Optical coherence tomography angiography (OCTA), as a non-invasive three-dimensional fundus vascular imaging technique, has significant advantages in the diagnosis and follow-up of eye diseases such as diabetic retinopathy and age-related macular degeneration. However, the existence of OCTA image artifacts has seriously affected its clinical application. These artifacts are caused by various factors such as image acquisition, internal characteristics of the eyeball, eye movement and image processing, such as weak signals, blinking, defocusing, bands, tilting, occlusion, exposure, projection, movement and layering, leading to vascular quantization deviation, lesion blurring and image distortion, thereby reducing the accuracy of clinical diagnosis. To address this issue, researchers have proposed a variety of correction strategies, including enhancing signal strength, optimizing equipment, developing algorithms to identify and eliminate shadow artifacts, using hardware or software methods for motion correction, and employing deep learning algorithms for image quality assessment and artifact removal. Constructing a unified and systematic framework for artifact cognition and processing is crucial for enhancing the reliability of OCTA diagnostic results and will drive the level of ophthalmic diagnosis and treatment to a new height.
ObjectivesTo develop a fundus photography (FP) image lesion recognition model based on the EfficientNet lightweight convolutional neural network architecture, and to preliminary evaluate its recognition performance. MethodsA diagnostic test. The data was collected in the Department of Ophthalmology at Sichuan Provincial People's Hospital from June 2023 to June 2025. A lightweight 16-category lesion recognition model was constructed based on deep learning and 610 072 FP images. The FP images were sourced from Sichuan Provincial People's Hospital as well as the APTOS, Diabetic Retinopathy_2015, Diabetic Retinopathy_2019, and Retinal Disease datasets. Model performance was evaluated as follows: first, testing was performed on four independent external validation sets using metrics such as accuracy, F1 score (the harmonic mean of precision and recall), and the area under the receiver operating characteristic curve (AUC) to measure the model's generalizability and accuracy. Second, the classification results of the model were compared with those of junior and mid-level ophthalmologists (two each) using the overlapping confidence interval (CI) comparison method to assess the clinical experience level corresponding to the model's medical proficiency. ResultsThe model achieved an accuracy of 96.78% (59 039/61 003), an F1 score of 82.51% (50 334/61 003), and an AUC of 99.93% (60 960/61 003) on the validation set. On the four external validation sets, it achieved an average accuracy of 87.77% (57 358/65 350), an average precision of 87.06% (56 894/65 350), and an average Kappa value of 82.28%. The average accuracy of FP image lesion identification for junior and mid-level ophthalmologists was 79.00% (79/100) (95%CI 67.71-90.29) and 87.00% (87/100) (95%CI 77.68-96.32), respectively. ConclusionsA 16-category FP image lesion recognition model is successfully constructed based on the EfficientNet lightweight convolutional neural network architecture. Its clinical performance preliminarily reaches the level of mid-level ophthalmologists.