文献速递青光眼神经眼科

政策驱动的多模态深度学习:从视盘与OCT影像预测视野

Policy-Driven, Multimodal Deep Learning for Predicting Visual Fields from the Optic Disc and OCT Imaging.
PubMed 文献 · Ophthalmology · 2022-02-21

该回顾性横断面数据库研究纳入英国3个临床中心6437例接受青光眼常规诊疗的患者,将OCT与红外反射视盘影像和7天内最近的视野配对,用EfficientNet B2训练两种单模态深度学习模型预测24-2视野模式中52个敏感点,并设计政策深度学习模型融合两种预测。政策模型相比单用红外视盘影像的逐点平均绝对误差改善0.485 dB,相比单用OCT改善0.060 dB,差异有统计学意义(P<0.0001)。

要点

  • 政策融合模型逐点平均绝对误差较单用红外视盘影像改善0.485 dB,较单用OCT改善0.060 dB(P<0.0001)。
  • 遮挡掩膜显示深度学习模型以数据驱动、特征不可知的方式学习到正确的结构-功能映射。
  • 多模态政策深度学习模型表现最佳,并提供可解释的融合置信度图。

核心结论

  • 多模态政策深度学习模型表现最佳,提供可解释的融合置信度图,并为探索青光眼结构-功能关系提供路径。

研究设计与样本

  • 回顾性横断面数据库研究,纳入英国3个临床中心6437例接受青光眼常规诊疗的患者。

主要发现

  • 使用5078对影像-视野配对作为留出测试集评估最终性能。
  • 政策融合模型的改善有统计学意义(P<0.0001)。
  • 遮挡掩膜显示深度学习模型以数据驱动、特征不可知的方式学习到正确的结构-功能映射。

关键数值与推荐

  • OCT与红外反射视盘影像和7天内最近的视野配对。
  • 使用EfficientNet B2训练2个单模态深度学习模型预测24-2视野模式中52个敏感点。
  • 设计并训练政策深度学习模型融合2个模型的预测。

临床怎么用

  • 原文未据此给出推荐。

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: To develop and validate a deep learning (DL) system for predicting each point on visual fields (VFs) from disc and OCT imaging and derive a structure-function mapping. DESIGN: Retrospective, cross-sectional database study. PARTICIPANTS: A total of 6437 patients undergoing routine care for glaucoma in 3 clinical sites in the United Kingdom. METHODS: OCT and infrared reflectance (IR) optic disc imaging were paired with the closest VF within 7 days. EfficientNet B2 was used to train 2 single-modality DL models to predict each of the 52 sensitivity points on the 24-2 VF pattern. A policy DL model was designed and trained to fuse the 2 model predictions. MAIN OUTCOME MEASURES: Pointwise mean absolute error (PMAE). RESULTS: A total of 5078 imaging scans to VF pairs were used as a held-out test set to measure the final performance. The improvement in PMAE with the policy model was 0.485 (0.438, 0.533) decibels (dB) compared with the IR image of the disc alone and 0.060 (0.047, 0.073) dB with to the OCT alone. The improvement with the policy fusion model was statistically significant (P < 0.0001). Occlusion masking shows that the DL models learned the correct structure-function mapping in a data-driven, feature agnostic fashion. CONCLUSIONS: The multimodal, policy DL model performed the best; it provided explainable maps of its confidence in fusing data from single modalities and provides a pathway for probing the structure-function relationship in glaucoma.

来源:Ophthalmology,查看原文。版权归原作者所有。

引用

  1. Kihara Y, Montesano G, Chen A, et al. Policy-Driven, Multimodal Deep Learning for Predicting Visual Fields from the Optic Disc and OCT Imaging. Ophthalmology. 2022. PMID: 35202616. doi:10.1016/j.ophtha.2022.02.017

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。