We have some good news for our RetCAD product. Recently, a validation study using RetCAD software has been published online. The RetCAD software version has been validated for the joint automatic detection of Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) on a dataset of 600 fundus images with mixed presence of eye diseases. Each image was graded for DR and AMD by an experienced ophthalmologist to establish the reference standard (RS), and by four independent observers for comparison with human performance. Validation was furtherly assessed on Messidor (1200 images) for individual identification of referable DR, and the Age‐Related Eye Disease Study (AREDS) dataset (133 821 images) for referable AMD, against the corresponding RS.
The RetCAD system achieved and AUC of 95.1% and 94.9% for detection referable DR and AMD, respectively. Sensitivity and specificity were 90.1% and 90.6% for DR and 91.8% and 87.5% for AMD. For the human experts, the average sensitivity and specificity were 61.5% and 97.8% for DR and 76.5% and 96.1% for AMD. On the additional validation sets Messidor and AREDS, the AUC of the system was 97.5% and 92.7%.
This work shows that RetCAD can facilitate access to joint screening of eye diseases and become a quick and reliable support to ophthalmologists.
It was also announced that RetCAD is now approved for clinical use in Singapore.