Limits...
Retinal blood vessels extraction using probabilistic modelling.

Kaba D, Wang C, Li Y, Salazar-Gonzalez A, Liu X, Serag A - Health Inf Sci Syst (2014)

Bottom Line: Then the blood vessels are extracted using probabilistic modelling that is optimised by the expectation maximisation algorithm.The experimental results are compared with some recently published methods of retinal blood vessels segmentation.The experimental results show that our method achieved the best overall performance and it is comparable to the performance of human experts.

View Article: PubMed Central - PubMed

Affiliation: Department of Information Systems, Computing and Mathematics Brunel University, London, UK.

ABSTRACT
The analysis of retinal blood vessels plays an important role in detecting and treating retinal diseases. In this review, we present an automated method to segment blood vessels of fundus retinal image. The proposed method could be used to support a non-intrusive diagnosis in modern ophthalmology for early detection of retinal diseases, treatment evaluation or clinical study. This study combines the bias correction and an adaptive histogram equalisation to enhance the appearance of the blood vessels. Then the blood vessels are extracted using probabilistic modelling that is optimised by the expectation maximisation algorithm. The method is evaluated on fundus retinal images of STARE and DRIVE datasets. The experimental results are compared with some recently published methods of retinal blood vessels segmentation. The experimental results show that our method achieved the best overall performance and it is comparable to the performance of human experts.

No MeSH data available.


Related in: MedlinePlus

Adaptive histogram equalisation results.(a)r=3, h=45. (b)r=6, 45. (c)r=3, h=81. (d)r=6, h=81.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4376494&req=5

Fig2: Adaptive histogram equalisation results.(a)r=3, h=45. (b)r=6, 45. (c)r=3, h=81. (d)r=6, h=81.

Mentions: The notation q represents the pixels in the image and q′ is the neighbourhood pixels of q, defined by a square window of width h.The value of r indicates the level of contrast between the vessels and the background, by increasing the value of r, the contrast between vessel pixels and the background increases. Figure 2 shows the output images of the adaptive histogram equalisation with different values of r and h.Figure 2


Retinal blood vessels extraction using probabilistic modelling.

Kaba D, Wang C, Li Y, Salazar-Gonzalez A, Liu X, Serag A - Health Inf Sci Syst (2014)

Adaptive histogram equalisation results.(a)r=3, h=45. (b)r=6, 45. (c)r=3, h=81. (d)r=6, h=81.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4376494&req=5

Fig2: Adaptive histogram equalisation results.(a)r=3, h=45. (b)r=6, 45. (c)r=3, h=81. (d)r=6, h=81.
Mentions: The notation q represents the pixels in the image and q′ is the neighbourhood pixels of q, defined by a square window of width h.The value of r indicates the level of contrast between the vessels and the background, by increasing the value of r, the contrast between vessel pixels and the background increases. Figure 2 shows the output images of the adaptive histogram equalisation with different values of r and h.Figure 2

Bottom Line: Then the blood vessels are extracted using probabilistic modelling that is optimised by the expectation maximisation algorithm.The experimental results are compared with some recently published methods of retinal blood vessels segmentation.The experimental results show that our method achieved the best overall performance and it is comparable to the performance of human experts.

View Article: PubMed Central - PubMed

Affiliation: Department of Information Systems, Computing and Mathematics Brunel University, London, UK.

ABSTRACT
The analysis of retinal blood vessels plays an important role in detecting and treating retinal diseases. In this review, we present an automated method to segment blood vessels of fundus retinal image. The proposed method could be used to support a non-intrusive diagnosis in modern ophthalmology for early detection of retinal diseases, treatment evaluation or clinical study. This study combines the bias correction and an adaptive histogram equalisation to enhance the appearance of the blood vessels. Then the blood vessels are extracted using probabilistic modelling that is optimised by the expectation maximisation algorithm. The method is evaluated on fundus retinal images of STARE and DRIVE datasets. The experimental results are compared with some recently published methods of retinal blood vessels segmentation. The experimental results show that our method achieved the best overall performance and it is comparable to the performance of human experts.

No MeSH data available.


Related in: MedlinePlus