Journals / Retina-Vitreus / 2009 / Cilt: 17 - Sayı: 2

Otomatik bilgisayarlı sistemle gözdibi fotoğraflarından diabetik retinopatinin derecelendirilmesi

Automated computer system grading of diabetic retinopathy from fundus photographs

Pages
114–119
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Conclusions: Computer algorithms were able to detect and grade retinopathy from fundus photographs taken of a set of sequentially screened diabetics with consistency similar to the agreement in grading between a general ophthalmologist and a retina specialist.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Purpose: To evaluate the efficacy of computer algorithms in the detection and grading of retinopathy derived from screening of diabetic photographs.
📊
Key Findings & Data:Methods: Screening fundus photographs (5 per eye) taken with a mydriatic camera in a general ophthalmology clinic for 52 sequential diabetic patients were graded by a general ophthalmologist and a retina specialist and compared with computer grading of digitized images acquired from color slides.
💡
Conclusion & Impact:Conclusions: Computer algorithms were able to detect and grade retinopathy from fundus photographs taken of a set of sequentially screened diabetics with consistency similar to the agreement in grading between a general ophthalmologist and a retina specialist.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Algoritma · Floresan anjiyografi · Diabetik retinopati

Abstract

Purpose: To evaluate the efficacy of computer algorithms in the detection and grading of retinopathy derived from screening of diabetic photographs. Methods: Screening fundus photographs (5 per eye) taken with a mydriatic camera in a general ophthalmology clinic for 52 sequential diabetic patients were graded by a general ophthalmologist and a retina specialist and compared with computer grading of digitized images acquired from color slides. Results: Among the 104 eyes, 64 (61.5%) had no retinopathy lesions (Grade 10), 6 (5.8%) eyes had only 1 or 2 microaneurysms, 21 (20.2%) eyes had more than 2 microaneurysms but no other lesions (grade 21), and 18 (17.3%) had additional lesions (grade 21+). Among the ophthalmologists, there was exact agreement in the grading of 76 eyes; in 21 eyes grading by each was within 1 grade level, and in 7 the grades differed by 2 grade levels. Computer algorithm grading agreed with the ophthalmologists’ grade in 51 (50%) eyes; in 24 (23%) eyes the computer under-graded by one grade level, and by 2 grades in 2 eyes. In 22 (21%) eyes, computer grading was greater by one grade level than the ophthalmologists’ grading and in 5 (5%) eyes the algorithms overgraded by 2 grades. Conclusions: Computer algorithms were able to detect and grade retinopathy from fundus photographs taken of a set of sequentially screened diabetics with consistency similar to the agreement in grading between a general ophthalmologist and a retina specialist.

Özet

Amaç: Diabetik hastaların fotografları tarayarak elde edilen retinopati bulunmasında ve derecelendirmesinde bilgisayar algoritimalarının etkinliğini araştırmak. Gereç ve Yöntem: Genel göz kliniğinde ardışık 52 diabetik hastanın midriatik kamera ile alınan gözdibi tarama fotografları (her göz için 5) genel göz doktorları ve retina uzmanları tarafından derecelendirildi ve renkli resimlerden elde edilen dijital imajların bilgisayar derecelendirilmesi ile karşılaştırıldı. Bulgular: Toplam 104 gözden 64 (%61.5) gözde retinopati lezyonu yoktu (Grade 10), 6 (%5.8) göz sadece 1 yada 2 mikroanevrizmaya, 21 (%20.2) göz 2’den fazla mikroanevrizmaya sahipti fakat başka lezyon yoktu. (grade 21) ve 18 (%17.3) gözde ek lezyonlar vardı (grade 21+). Tüm göz doktorları, 76 gözün derecelendirilmesinde bilgisayar derecelendirmesi ile tamamen aynı fikirde idi, her biri arasında 21 gözün derecelendirmesinde bir seviye, ve 7’sinde dereceler arasında 2 derece seviyesi fark vardı. 51 (%50) gözün bilgisayar algoritma derecelendirmesi ile göz doktoru derecelendirmesi aynı idi; 24 (%23) gözde bilgisayar derecelendirmesi göz doktoru derecelendirmesinden bir seviye aşağı ve 2 gözde de iki seviye aşağı idi. 22 (%21) gözde bilgisayar değerlendirmesi göz doktoru derecelendirmesinden bir seviye yukarı ve 5 (%5) gözde 2 derece fazla idi. Sonuç: Bilgisayar algoritmaları önceden hazırlanmış bir ardışık diabetik hasta taramasından alınan gözdibi fotograflarından, genel göz doktorları ve retina uzmanları arasında derecelendirmedeki karar uygun benzerlikte, retinopatiyi tespit edebildi ve derecelendirebildi.

