Background Myopic maculopathy (MM) is one of the major causes of visual impairment and irreversible blindness in eyes with pathologic myopia (PM). However, the classification of each type of lesion associated with MM has not been determined. Recently, a new MM classification system, known as the ATN grading and classification system, was proposed; it is based on the fundus photographs and optical coherence tomography (OCT) images and includes three variable components: atrophy (A), traction (T), and neovascularization (N). This study aimed to perform an independent evaluation of interobserver and intraobserver agreement for the recently developed ATN grading system for MM. Methods This was a retrospective study. Fundus photographs and OCT images of 125 patients (226 eyes) with various MMs were evaluated and classified using the ATN grading of the new MM classification system by four blinded and independent evaluators (2 attending ophthalmologists and 2 ophthalmic residents). All cases were randomly re-evaluated by the same observers after an interval of 6 weeks. The kappa coefficient (κ) and 95% confidence interval (CI) were used to determine the interobserver and intraobserver agreement. Results The interobserver agreement was substantial when considering the maculopathy type (A, T, and N). The weighted Fleiss κ values for each MM type (A, T, and N) were 0.651 (95% CI: 0.602–0.700), 0.734 (95% CI: 0.689–0.779), and 0.702 (95% CI: 0.649–0.755), respectively. The interobserver agreement when considering the subtypes was good or excellent, except for stages A1, A2, and N1, in which the weighted κ value was less than 0.6, with moderate agreement. The intraobserver agreement of types and subtypes was excellent, with κ > 0.8. No significant differences were observed between the attending ophthalmologists and residents for interobserver reliability or intraobserver reproducibility. Conclusions The ATN classification allows an adequate agreement among ophthalmologists with different qualifications and by the same observer on separate occasions. Future prospective studies should further evaluate whether this classification can be better implemented in clinical decision-making and disease progression assessments.
BackgroundTo develop and validate a deep transfer learning (DTL) algorithm in detecting abnormalities of fundus images from non-mydriatic fundus photography examination.Methods1,295 fundus images from January 2017 to December 2018 at Yijishan Hospital of Wannan Medical College were collected for developing and validating the deep transfer learning algorithm in detecting abnormal fundus images. The DTL model was developed by using 929(normal 254, abnormal 402) fundus images, including normal fundus images and abnormal fundus images, the latter including, maculopathy, optic neuropathy, vascular lesion, choroidal lesions, vitreous disease, cataract and the others. We tested our model using a subset of the publically available MESSIDOR dataset (using 366 images) and evaluate the testing performance of the DTL model for detecting abnormal fundus images. ResultsIn the internal validation data set (n=273 images), the AUC, sensitivity, accuracy and specificity of the DTL for correctly classified funds images were 0.997, 97.41%, 97.07% and 96.82%, respectively. For test data set (n=273 images), the AUC, sensitivity, accuracy and specificity of the DTL for correctly classification funds images were 0.926, 88.17%, 87.18% and 86.67%, respectively.ConclusionIn the evaluation, the DTL presented high sensitivity and specificity for detecting abnormal fundus-related diseases. Further research is necessary to improve this method and evaluate the applicability of the DTL in the community health care center.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.