Guy's and St Thomas' NHS Foundation Trust, London, UK.
Centre for Vision, Speech and Signal Processing, Department of Electrical and Electronic Engineering, Faculty of Engineering and Physical Sciences, University of Surrey, Guildford, UK.
Graefes Arch Clin Exp Ophthalmol. 2023 Mar;261(3):715-721. doi: 10.1007/s00417-022-05884-3. Epub 2022 Oct 28.
To develop and evaluate an automated deep learning model to predict the anatomical outcome of rhegmatogenous retinal detachment (RRD) surgery.
Six thousand six hundred and sixty-one digital images of RRD treated by vitrectomy and internal tamponade were collected from the British and Eire Association of Vitreoretinal Surgeons database. Each image was classified as a primary surgical success or a primary surgical failure. The synthetic minority over-sampling technique was used to address class imbalance. We adopted the state-of-the-art deep convolutional neural network architecture Inception v3 to train, validate, and test deep learning models to predict the anatomical outcome of RRD surgery. The area under the curve (AUC), sensitivity, and specificity for predicting the outcome of RRD surgery was calculated for the best predictive deep learning model.
The deep learning model was able to predict the anatomical outcome of RRD surgery with an AUC of 0.94, with a corresponding sensitivity of 73.3% and a specificity of 96%.
A deep learning model is capable of accurately predicting the anatomical outcome of RRD surgery. This fully automated model has potential application in surgical care of patients with RRD.
开发和评估一种自动化深度学习模型，以预测孔源性视网膜脱离（RRD）手术的解剖学结果。
从英国和爱尔兰玻璃体视网膜外科医生协会数据库中收集了 661 张接受玻璃体切除术和内填塞治疗的 RRD 的数字图像。每张图像都被分类为原发性手术成功或原发性手术失败。采用合成少数过采样技术来解决类别不平衡问题。我们采用了最先进的深度卷积神经网络架构 Inception v3 来训练、验证和测试深度学习模型，以预测 RRD 手术的解剖学结果。计算了最佳预测 RRD 手术结果的深度学习模型的曲线下面积（AUC）、灵敏度和特异性。
深度学习模型能够以 0.94 的 AUC 预测 RRD 手术的解剖学结果，相应的灵敏度为 73.3%，特异性为 96%。
深度学习模型能够准确预测 RRD 手术的解剖学结果。这种全自动模型在 RRD 患者的手术护理中有潜在的应用。
