生成式深度学习预测年龄相关性黄斑变性治疗后12个月的光学相干断层扫描图像
本研究纳入513例未经治疗的新生血管性年龄相关性黄斑变性患者的533只眼,采用条件生成对抗网络,以治疗前OCT、荧光素眼底血管造影和吲哚菁绿血管造影生成12个月后的OCT图像。依次加入三次负荷剂量后OCT、基线视力、治疗方案、药物类型及换药事件后,模型区分湿性与干性黄斑状态的准确率达92%。
要点
- 基线模型对4个黄斑液体腔隙的预测准确度为0.74-0.96。
- 加入负荷剂量后OCT及其他临床参数后准确度提升至0.91-0.98。
- 整合全部临床输入后,模型区分湿性与干性黄斑状态的准确率为92%。
核心结论
- 整合临床和治疗数据,尤其是负荷剂量后的OCT数据,显著提升了条件生成对抗网络对12个月解剖结果的预测性能。
- 该方法可帮助临床医生预判解剖结局并指导个体化长期治疗策略。
研究设计与样本
- 研究纳入513例未经治疗的新生血管性年龄相关性黄斑变性患者的533只眼。
- 以条件生成对抗网络为基线模型,利用治疗前OCT、荧光素眼底血管造影和吲哚菁绿血管造影生成12个月OCT图像。
- 依次加入三次负荷剂量后OCT、基线视力、治疗方案(按需治疗或治疗-延长)、药物类型及换药事件。
- 对生成图像与患者OCT图像中的视网膜内液、视网膜下液、色素上皮脱离和视网膜下高反射物质进行定性和定量比较。
主要发现
- 基线模型对4个黄斑液体腔隙的预测准确度范围为0.74-0.96。
- 加入负荷剂量后OCT及其他临床参数后,准确度范围为0.91-0.98。
- 整合全部临床输入后,模型区分湿性与干性黄斑状态的准确率为92%。
- 生成图像中分割的液体腔隙与患者图像中的相应腔隙呈正相关。
临床怎么用
- 作者认为该方法可帮助临床医生预判解剖结局并指导个体化长期新生血管性年龄相关性黄斑变性治疗策略。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: Predicting long-term anatomical responses in neovascular age-related macular degeneration patients is critical for patient-specific management. This study validates a generative deep learning model to predict 12-month posttreatment optical coherence tomography (OCT) images and evaluates the impact of incorporating clinical data on predictive performance. METHODS: A total of 533 eyes from 513 treatment-naïve neovascular age-related macular degeneration patients were analyzed. A conditional generative adversarial network served as the baseline model, generating 12-month OCT images using pretreatment OCT, fluorescein angiography, and indocyanine green angiography. We then sequentially added OCT after three loading doses, baseline visual acuity, treatment regimen (pro re nata or treat-and-extend), drug type, and switching events. The generated and patient OCT images were compared for intraretinal fluid, subretinal fluid, pigment epithelial detachment, and subretinal hyperreflective material, both qualitatively and quantitatively. RESULTS: The baseline model achieved acceptable accuracy for 4 macular fluid compartments (range 0.74-0.96). Incorporating OCT after loading doses and other clinical parameters improved accuracy (range 0.91-0.98). With all the clinical inputs, the model achieved 92% accuracy in distinguishing wet macular status from dry macular status. The segmented fluid compartments in the generated images correlated positively with those in the patient images. CONCLUSION: Integrating clinical and treatment data, particularly OCT data after loading doses, significantly enhanced the 12-month predictive performance of conditional generative adversarial networks. This approach can help clinicians anticipate anatomical outcomes and guide personalized, long-term neovascular age-related macular degeneration treatment strategies.
引用
- Lee H, Kim N, Kim NH, et al. GENERATIVE DEEP LEARNING APPROACH TO PREDICT POSTTREATMENT OPTICAL COHERENCE TOMOGRAPHY IMAGES OF AGE-RELATED MACULAR DEGENERATION AFTER 12 MONTHS. Retina. 2025. PMID: 39841905. doi:10.1097/IAE.0000000000004409
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。