• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Graefe's archive for clinical and experimental ophthalmology: Albrecht von Graefes Archiv fur klinische und experimentelle Opthalmologie >Deep learning-based detection and classification of geographic atrophy using a deep convolutional neural network classifier
【24h】

Deep learning-based detection and classification of geographic atrophy using a deep convolutional neural network classifier

机译：深度卷积神经网络分类器基于深度学习的地理萎缩分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Purpose To automatically detect and classify geographic atrophy (GA) in fundus autofluorescence (FAF) images using a deep learning algorithm. Methods In this study, FAF images of patients with GA, a healthy comparable group and a comparable group with other retinal diseases (ORDs) were used to train a multi-layer deep convolutional neural network (DCNN) (1) to detect GA and (2) to differentiate in GA between a diffuse-trickling pattern (dt-GA) and other GA FAF patterns (ndt-GA) in FAF images. 1. For the automated detection of GA in FAF images, two classifiers were built (GA vs. healthy/GA vs. ORD). The DCNN was trained and validated with 400 FAF images in each case (GA 200, healthy 200, or ORD 200). For the subsequent testing, the built classifiers were then tested with 60 untrained FAF images in each case (AMD 30, healthy 30, or ORD 30). Hereby, both classifiers automatically determined a GA probability score and a normal FAF probability score or an ORD probability score. 2. To automatically differentiate between dt-GA and ndt-GA, the DCNN was trained and validated with 200 FAF images (dt-GA 72; ndt-GA 138). Afterwards, the built classifier was tested with 20 untrained FAF images (dt-GA 10; ndt-GA 10) and a dt-GA probability score and an ndt-GA probability score was calculated. For both classifiers, the performance of the training and validation procedure after 500 training steps was measured by determining training accuracy, validation accuracy, and cross entropy. Results For the GA classifiers (GA vs. healthy/GA vs. ORD), the achieved training accuracy was 99/98%, the validation accuracy 96/91%, and the cross entropy 0.062/0.100. For the dt-GA classifier, the training accuracy was 99%, the validation accuracy 77%, and the cross entropy 0.166. The mean GA probability score was 0.981?±?0.048 (GA vs. healthy)/0.972?±?0.439 (GA vs. ORD) in the GA image group and 0.01?±?0.016 (healthy)/0.061?±?0.072 (ORD) in the comparison groups ( p ?
机译：目的使用深度学习算法自动检测和分类眼底自发荧光（FAF）图像的地理萎缩（GA）。本研究中的方法，使用Ga，健康的可比较组和与其他视网膜疾病（ords）的可比较群体的FA法图像用于培训多层深卷积神经网络（DCNN）（1）检测GA和（ 2）在FAF图像中的漫射滴定模式（DT-GA）和其他GA FAF图案（NDT-GA）之间的Ga之间区分Ga。 1.对于在FAF图像中的GA的自动检测，构建了两个分类器（GA与健康/ GA与ORD）。在每种情况下，DCNN培训并验证了400个FAF图像（GA 200，健康200或ORD 200）。对于随后的测试，然后在每种情况下用60个未训练的FAF图像进行测试（AMD 30，健康30或ORD 30），测试内置的分类器。因此，两个分类器都自动确定了GA概率分数和正常的FAF概率分数或ord概率分数。 2.为了在DT-GA和NDT-GA之间自动区分，DCNN培训并用200 fAF图像（DT-GA 72; NDT-GA 138）验证。之后，用20个未训练的FAF图像（DT-GA 10; NDT-GA 10）和DT-GA概率分数和NDT-GA概率得分进行测试。对于两个分类器，通过确定培训准确性，验证精度和交叉熵来测量500次训练步骤后培训和验证程序的性能。 GA分类器的结果（GA与健康/ GA与ord），实现的培训准确度为99/98％，验证精度为96/91％，交叉熵0.062 / 0.100。对于DT-GA分类器，训练精度为99％，验证精度为77％，交叉熵0.166。平均GA概率得分为0.981？±±0.048（GA与健康）/0.972±??0.439（GA与ord）在GA Image组和0.01？±0.016（健康）/0.061个?±?0.072（在比较群中ord）（p？<0.001）。在DT-GA图像组中，平均dt-ga概率得分为0.807≤0.116，在NDT-GA图像组中为0.180？±0.100（p？<〜0.001）。结论是首次，本研究描述了使用深度学习的算法在FAF中自动检测和分类GA。因此，所创建的分类器显示出优异的结果。通过进一步的发展，该模型可以是预测GA的个人进展风险的工具，并提供未来治疗方法的相关信息。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号