🔖

Cite This Article

ÜNVER, Y. B., YAVUZ, G. A., SINCLAIR, S. H. (2009). Otomatik bilgisayarlı sistemle gözdibi fotoğraflarından diabetik retinopatinin derecelendirilmesi. Retina-Vitreus, Cilt: 17 - Sayı: 2, 114–119. https://ajindex.com/articles/308101

References (17)

  1. American Diabetes Association PS.: Implications of the diabetes control and complications trial. Clin Diabetes. 1993;11:91-96
  2. Klein R.: Barriers to prevention of vision loss caused by diabetic retinopathy. Arch Ophthalmol. 1997;115:1073-1074
  3. Early Treatment Diabetic Retinopathy Study Research Group.: Photocoagulation for diabetic macular edema: Early Treatment Diabetic Retinopathy Study Report no
  4. Int Ophthalmol Clin. 1987;27:265-272
  5. Diabetic Retinopathy Study Research Group.: Photocoagulation treatment of proliferative diabetic retinopathy. Ophthalmology. 1981;88:583
  6. Donovan J.: Patient decision making: The missing ingredient in compliance research. International journal of technology assessment in health care. 1995;11:443-455
  7. Brechner R, Cowie C, Howie L, et al.: Ophthalmic examination among adults with diagnosed diabetes mellitus. JAMA. 1993; 270:1714-1718
  8. Sussman E, Tsiaras W,Soper K.: Diagnosis of diabetic eye disease. JAMA. 1982;247:3231-3234
  9. Kleinstein R, Roseman J, Herman W, et al.: Detection of diabetic retinopathy by optometrists. J Am Optom Assoc. 1987;58:879-882
  10. Kraft S, Marrero D, Lazaridis E, et al.: Primary care physicians’ practice patterns and diabetic retinopathy. Current levels of care. Arch FAM Med. 1997;6:29-37
  11. Moss S, Klein R, Kressler S, Richie K.: Comparison between ophthalmoscopy and fundus photography in determining severity of diabetic retinopathy. Ophthalmology. 1985;92:62-67
  12. Valez R, Haffner S, Stern M.: Ophthalmologist vs retinal photographs in screening for diabetic retinopathy. Clin Res. 1987;35:363A
  13. O’Hare J, Hopper A, Madhaven C, et al.: Adding retinal photography to screening for diabetic retinopathy: a prospective study in primary care. BMJ. 1996;312:679-682
  14. Klein R, Moss S, Klien B.: New management concepts for timely diagnosis of diabetic retinopathy treatable by photocoagulation. Diabetes Care. 1987;10:633-638
  15. Early Treatment Diabetic Retinopathy Study Research Group.: Grading diabetic retinopathy from stereoscopic color fundus photographs-an extension of the modified Airlie house classification: ETDRS report number 10. Ophthalmology. 1991;98:786-806
  16. Goldbaum M, Katz N, Nelson M, et al.: The discrimination of similarly colored objects in computer images of the ocular fundus. Invest Ophthalmol Vis Sci. 1990;31:617-623
  17. Cree M, Olson J, McHardy K, et al.: A fully automated comparative microaneurysm digital detection system. Eye. 1997;11:622-628. 17.