Towards automatic detection of abnormal retinal capillaries in ultra-widefield-of-view retinal angiographic exams

Krists Zutis, E. Trucco, J.P. Hubschman, D. Reed, S. Shah, J. Van Hemert

    Research output: Chapter in Book/Report/Conference proceedingChapter

    3 Citations (Scopus)

    Abstract

    Retinal capillary abnormalities include small, leaky, severely tortuous blood vessels that are associated with a variety of retinal pathologies. We present a prototype image-processing system for detecting abnormal retinal capillary regions in ultra-widefield-of-view (UWFOV) fluorescein angiography exams of the human retina. The algorithm takes as input an UWFOV FA frame and returns the candidate regions identified. An SVM classifier is trained on regions traced by expert ophthalmologists. Tests with a variety of feature sets indicate that edge features and allied properties differentiate best between normal and abnormal retinal capillary regions. Experiments with an initial set of images from patients showing branch retinal vein occlusion (BRVO) indicate promising area under the ROC curve of 0.950 and a weighted Cohen's Kappa value of 0.822.
    Original languageEnglish
    Title of host publicationProceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
    Pages7372-7375
    Number of pages4
    DOIs
    Publication statusPublished - 2013

    Fingerprint Dive into the research topics of 'Towards automatic detection of abnormal retinal capillaries in ultra-widefield-of-view retinal angiographic exams'. Together they form a unique fingerprint.

  • Cite this

    Zutis, K., Trucco, E., Hubschman, J. P., Reed, D., Shah, S., & Van Hemert, J. (2013). Towards automatic detection of abnormal retinal capillaries in ultra-widefield-of-view retinal angiographic exams. In Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 7372-7375) https://doi.org/10.1109/EMBC.2013.6611261