Deep learning-based risk classification and auxiliary diagnosis of macular edema

• Published in: Intelligence-based medicine Vol. 6; p. 100053
• Main Authors: Wu, Tianzhu, Liu, Liting, Zhang, Tianer, Wu, Xuesen
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 2022
• Subjects: CNN; Deep learning; Diabetic macular edema; Deep learning; CNN; Diabetic macular edema
• ISSN: 2666-5212; 2666-5212
• DOI: 10.1016/j.ibmed.2022.100053

Diabetic macular edema is one of the main causes of visual impairment in patients with diabetic retinopathy. As the number of patients with diabetes increases, so will the number of patients with diabetic macular edema. Early screening of patients for macular edema can provide timely and scientific clinical diagnosis and treatment. In this paper, we take fundus images of diabetic retinopathy patients as the processing object and use artificial intelligence technology to construct an automatic macular edema classification model, in order to achieve low-cost and rapid fundus image classification. This can be considered beneficial for the screening of macular edema patients on a large scale. In this paper, a computerized automatic macular edema grading model is constructed using a senet154 convolutional neural network embedded within the Squeeze-and-Excitation module, optimizing the algorithm to use the imbalanced public data set Messidor and drawing class activation maps to aid in diagnosis. The AUCs of macular edema risk grades 0, 1, and 2 were 0.965, 0.881, and 0.963, respectively. Class activation mappings correctly mark focal areas for macular edema risk classification in fundus images. The constructed grading model showed a good recognition rate for fundus image variations caused by diabetic retinopathy. These results are of certain theoretical and practical significance for the auxiliary diagnosis of macular edema risk grades. •The Squeeze-and-Excitation attention mechanism allows the model to focus more on the most informative channel features and to suppress those that are less important.•An automatic risk classification model for diabetic macular edema has been innovatively developed and constructed.•The diagnosis is followed by the output of a class activation mapping to label the focal area, both to classify the risk of DME and to assist the doctor in making the diagnosis.