Document Detail


Identification of suitable fundus images using automated quality assessment methods.
MedLine Citation:
PMID:  24718384     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
ABSTRACT. Retinal image quality assessment (IQA) is a crucial process for automated retinal image analysis systems to obtain an accurate and successful diagnosis of retinal diseases. Consequently, the first step in a good retinal image analysis system is measuring the quality of the input image. We present an approach for finding medically suitable retinal images for retinal diagnosis. We used a three-class grading system that consists of good, bad, and outlier classes. We created a retinal image quality dataset with a total of 216 consecutive images called the Diabetic Retinopathy Image Database. We identified the suitable images within the good images for automatic retinal image analysis systems using a novel method. Subsequently, we evaluated our retinal image suitability approach using the Digital Retinal Images for Vessel Extraction and Standard Diabetic Retinopathy Database Calibration level 1 public datasets. The results were measured through the F1 metric, which is a harmonic mean of precision and recall metrics. The highest F1 scores of the IQA tests were 99.60%, 96.50%, and 85.00% for good, bad, and outlier classes, respectively. Additionally, the accuracy of our suitable image detection approach was 98.08%. Our approach can be integrated into any automatic retinal analysis system with sufficient performance scores.
Authors:
Ugur Sevik; Cemal Köse; Tolga Berber; Hidayet Erdöl
Related Documents :
22516594 - Development of image quality assurance support system using image recognition technolog...
21216124 - Susceptibility-weighted imaging of the brain: does gadolinium administration matter?
3595104 - Fast microcomputer-based multipurpose filtering routine.
18282984 - Color image processing using adaptive multichannel filters.
20484694 - Fluorescence/luminescence circadian imaging of complex tissues at single-cell resolution.
25010694 - On plant detection of intact tomato fruits using image analysis and machine learning me...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of biomedical optics     Volume:  19     ISSN:  1560-2281     ISO Abbreviation:  J Biomed Opt     Publication Date:  2014 Apr 
Date Detail:
Created Date:  2014-04-10     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9605853     Medline TA:  J Biomed Opt     Country:  United States    
Other Details:
Languages:  eng     Pagination:  46006     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Paris saponin I induces apoptosis via increasing the Bax/Bcl?2 ratio and caspase?3 expression in gef...
Next Document:  Calibration-free structured-illumination photoacoustic flowgraphy of transverse flow in scattering m...