September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
Bayesian expectation maximization approach for classification of arteries and veins
Author Affiliations & Notes
  • Francesco Caliva'
    Computer Science, University of Lincoln, Lincoln, England, United Kingdom
  • Bashir Al-Diri
    Computer Science, University of Lincoln, Lincoln, England, United Kingdom
  • Luca Antiga
    OROBIX srl, Bergamo, Italy, Italy
  • Andrew Hunter
    Computer Science, University of Lincoln, Lincoln, England, United Kingdom
  • Footnotes
    Commercial Relationships   Francesco Caliva', None; Bashir Al-Diri, None; Luca Antiga, None; Andrew Hunter, None
  • Footnotes
    Support  European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 316990.
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 5967. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Francesco Caliva', Bashir Al-Diri, Luca Antiga, Andrew Hunter; Bayesian expectation maximization approach for classification of arteries and veins. Invest. Ophthalmol. Vis. Sci. 2016;57(12):5967.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : The classification of retinal vessels as arteries (A) and veins (V) is an important step in computer analysis of cardiovascular diseases (e.g. diabetic retinopathy (DR), hypertension) that have different effects on the different vessel types. In this work it is demonstrated that by comparing features of closely running blood vessels A and V along the main retinal arcades (RAs) can be distinguished, as A appear brighter and slightly narrower than V.

Methods : DRIVE dataset was used to train and test the algorithm. Vessels running along RAs were detected by ellipse fitting (EF) on sample coordinates of the main vessels. Variations between diameters and pixel intensities for each pair of adjacent vessels were gathered for a supervised training stage. 4023 samples (1394 A-V, 1394 V-A, 430 A-A, 806 V-V occurrences) were selected and probability density functions (pdf) were estimated by kernel density estimation (KDE). Under the assumption of independent and identically distributed (iid) features, maximum likelihood (ML) was computed by implementing an expectation maximization algorithm (EMA). Assuming that there was equal probability (P) for a segment (S) to be A or V, every time S appeared in a classification window (CW), P was updated by applying the Naïve-Bayes theorem. At the end ML was selected to define whether S was A or V.

Results : During testing, results assessment was done by comparing to the manual labelling provided with DRIVE dataset. 1419 S were considered as located along the RAs and thus investigated and achieving a classification accuracy of 83.3%.

Conclusions : Results were consistent with the initial hypothesis. Sometimes pathological conditions (e.g. DR) and bad image illumination invalidated the initial assumptions. Next, vascular network topological information will be added, as we believe that this will reduce error due to BV overlap.

This is an abstract that was submitted for the 2016 ARVO Annual Meeting, held in Seattle, Wash., May 1-5, 2016.

 

BVs segmentation was achieved by pairing a multi-scale tramline-filtering with an active contour method. RA were identified through EF on MV (a-b). Based on RA, CWs were identified (c); pdf of A-V, V-A, A-A and V-V occurrences were estimated by KDE (d).

BVs segmentation was achieved by pairing a multi-scale tramline-filtering with an active contour method. RA were identified through EF on MV (a-b). Based on RA, CWs were identified (c); pdf of A-V, V-A, A-A and V-V occurrences were estimated by KDE (d).

 

a) Blue and red lines are V and A respectively; yellow and black lines are V (A) misclassified as A (V). b) By considering neighbouring vessel information misclassification errors were corrected.

a) Blue and red lines are V and A respectively; yellow and black lines are V (A) misclassified as A (V). b) By considering neighbouring vessel information misclassification errors were corrected.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×