Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention.

Purpose: Automatic multilabel classification of multiple fundus diseases is of importance for ophthalmologists. This study aims to design an effective multilabel classification model that can automatically classify multiple fundus diseases based on color fundus images. Methods: We proposed a multilabel fundus disease classification model based on a convolutional neural network to classify normal and seven categories of common fundus diseases. Specifically, an attention mechanism was introduced into the network to further extract information features from color fundus images. The fundus images with eight categories of labels were applied to train, validate, and test our model. We employed the validation accuracy, area under the receiver operating characteristic curve (AUC), and F1-score as performance metrics to evaluate our model. Results: Our proposed model achieved better performance with a validation accuracy of 94.27%, an AUC of 85.80%, and an F1-score of 86.08%, compared to two state-of-the-art models. Most important, the number of training parameters has dramatically dropped by three and eight times compared to the two state-of-the-art models. Conclusions: This model can automatically classify multiple fundus diseases with not only excellent accuracy, AUC, and F1-score but also significantly fewer training parameters and lower computational cost, providing a reliable assistant in clinical screening. Translational Relevance: The proposed model can be widely applied in large-scale multiple fundus disease screening, helping to create more efficient diagnostics in primary care settings.

Doubles trouble-85 cases of ocular trauma in badminton: clinical features and prevention.

OBJECTIVES: To describe ocular injuries caused by badminton and to explore the implications for future prevention strategies. METHODS: We enrolled 85 patients with ocular trauma caused by badminton. Information collected from patients included type of game, instigator, instrument of injury and lessons in badminton from a professional, and ocular trauma information such as type of injury, treatment and final outcomes. RESULTS: The 85 patients (52 men, 33 women) were aged 15-65 years with an average age of 42.9 (±10.7) years. In 60 cases the player was hit by a shuttlecock and in 25 the player was hit by a racquet. 73 cases occurred in doubles matches and 10 in singles matches. In 31 cases the trauma was caused by an opponent and in 52 cases by a partner; 2 cases involved bystanders, not players. About 70% (43/61) of the injured and 82% (40/49) of the instigators had not received badminton lessons from a professional. 80 injuries were non-penetrating and 5 were penetrating. There were 58 cases with hyphaema, 36 with secondary glaucoma, 23 with lens subluxation and 2 with retinal detachment. Surgery comprised phacoemulsification or lensectomy and vitrectomy in 16 cases, silicone oil tamponade in 2 cases, trabeculectomy in 3 cases and direct cyclopexy in 5 cases. CONCLUSION: The vast majority of the badminton related eye injuries occurred among doubles players and were instigated by the injured person's partner. Non-penetrating injury was more frequent; penetrating injury was usually more serious. We recommend that badminton players use protective eyewear and receive safety education and professional coaching/instruction on techniques to protect against serious eye injuries.