Zhang Laihe, Huang Ying, Chen Jiaqin, Xu Xiangzhong, Xu Fan, Yao Jin
The Affiliated Eye Hospital, Nanjing Medical University, Nanjing, China.
The Fourth School of Clinical Medicine, Nanjing Medical University, Nanjing, China.
Heliyon. 2024 Apr 10;10(8):e29334. doi: 10.1016/j.heliyon.2024.e29334. eCollection 2024 Apr 30.
To develop a multimodal deep transfer learning (DTL) fusion model using optical coherence tomography angiography (OCTA) images to predict the recurrence of retinal vein occlusion (RVO) and macular edema (ME) after three consecutive anti-VEGF therapies.
This retrospective cross-sectional study consisted of 2800 B-scan OCTA macular images collected from 140 patients with RVO-ME. The central macular thickness (CMT) > 250 μm was used as a criterion for recurrence in the three-month follow-up after three injections of anti-VEGF therapy. The qualified OCTA image preprocessing and the lesion area segmentation were performed by senior ophthalmologists. We developed and validated the clinical, DTL, and multimodal fusion models based on clinical and extracted OCTA imaging features. The performance of the models and experts predictions were evaluated using several performance metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.
The DTL models exhibited higher prediction efficacy than the clinical models and experts' predictions. Among the DTL models, the Vgg19 performed better than that of the other models, with an AUC of 0.968 (95 % CI, 0.943-0.994), accuracy of 0.913, sensitivity of 0.922, and specificity of 0.902 in the validation cohort. Moreover, the fusion Vgg19 model showed the highest prediction efficacy among all the models, with an AUC of 0.972 (95 % CI, 0.946-0.997), accuracy of 0.935, sensitivity of 0.935, and specificity of 0.934 in the validation cohort.
Multimodal fusion DTL models showed robust performance in predicting RVO-ME recurrence and may be applied to assist clinicians in determining patients' follow-up time after anti-VEGF therapy.
利用光学相干断层扫描血管造影（OCTA）图像开发一种多模态深度迁移学习（DTL）融合模型，以预测连续三次抗血管内皮生长因子（VEGF）治疗后视网膜静脉阻塞（RVO）和黄斑水肿（ME）的复发情况。
这项回顾性横断面研究包括从140例RVO-ME患者收集的2800张黄斑区B扫描OCTA图像。中心黄斑厚度（CMT）>250μm被用作三次抗VEGF治疗后三个月随访中复发的标准。合格的OCTA图像预处理和病变区域分割由资深眼科医生进行。我们基于临床和提取的OCTA成像特征开发并验证了临床、DTL和多模态融合模型。使用包括受试者操作特征曲线下面积（AUC）、准确性、敏感性和特异性在内的多个性能指标评估模型和专家预测的性能。
DTL模型表现出比临床模型和专家预测更高的预测效能。在DTL模型中，Vgg19的表现优于其他模型，在验证队列中的AUC为0.968（95%CI，0.943-0.994），准确性为0.913，敏感性为0.922，特异性为0.902。此外，融合Vgg19模型在所有模型中显示出最高的预测效能，在验证队列中的AUC为0.972（95%CI，0.946-0.997），准确性为0.935，敏感性为0.935，特异性为0.934。
多模态融合DTL模型在预测RVO-ME复发方面表现出强大的性能，可应用于协助临床医生确定抗VEGF治疗后患者的随访时间。
