Retinal artery/vein classification using genetic-search feature selection

BACKGROUND AND OBJECTIVES The automatic classification of retinal blood vessels into artery and vein (A/V) is still a challenging task in retinal image analysis. Recent works on A/V classification mainly focus on the graph analysis of the retinal vasculature, which exploits the connectivity of vessels to improve the classification performance. While they have overlooked the importance of pixel-wise classification to the final classification results. This paper shows that a complicated feature set is efficient for vessel centerline pixels classification. METHODS We extract enormous amount of features for vessel centerline pixels, and apply a genetic-search based feature selection technique to obtain the optimal feature subset for A/V classification. RESULTS The proposed method achieves an accuracy of 90.2%, the sensitivity of 89.6%, the specificity of 91.3% on the INSPIRE dataset. It shows that our method, using only the information of centerline pixels, gives a comparable performance as the techniques which use complicated graph analysis. In addition, the results on the images acquired by different fundus cameras show that our framework is capable for discriminating vessels independent of the imaging device characteristics, image resolution and image quality. CONCLUSION The complicated feature set is essential for A/V classification, especially on the individual vessels where graph-based methods receive limitations. And it could provide a higher entry to the graph-analysis to achieve a better A/V labeling.

[1]  R. Klein,et al.  Retinal vascular tortuosity, blood pressure, and cardiovascular risk factors. , 2011, Ophthalmology.

[2]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[3]  Manuel G. Penedo,et al.  Improving retinal artery and vein classification by means of a minimal path approach , 2012, Machine Vision and Applications.

[4]  Ana Maria Mendonça,et al.  An Automatic Graph-Based Approach for Artery/Vein Classification in Retinal Images , 2014, IEEE Transactions on Image Processing.

[5]  Jiong Zhang,et al.  Automatic Optic Disc and Fovea Detection in Retinal Images Using Super-Elliptical Convergence Index Filters , 2016, ICIAR.

[6]  Siegfried Priglinger,et al.  Retinal Vessel Analysis Reproducibility in Assessing Cardiovascular Disease , 2008, Optometry and vision science : official publication of the American Academy of Optometry.

[7]  B. Wasan,et al.  Vascular network changes in the retina with age and hypertension , 1995, Journal of hypertension.

[8]  Enrico Grisan,et al.  Luminosity and contrast normalization in retinal images , 2005, Medical Image Anal..

[9]  B. H. Romeny,et al.  Curvature Based Biomarkers for Diabetic Retinopathy via Exponential Curve Fits in SE(2) , 2015 .

[10]  Hai-Chao Han Twisted Blood Vessels: Symptoms, Etiology and Biomechanical Mechanisms , 2012, Journal of Vascular Research.

[11]  Qiao Hu,et al.  Automated construction of arterial and venous trees in retinal images , 2015, Journal of medical imaging.

[12]  Tien Yin Wong,et al.  Retinal vascular changes and diabetic retinopathy , 2009, Current diabetes reports.

[13]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[14]  Bram van Ginneken,et al.  Automated Measurement of the Arteriolar-to-Venular Width Ratio in Digital Color Fundus Photographs , 2011, IEEE Transactions on Medical Imaging.

[15]  Carlo Tomasi,et al.  Retinal Artery-Vein Classification via Topology Estimation , 2015, IEEE Transactions on Medical Imaging.

[16]  Bram van Ginneken,et al.  Automatic classification of retinal vessels into arteries and veins , 2009, Medical Imaging.

[17]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[18]  T. Wong,et al.  Retinal vascular caliber: systemic, environmental, and genetic associations. , 2009, Survey of ophthalmology.

[19]  Manuel G. Penedo,et al.  AUTOMATIC CLASSIFICATION OF RETINAL VESSELS INTO ARTERIES AND VEINS , 2010 .

[20]  Josien P. W. Pluim,et al.  Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores , 2016, IEEE Transactions on Medical Imaging.

[21]  Ana Maria Mendonça,et al.  RetinaCAD, a system for the assessment of retinal vascular changes , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[22]  Krzysztof Krawiec,et al.  Segmenting Retinal Blood Vessels With Deep Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[23]  George Azzopardi,et al.  Trainable COSFIRE filters for vessel delineation with application to retinal images , 2015, Medical Image Anal..

[24]  N. Chapman,et al.  Peripheral vascular disease is associated with abnormal arteriolar diameter relationships at bifurcations in the human retina. , 2002, Clinical science.

[25]  John G Flanagan,et al.  Retinal hemodynamics in early diabetic macular edema. , 2006, Diabetes.

[26]  Farshad Tajeripour,et al.  Computerized Medical Imaging and Graphics Automated Characterization of Blood Vessels as Arteries and Veins in Retinal Images , 2022 .

[27]  A. Stanton,et al.  Retinal vascular network architecture in low‐birth‐weight men , 1997, Journal of hypertension.

[28]  Samaneh Abbasi-Sureshjani,et al.  Retinal health information and notification system (RHINO) , 2017, Medical Imaging.

[29]  J. Reinhardt,et al.  Automated Method for Identification and Artery-Venous Classification of Vessel Trees in Retinal Vessel Networks , 2014, PloS one.

[30]  Qiao Hu,et al.  Automated Separation of Binary Overlapping Trees in Low-Contrast Color Retinal Images , 2013, MICCAI.

[31]  P. Dagnelie,et al.  The Maastricht Study: an extensive phenotyping study on determinants of type 2 diabetes, its complications and its comorbidities , 2014, European Journal of Epidemiology.

[32]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[33]  Michael D. Abràmoff,et al.  An improved arteriovenous classification method for the early diagnostics of various diseases in retinal image , 2017, Comput. Methods Programs Biomed..

[34]  Zicheng Guo,et al.  Parallel thinning with two-subiteration algorithms , 1989, Commun. ACM.

[35]  Andrea Giachetti,et al.  Effective features for artery-vein classification in digital fundus images , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).