Automated Analysis of Diabetic Retinopathy Images: Principles, Recent Developments, and Emerging Trends.

School of Computing, Informatics & Decision Systems Engineering, Arizona State University, 699 S Mill AVE #553, Tempe, AZ, 85281, USA, .
Current Diabetes Reports (Impact Factor: 3.38). 05/2013; 13(4). DOI: 10.1007/s11892-013-0393-9
Source: PubMed

ABSTRACT Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The optic disk (OD) center and margin are typically requisite landmarks in establishing a frame of reference for classifying retinal and optic nerve pathology. Reliable and efficient OD localization and segmentation are important tasks in automatic eye disease screening. This paper presents a new, fast, and fully automatic OD localization and segmentation algorithm developed for retinal disease screening. First, OD location candidates are identified using template matching. The template is designed to adapt to different image resolutions. Then, vessel characteristics (patterns) on the OD are used to determine OD location. Initialized by the detected OD center and estimated OD radius, a fast, hybrid level-set model, which combines region and local gradient information, is applied to the segmentation of the disk boundary. Morphological filtering is used to remove blood vessels and bright regions other than the OD that affect segmentation in the peripapillary region. Optimization of the model parameters and their effect on the model performance are considered. Evaluation was based on 1200 images from the publicly available MESSIDOR database. The OD location methodology succeeded in 1189 out of 1200 images (99% success). The average mean absolute distance between the segmented boundary and the reference standard is 10% of the estimated OD radius for all image sizes. Its efficiency, robustness, and accuracy make the OD localization and segmentation scheme described herein suitable for automatic retinal disease screening in a variety of clinical settings.
    IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society 05/2012; 16(4):644-57. DOI:10.1109/TITB.2012.2198668 · 1.69 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: OBJECTIVE— To evaluate the performance of a system for automated detection of diabetic retinopathy in digital retinal photographs, built from published algorithms, in a large, representative, screening population. RESEARCH DESIGN AND METHODS— We conducted a retrospective analysis of 10,000 consecutive patient visits, specifically exams (four retinal photographs, two left and two right) from 5,692 unique patients from the EyeCheck diabetic retinopathy screening project imaged with three types of cameras at 10 centers. Inclusion criteria included no previous diagnosis of diabetic retinopathy, no previous visit to ophthalmologist for dilated eye exam, and both eyes photographed. One of three retinal specialists evaluated each exam as unacceptable quality, no referable retinopathy, or referable retinopathy. We then selected exams with sufficient image quality and determined presence or absence of referable retinopathy. Outcome measures included area under the receiver operating characteristic curve (number needed to miss one case [NNM]) and type of false negative. RESULTS— Total area under the receiver operating characteristic curve was 0.84, and NNM was 80 at a sensitivity of 0.84 and a specificity of 0.64. At this point, 7,689 of 10,000 exams had sufficient image quality, 4,648 of 7,689 (60%) were true negatives, 59 of 7,689 (0.8%) were false negatives, 319 of 7,689 (4%) were true positives, and 2,581 of 7,689 (33%) were false positives. Twenty-seven percent of false negatives contained large hemorrhages and/or neovascularizations. CONCLUSIONS— Automated detection of diabetic retinopathy using published algorithms cannot yet be recommended for clinical practice. However, performance is such that evaluation on validated, publicly available datasets should be pursued. If algorithms can be improved, such a system may in the future lead to improved prevention of blindness and vision loss in patients with diabetes.
    Diabetes care 09/2008; 31(8):e63; author reply e64. DOI:10.2337/dc08-0827 · 7.74 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: To evaluate single-field digital monochromatic nonmydriatic fundus photography as an adjunct in the screening of diabetic retinopathy. Prospective, comparative, observational case series. Patients with type I and type II diabetes mellitus (n = 197) were sequentially evaluated by three different techniques: single-field digital monochromatic nonmydriatic photography; dilated ophthalmoscopy by an ophthalmologist; and seven Early Treatment Diabetic Retinopathy Study (ETDRS) standardized 35-mm color stereoscopic mydriatic images. The seven stereoscopic color photographs served as the reference standard and were compared with either ophthalmoscopy or a single digital photograph transmitted electronically to a reading site. Levels of agreement were determined by kappa analyses. The sensitivity and specificity of the three methods were compared based on a threshold for referral to further ophthalmologic evaluation (ETDRS level > or =35). There was highly significant agreement (kappa = 0.97, P =.0001) between the degree of retinopathy detected by a single nonmydriatic monochromatic digital photograph and that seen in seven standard 35-mm color stereoscopic mydriatic fields. The sensitivity of digital photography compared with color photography was 78%, with a specificity of 86%. Agreement was poor (kappa = 0.40, P =.0001) between mydriatic ophthalmoscopy and the seven-field standard 35-mm color photographs. Sensitivity of ophthalmoscopy compared with color photography was 34%, with a specificity of 100%. A single nonmydriatic monochromatic wide-field digital photograph of the disk and macula was more sensitive for diabetic retinopathy screening than mydriatic ophthalmoscopy, the currently accepted screening method. When adjudicated by standard seven-field color photographs, the higher sensitivity of digital photography primarily reflected the reduced sensitivity of ophthalmoscopy in detecting early retinopathy.
    American Journal of Ophthalmology 08/2002; 134(2):204-13. DOI:10.1016/S0002-9394(02)01522-2 · 4.02 Impact Factor