AIMS: To assess the safety and workload reduction of an automated 'disease/no disease' grading system for diabetic retinopathy (DR) within a systematic screening programme. METHODS: Single 45° macular field image per eye was obtained from consecutive patients attending a regional primary care based DR screening programme in Valencia (Spain). The sensitivity and specificity of automated system operating as 'one or more than one microaneurysm detection for disease presence' grader were determined relative to a manual grading as gold standard. Data on age, gender and diabetes mellitus were also recorded. RESULTS: A total of 5278 patients with diabetes were screened. The median age and duration of diabetes was 69 years and 6.9 years, respectively. Estimated prevalence of DR was 15.6%. The software classified 43.9% of the patients as having no DR and 26.1% as having ungradable images. Detection of DR was achieved with 94.5% sensitivity (95% CI 92.6- 96.5) and 68.8% specificity (95%CI 67.2-70.4). The overall accuracy of the automated system was 72.5% (95%CI 71.1-73.9). CONCLUSIONS: The present retinal image processing algorithm that can act as prefilter to flag out images with pathological lesions can be implemented in practice. Our results suggest that it could be considered when implementing DR screening programmes.
AIMS: To assess the safety and workload reduction of an automated 'disease/no disease' grading system for diabetic retinopathy (DR) within a systematic screening programme. METHODS: Single 45° macular field image per eye was obtained from consecutive patients attending a regional primary care based DR screening programme in Valencia (Spain). The sensitivity and specificity of automated system operating as 'one or more than one microaneurysm detection for disease presence' grader were determined relative to a manual grading as gold standard. Data on age, gender and diabetes mellitus were also recorded. RESULTS: A total of 5278 patients with diabetes were screened. The median age and duration of diabetes was 69 years and 6.9 years, respectively. Estimated prevalence of DR was 15.6%. The software classified 43.9% of the patients as having no DR and 26.1% as having ungradable images. Detection of DR was achieved with 94.5% sensitivity (95% CI 92.6- 96.5) and 68.8% specificity (95%CI 67.2-70.4). The overall accuracy of the automated system was 72.5% (95%CI 71.1-73.9). CONCLUSIONS: The present retinal image processing algorithm that can act as prefilter to flag out images with pathological lesions can be implemented in practice. Our results suggest that it could be considered when implementing DR screening programmes.
Authors: Spencer D Fuller; Jenny Hu; James C Liu; Ella Gibson; Martin Gregory; Jessica Kuo; Rithwick Rajagopal Journal: J Diabetes Sci Technol Date: 2020-10-30
Authors: Soledad Jimenez-Carmona; Pedro Alemany-Marquez; Pablo Alvarez-Ramos; Eduardo Mayoral; Manuel Aguilar-Diosdado Journal: J Clin Med Date: 2021-12-21 Impact factor: 4.241
Authors: Paolo Lanzetta; Valentina Sarao; Peter H Scanlon; Jane Barratt; Massimo Porta; Francesco Bandello; Anat Loewenstein Journal: Acta Diabetol Date: 2020-03-28 Impact factor: 4.280