文献速递眼底病与葡萄膜炎

量化年龄相关性黄斑变性中的地图样萎缩:12种深度学习模型的比较分析

Quantifying Geographic Atrophy in Age-Related Macular Degeneration: A Comparative Analysis Across 12 Deep Learning Models.
PubMed 文献 · Invest Ophthalmol Vis Sci · 2024-01-01

本研究比较了12种不同AI架构组合在眼底自发荧光(FAF)图像上分割地图样萎缩(GA)的表现。训练集为AREDS2研究的601张FAF图像,验证集为葛兰素史克研究的156张FAF图像。结果显示,采用mViT编码器与UNet或FPN解码器的模型表现最佳,PSPNet框架表现最差;AI架构选择影响GA分割性能。

要点

  • 采用mViT编码器与UNet或FPN解码器的模型在GA分割中表现最佳。
  • PSPNet框架在12种架构组合中表现最差。
  • AI架构的选择需根据项目具体目标进行定制。

核心结论

  • AI架构的选择会影响GA分割性能。
  • 与基于卷积神经网络和PSPNet的模型相比,采用FPN和UNet架构的视觉变换器在此任务中表现出更强的适用性。
  • 选择AI架构必须针对项目的具体目标,开发者应考虑哪种架构最适合其项目。

研究设计与样本

  • 探索了12种不同的AI架构组合,每种组合包含不同的编码器和解码器。
  • 架构包括三种解码器:FPN、UNet和PSPNet,作为分割任务的基础框架。
  • 编码器包括EfficientNet、ResNet、VGG和Mix Vision Transformer(mViT),用于提取最优潜在特征。
  • 训练数据集包括来自AREDS2研究的601张FAF图像,验证集包括来自葛兰素史克研究的156张FAF图像。

主要发现

  • 评估者测量面积与AI预测面积之间的平均绝对差异范围为-0.08 mm2(95% CI = -1.35, 1.19)至0.73 mm2(95% CI = -5.75, 4.29)。
  • Dice系数(DC)介于0.884至0.993之间。
  • 表现最佳的模型是采用mViT的UNet和FPN框架,表现最差的模型是PSPNet框架。

关键数值与推荐

  • 性能通过比较人类与AI预测的GA面积以及Dice系数(DC)来衡量。

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: AI algorithms have shown impressive performance in segmenting geographic atrophy (GA) from fundus autofluorescence (FAF) images. However, selection of artificial intelligence (AI) architecture is an important variable in model development. Here, we explore 12 distinct AI architecture combinations to determine the most effective approach for GA segmentation. METHODS: We investigated various AI architectures, each with distinct combinations of encoders and decoders. The architectures included three decoders-FPN (Feature Pyramid Network), UNet, and PSPNet (Pyramid Scene Parsing Network)-and serve as the foundation framework for segmentation task. Encoders including EfficientNet, ResNet (Residual Networks), VGG (Visual Geometry Group) and Mix Vision Transformer (mViT) have a role in extracting optimum latent features for accurate GA segmentation. Performance was measured through comparison of GA areas between human and AI predictions and Dice Coefficient (DC). RESULTS: The training dataset included 601 FAF images from AREDS2 study and validation included 156 FAF images from the GlaxoSmithKline study. The mean absolute difference between grader measured and AI predicted areas ranged from -0.08 (95% CI = -1.35, 1.19) to 0.73 mm2 (95% CI = -5.75,4.29) and DC between 0.884-0.993. The best-performing models were UNet and FPN frameworks with mViT, and the least-performing models were PSPNet framework. CONCLUSIONS: The choice of AI architecture impacts GA segmentation performance. Vision transformers with FPN and UNet architectures demonstrate stronger suitability for this task compared to Convolutional Neural Network- and PSPNet-based models. Selecting an AI architecture must be tailored to the specific goals of the project, and developers should consider which architecture is ideal for their project.

来源:Invest Ophthalmol Vis Sci,查看原文。版权归原作者所有。

引用

  1. Safai A, Froines C, Slater R, et al. Quantifying Geographic Atrophy in Age-Related Macular Degeneration: A Comparative Analysis Across 12 Deep Learning Models. Invest Ophthalmol Vis Sci. 2024. PMID: 39046755. doi:10.1167/iovs.65.8.42

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。