Influence of Different Types of Retinal Cameras on the Performance of Deep Learning Algorithms in Diabetic Retinopathy Screening

Background: The aim of this study was to assess the performance of regional graders and artificial intelligence algorithms across retinal cameras with different specifications in classifying an image as gradable and ungradable. Methods: Study subjects were included from a community-based nationwide diabetic retinopathy screening program in Thailand. Various non-mydriatic fundus cameras were used for image acquisition, including Kowa Nonmyd, Kowa Nonmyd alpha-DIII, Kowa Nonmyd 7, Kowa Nonmyd WX, Kowa VX 10 alpha, Kowa VX 20 and Nidek AFC 210. All retinal photographs were graded by deep learning algorithms and human graders and compared with a standard reference. Results: Images were divided into two categories as gradable and ungradable images. Four thousand eight hundred fifty-two participants with 19,408 fundus images were included, of which 15,351 (79.09%) were gradable images and the remaining 4057 (20.90%) were ungradable images. Conclusions: The deep learning (DL) algorithm demonstrated better sensitivity, specificity and kappa than the human graders for all eight types of non-mydriatic fundus cameras. The deep learning system showed, more consistent diagnostic performance than the human graders across images of varying quality and camera types.

Automated summary

This study assessed the performance of regional graders and artificial intelligence algorithms in classifying images as gradable or ungradable using retinal cameras of different specifications. The deep learning algorithm outperformed human graders in sensitivity, specificity, and kappa for all types of non-mydriatic fundus cameras. The deep learning system showed consistent diagnostic performance across images of varying quality and camera types, surpassing human graders.