Scribd Logo
Upload

Welcome to Scribd!

  • 25 views

    Deep Learning Segmentation in Fundus Images For Diabetic Retinopathy Detection

    Uploaded by

    Jilly Arasu
    abstract

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Deep Learning Segmentation in Fundus Images For Diabetic Retinopathy Detection

    Uploaded by

    Jilly Arasu
    25 views1 page
    abstract

    Original Title

    Retinal Fundus

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    abstract

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    25 views1 page

    Deep Learning Segmentation in Fundus Images For Diabetic Retinopathy Detection

    Uploaded by

    Jilly Arasu
    abstract

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 1

    Deep Learning Segmentation in Fundus Images for Diabetic

    Retinopathy Detection

    ABSTRACT

    The segmentation of anatomical structures in medical images plays an

    important role in the diagnosis and treatment of diseases. It is frequently used to

    visualize organs, extract quantitative clinical measurements, and define the region

    of interest to localize pathologies and aid in the surgical treatment planning.

    Accurate segmentation algorithms can save the time and effort of medical experts

    and minimize the intra and inter-subject variability involved in manual

    segmentation. The Convolutional Neural Networks (CNN) address this issue by

    learning robust features in a supervised end-to-end manner. The proposed work

    presents a Recurrent Neural Network (RNN) based solution called the RACE-net

    to address the above issues. Initially, the retinal images are preprocessed in order to

    remove the unwanted pixel entry. The histogram based intensity enhancement

    techniques are applied for the later issues. The RACE-net allows the segmentation

    to be learned in an end-to-end manner while minimizing the number of network

    parameters, computation time and memory requirements. The RACE-net is

    implemented for three different segmentation tasks: Optic disc and cup in color

    fundus images and cell nuclei in histopathological images.

    You might also like