An Automatic Cognitive Graph-Based Segmentation for Detection of Blood Vessels in Retinal Images

Rasha Alshehhi, Prashanth Reddy Marpu, Wei Lee Woon

    Research output: Contribution to journalArticle

    Abstract

    This paper presents a hierarchical graph-based segmentation for blood vessel detection in digital retinal images. This segmentation employs some of perceptual Gestalt principles: similarity, closure, continuity, and proximity to merge segments into coherent connected vessel-like patterns. The integration of Gestalt principles is based on object-based features (e.g., color and black top-hat (BTH) morphology and context) and graph-analysis algorithms (e.g., Dijkstra path). The segmentation framework consists of two main steps: preprocessing and multiscale graph-based segmentation. Preprocessing is to enhance lighting condition, due to low illumination contrast, and to construct necessary features to enhance vessel structure due to sensitivity of vessel patterns to multiscale/multiorientation structure. Graph-based segmentation is to decrease computational processing required for region of interest into most semantic objects. The segmentation was evaluated on three publicly available datasets. Experimental results show that preprocessing stage achieves better results compared to state-of-the-art enhancement methods. The performance of the proposed graph-based segmentation is found to be consistent and comparable to other existing methods, with improved capability of detecting small/thin vessels.

    Original languageEnglish (US)
    Article number7906165
    JournalMathematical Problems in Engineering
    Volume2016
    DOIs
    StatePublished - Jan 1 2016

    Fingerprint

    Blood Vessels
    Blood vessels
    Segmentation
    Lighting
    Vessel
    Graph in graph theory
    Preprocessing
    Semantics
    Color
    Processing
    Dijkstra Algorithm
    Algorithm Analysis
    Region of Interest
    Digital Image
    Proximity
    Illumination
    Closure
    Enhancement
    Decrease
    Path

    ASJC Scopus subject areas

    • Mathematics(all)
    • Engineering(all)

    Cite this

    An Automatic Cognitive Graph-Based Segmentation for Detection of Blood Vessels in Retinal Images. / Alshehhi, Rasha; Marpu, Prashanth Reddy; Woon, Wei Lee.

    In: Mathematical Problems in Engineering, Vol. 2016, 7906165, 01.01.2016.

    Research output: Contribution to journalArticle

    @article{37a85747dfe249d3a2fe7802cf0e6580,
    title = "An Automatic Cognitive Graph-Based Segmentation for Detection of Blood Vessels in Retinal Images",
    abstract = "This paper presents a hierarchical graph-based segmentation for blood vessel detection in digital retinal images. This segmentation employs some of perceptual Gestalt principles: similarity, closure, continuity, and proximity to merge segments into coherent connected vessel-like patterns. The integration of Gestalt principles is based on object-based features (e.g., color and black top-hat (BTH) morphology and context) and graph-analysis algorithms (e.g., Dijkstra path). The segmentation framework consists of two main steps: preprocessing and multiscale graph-based segmentation. Preprocessing is to enhance lighting condition, due to low illumination contrast, and to construct necessary features to enhance vessel structure due to sensitivity of vessel patterns to multiscale/multiorientation structure. Graph-based segmentation is to decrease computational processing required for region of interest into most semantic objects. The segmentation was evaluated on three publicly available datasets. Experimental results show that preprocessing stage achieves better results compared to state-of-the-art enhancement methods. The performance of the proposed graph-based segmentation is found to be consistent and comparable to other existing methods, with improved capability of detecting small/thin vessels.",
    author = "Rasha Alshehhi and Marpu, {Prashanth Reddy} and Woon, {Wei Lee}",
    year = "2016",
    month = "1",
    day = "1",
    doi = "10.1155/2016/7906165",
    language = "English (US)",
    volume = "2016",
    journal = "Mathematical Problems in Engineering",
    issn = "1024-123X",
    publisher = "Hindawi Publishing Corporation",

    }

    TY - JOUR

    T1 - An Automatic Cognitive Graph-Based Segmentation for Detection of Blood Vessels in Retinal Images

    AU - Alshehhi, Rasha

    AU - Marpu, Prashanth Reddy

    AU - Woon, Wei Lee

    PY - 2016/1/1

    Y1 - 2016/1/1

    N2 - This paper presents a hierarchical graph-based segmentation for blood vessel detection in digital retinal images. This segmentation employs some of perceptual Gestalt principles: similarity, closure, continuity, and proximity to merge segments into coherent connected vessel-like patterns. The integration of Gestalt principles is based on object-based features (e.g., color and black top-hat (BTH) morphology and context) and graph-analysis algorithms (e.g., Dijkstra path). The segmentation framework consists of two main steps: preprocessing and multiscale graph-based segmentation. Preprocessing is to enhance lighting condition, due to low illumination contrast, and to construct necessary features to enhance vessel structure due to sensitivity of vessel patterns to multiscale/multiorientation structure. Graph-based segmentation is to decrease computational processing required for region of interest into most semantic objects. The segmentation was evaluated on three publicly available datasets. Experimental results show that preprocessing stage achieves better results compared to state-of-the-art enhancement methods. The performance of the proposed graph-based segmentation is found to be consistent and comparable to other existing methods, with improved capability of detecting small/thin vessels.

    AB - This paper presents a hierarchical graph-based segmentation for blood vessel detection in digital retinal images. This segmentation employs some of perceptual Gestalt principles: similarity, closure, continuity, and proximity to merge segments into coherent connected vessel-like patterns. The integration of Gestalt principles is based on object-based features (e.g., color and black top-hat (BTH) morphology and context) and graph-analysis algorithms (e.g., Dijkstra path). The segmentation framework consists of two main steps: preprocessing and multiscale graph-based segmentation. Preprocessing is to enhance lighting condition, due to low illumination contrast, and to construct necessary features to enhance vessel structure due to sensitivity of vessel patterns to multiscale/multiorientation structure. Graph-based segmentation is to decrease computational processing required for region of interest into most semantic objects. The segmentation was evaluated on three publicly available datasets. Experimental results show that preprocessing stage achieves better results compared to state-of-the-art enhancement methods. The performance of the proposed graph-based segmentation is found to be consistent and comparable to other existing methods, with improved capability of detecting small/thin vessels.

    UR - http://www.scopus.com/inward/record.url?scp=84975127045&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84975127045&partnerID=8YFLogxK

    U2 - 10.1155/2016/7906165

    DO - 10.1155/2016/7906165

    M3 - Article

    VL - 2016

    JO - Mathematical Problems in Engineering

    JF - Mathematical Problems in Engineering

    SN - 1024-123X

    M1 - 7906165

    ER -