Detection and Classification of Myocardial Delayed Enhancement Patterns on MR Images with Deep Neural Networks: A Feasibility Study.
Detection and Classification of Myocardial Delayed Enhancement Patterns on MR Images with Deep Neural Networks: A Feasibility Study.
复制标题
使用深度神经网络对 MR 图像上的心肌延迟增强模式进行检测和分类：可行性研究。
DOI：
10.1148/ryai.2019180061
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
T. Ogawa
中科院分区：
文献类型：
--
作者：
Y. Ohta;H. Yunaga;Shin;T. Fukuda;T. Ogawa
目的
评估深度神经网络在与美国心脏病学会核心心血管训练声明中的医生培训期间所需的图像数量相似的图像上进行训练是否可以获得检测和分类心肌延迟增强（MDE）模式的能力。
材料与方法
作者回顾性评估了 1995 年的 MDE 图像，用于深度神经网络的训练和验证。图像来自 200 名连续接受心血管 MRI 的患者，并从机构数据库中获得。经验丰富的心脏 MR 图像阅读器将图像分类为显示以下 MDE 模式：无模式、心外膜增强、心内膜下增强、中壁增强、局灶性增强、透壁增强和非诊断性。使用四重交叉验证方法将数据分为训练数据集和验证数据集。使用训练数据集图像训练三个使用卷积神经网络 (CNN) 技术的未经训练的深度神经网络架构。使用验证数据计算训练后的 CNN 的检测和分类精度。
结果
1995 年 MDE 图像被人类读者分类如下：无模式，926；心外膜增强，91；心内膜下增强，458；中壁增强，118；焦点增强，141；透壁增强，190； 71. GoogLeNet、AlexNet 和 ResNet-152 CNN 的准确率分别为 79.5%（1995 年图像中的 1592 张）、78.9%（1995 年图像中的 1574 张）和 82.1%（1995 年图像中的 1637 张）。
结论
使用 CNN 进行深度学习，使用有限数量的训练数据（少于医生培训期间所需的数据），在 MR 图像上的 MDE 检测中实现了较高的诊断性能。© RSNA，2019 本文提供了补充材料。
Purpose
To evaluate whether deep neural networks trained on a similar number of images to that required during physician training in the American College of Cardiology Core Cardiovascular Training Statement can acquire the capability to detect and classify myocardial delayed enhancement (MDE) patterns.
Materials and Methods
The authors retrospectively evaluated 1995 MDE images for training and validation of a deep neural network. Images were from 200 consecutive patients who underwent cardiovascular MRI and were obtained from the institutional database. Experienced cardiac MR image readers classified the images as showing the following MDE patterns: no pattern, epicardial enhancement, subendocardial enhancement, midwall enhancement, focal enhancement, transmural enhancement, and nondiagnostic. Data were divided into training and validation datasets by using a fourfold cross-validation method. Three untrained deep neural network architectures using the convolutional neural network (CNN) technique were trained with the training dataset images. The detection and classification accuracies of the trained CNNs were calculated with validation data.
Results
The 1995 MDE images were classified by human readers as follows: no pattern, 926; epicardial enhancement, 91; subendocardial enhancement, 458; midwall enhancement, 118; focal enhancement, 141; transmural enhancement, 190; and nondiagnostic, 71. GoogLeNet, AlexNet, and ResNet-152 CNNs demonstrated accuracies of 79.5% (1592 of 1995 images), 78.9% (1574 of 1995 images), and 82.1% (1637 of 1995 images), respectively.
Conclusion
Deep learning with CNNs using a limited amount of training data, less than that required during physician training, achieved high diagnostic performance in the detection of MDE on MR images.© RSNA, 2019Supplemental material is available for this article.
影响因子：
19.7
作者：
Kundel, HL;Polansky, M
通讯作者：
Polansky, M