Automated detection of diabetic retinopathy in a fundus photographic screening population

被引:59
|
作者
Larsen, N [1 ]
Godt, J
Grunkin, M
Lund-Andersen, H
Larsen, M
机构
[1] Univ Copenhagen, Herlev Hosp, Dept Ophthalmol, DK-2730 Herlev, Denmark
[2] Steno Diabet Ctr, DK-2820 Gentofte, Denmark
[3] Retinalyze AS, Horsholm, Denmark
关键词
D O I
10.1167/iovs.02-0417
中图分类号
R77 [眼科学];
学科分类号
100212 ;
摘要
PURPOSE. To evaluate the performance of an automated fundus photographic image-analysis algorithm in high-sensitivity and/or high-specificity segregation of patients with diabetes with untreated diabetic retinopathy from those without retinopathy. METHODS. This was a retrospective cross-sectional study of 260 consecutive nonphotocoagulated eyes in 137 diabetic patients attending routine photographic retinopathy screening. Mydriatic 60degrees fundus photography on 35-mm color transparency film was used, with a single fovea-centered field. Routine grading was based on visual examination of slide-mounted transparencies. Reference grading was performed with specific emphasis on achieving high sensitivity. Computer-assisted automated red lesion detection was performed on digitized transparencies. RESULTS. When applied in a screening population comprising patients with diabetes with untreated diabetic retinopathy in any eye and patients with diabetes without retinopathy, the automated lesion detection correctly identified 90.1% of patients with retinopathy and 81.3% of patients without retinopathy. A per-eye analysis for methodological purposes demonstrated that the automated lesion detection could be adapted to simulate various visual evaluation strategies. When adapted at high sensitivity, the automated system demonstrated sensitivity at 93.1% and specificity at 71.6%. When adapted at high specificity the automated system demonstrated sensitivity at 76.4% and specificity at 96.6%, closely matching routine visual grading at sensitivity 76.4% and specificity 98.3%. CONCLUSIONS. Automated detection of untreated diabetic retinopathy in fundus photographs from a screening population of patients with diabetes can be made with adjustable priority settings, emphasizing high-sensitivity identification of diabetic retinopathy or high-specificity identification of absence of retinopathy, covering opposing extremes of visual evaluation strategies demonstrated by human observers.
引用
收藏
页码:767 / 771
页数:5
相关论文
共 50 条
  • [1] Automated detection of fundus photographic red lesions in diabetic retinopathy
    Larsen, M
    Godt, J
    Larsen, N
    Lund-Andersen, H
    Sjolie, AK
    Agardh, E
    Kalm, H
    Grunkin, M
    Owens, DR
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2003, 44 (02) : 761 - 766
  • [2] Automated detection of fundus photographic dark lesions in diabetic retinopathy.
    Sander, B
    Godt, J
    Lund-Andersen, H
    Grunkin, M
    Owens, D
    Larsen, N
    Larsen, M
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2001, 42 (04) : S809 - S809
  • [3] Automated detection of diabetic retinopathy on digital fundus images
    Sinthanayothin, C
    Boyce, JF
    Williamson, TH
    Cook, HL
    Mensah, E
    Lal, S
    Usher, D
    DIABETIC MEDICINE, 2002, 19 (02) : 105 - 112
  • [4] Detection of diabetic retinopathy by automated fundus image analysis
    Larsen, M
    Godt, J
    Larsen, N
    Lund-Andersen, H
    Grunkin, M
    Owens, DR
    DIABETES, 2001, 50 : A193 - A193
  • [5] A Review of Fundus Image Analysis for the Automated Detection of Diabetic Retinopathy
    Noronha, Kevin
    Nayak, K. Prabhakar
    JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2012, 2 (03) : 258 - 265
  • [6] Automated Detection of Diabetic Retinopathy in Blurred Digital Fundus Images
    Shahin, Eman M.
    Taha, Taha E.
    Al-Nuaimy, W.
    El Rabaie, S.
    Zahran, Osama F.
    Abd El-Samie, Fathi E.
    2012 8TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO): TODAY INFORMATION SOCIETY WHAT'S NEXT?, 2012, : 20 - 25
  • [7] Automated Detection of Diabetic Retinopathy from Smartphone Fundus Videos
    Mueller, Simon
    Karpova, Snezhana
    Wintergerst, Maximilian W. M.
    Murali, Kaushik
    Shanmugam, Mahesh P.
    Finger, Robert P.
    Schultz, Thomas
    OPHTHALMIC MEDICAL IMAGE ANALYSIS, OMIA 2020, 2020, 12069 : 83 - 92
  • [8] Prevalence of diabetic retinopathy in an urban diabetic population based on a single-field nonnnydriatic digital fundus photographic screening modality
    Lin, DY
    Blumenkranz, MS
    Brothers, RJ
    Grosvenor, DM
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2002, 43 : U1263 - U1263
  • [9] Automated detection of exudates for diabetic retinopathy screening
    Fleming, Alan D.
    Philip, Sam
    Goatman, Keith A.
    Williams, Graeme J.
    Olson, John A.
    Sharp, Peter F.
    PHYSICS IN MEDICINE AND BIOLOGY, 2007, 52 (24): : 7385 - 7396
  • [10] Automated Detection of Optic Disc from Digital Retinal Fundus Images for Screening Systems of Diabetic Retinopathy
    高玮玮
    马晓峰
    左晶
    Journal of Donghua University(English Edition), 2020, 37 (01) : 74 - 79