Scribd
Upload
110 views3 pages

Automated Macular Pathology Detection

This document proposes an automated system to diagnose multiple macular pathologies in retinal optical coherence tomography (OCT) images. Existing systems are time-consuming and rely on specialist interpretation. The proposed system uses normalization, morphological operations, and curve filling for pre-processing, and extracts texture and shape features using gray-level co-occurrence matrix (GLCM) and principal component analysis (PCA). A support vector machine classifier then identifies normal macula and macular pathologies like holes, cysts, and age-related macular degeneration. This automated process could improve efficiency in OCT-based diagnosis and reduce processing time.

Uploaded by

Anonymous 1aqlkZ
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
110 views3 pages

Automated Macular Pathology Detection

This document proposes an automated system to diagnose multiple macular pathologies in retinal optical coherence tomography (OCT) images. Existing systems are time-consuming and rely on specialist interpretation. The proposed system uses normalization, morphological operations, and curve filling for pre-processing, and extracts texture and shape features using gray-level co-occurrence matrix (GLCM) and principal component analysis (PCA). A support vector machine classifier then identifies normal macula and macular pathologies like holes, cysts, and age-related macular degeneration. This automated process could improve efficiency in OCT-based diagnosis and reduce processing time.

Uploaded by

Anonymous 1aqlkZ
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Automated macular pathology diagnosis in retinal OCT images

Abstract:

Optical Coherence Tomography (OCT) is a non-contact, noninvasive imaging


technique which performs optical sectioning at microscopic resolution. This
technology measures the optical back scattering of the tissues of the eye, making it
possible to visualize intraocular structures such as the retina and the optic nerve
head. The ability to visualize the internal structures of the retina makes it possible
to diagnose diseases, such as glaucoma and macular hole, objectively and
quantitatively.

Existing system

OCT imaging technology continues to evolve, the development of technology to


assist in the interpretation of OCT images has not kept pace. With OCT data being
generated in increasingly larger amounts and captured at increasingly higher
sampling rates, there is a strong need for computer assisted analysis to support
disease diagnosis. This need is amplified by the fact that an ophthalmologist
making a diagnosis under standard clinical conditions does not have the assistance
of a specialist in interpreting OCT data. This is in contrast to other medical
imaging situations, where a radiologist is usually available. There have been some
previous works addressing topics in ocular OCT image processing, such as intra-
retinal layer segmentation, optic disc segmentation, detection of fluid-filled areas
and local quality assessment. However, to our knowledge, there has been no prior
work on automated macular pathology identification in OCT images.
Disadvantages of Existing System

1. No Automated system for detection of macular pathology


2. Time Consuming Process

Proposed System

We propose a system to determine the probability that each common type of


pathology is present in a given macular cross-section from a known anatomical
Position. The objective of proposed system is to diagnosis of multiple macular
pathologies in retinal OCT images. The goal is to identify the presence of normal
macula and each of three types of macular pathologies, namely, macular hole, cyst
detection OCT, denoising decrypting of OCT images and age-related macular
degeneration. We use normalization technique for smoothing the input image and
morphological and curve filling techniques for segmentation. Our local features are
dimension-reduced local binary pattern histograms, which are capable of encoding
texture and shape information in retinal OCT images and their edge maps,
respectively. Features are extracted using GLCM and PCA algorithm .Our
representation operates at multiple spatial scales and granularities, leading to
robust performance. We use support vector machine classifiers to identify the
presence of normal macula and each of the three pathologies. To further
discriminate sub-types within a pathology, we also build a classifier to differentiate
full-thickness holes from pseudo-holes within the macular hole category.

Advantages:

1. Improved in the efficiency of OCT-based ocular pathology


2. Automated process
3. Reduced Processing time

Software Requirements :

1. MATLAB R2013a
2. Coding Language: C
3. Tool: Image processing

Block Diagram:

INPUT NORMALIZATION MORPHOLOGICAL


CURVE FILLING
IMAGE OPERATION
PRE-PROCESSING

DATASET GLCM

FEATURE
SUPPORT VECTOR EXTRACTION
OUTPUT MECHINE-
CLASSIFIER
PCA

You might also like