCT via wrapping is applied in 5 scales and 16 directions is defined in the second scales, which makes 32 directions in 3rd and 4th scales and 64 directions in 5th scale to produce directional images.

Bottom Line: In order to extract blood vessel centerlines, the algorithm of vessel extraction starts with the analysis of directional images resulting from sub-bands of fast discrete curvelet transform (FDCT) in the similar directions and different scales.The final vessel segmentation is obtained using a simple region growing algorithm iteratively, which merges centerline images with the contents of images resulting from modified top-hat transform followed by bit plane slicing.The experimental results show the accuracy more than 93% for vessel segmentation and more than 87% for OD boundary extraction.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran.

ABSTRACT
This paper presents a new procedure for automatic extraction of the blood vessels and optic disk (OD) in fundus fluorescein angiogram (FFA). In order to extract blood vessel centerlines, the algorithm of vessel extraction starts with the analysis of directional images resulting from sub-bands of fast discrete curvelet transform (FDCT) in the similar directions and different scales. For this purpose, each directional image is processed by using information of the first order derivative and eigenvalues obtained from the Hessian matrix. The final vessel segmentation is obtained using a simple region growing algorithm iteratively, which merges centerline images with the contents of images resulting from modified top-hat transform followed by bit plane slicing. After extracting blood vessels from FFA image, candidates regions for OD are enhanced by removing blood vessels from the FFA image, using multi-structure elements morphology, and modification of FDCT coefficients. Then, canny edge detector and Hough transform are applied to the reconstructed image to extract the boundary of candidate regions. At the next step, the information of the main arc of the retinal vessels surrounding the OD region is used to extract the actual location of the OD. Finally, the OD boundary is detected by applying distance regularized level set evolution. The proposed method was tested on the FFA images from angiography unit of Isfahan Feiz Hospital, containing 70 FFA images from different diabetic retinopathy stages. The experimental results show the accuracy more than 93% for vessel segmentation and more than 87% for OD boundary extraction.

No MeSH data available.


Related in: MedlinePlus