.png){kind=icon}
返回
Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification
.png){kind=icon}
OA
AI
DOI：10.1016/j.acra.2018.08.003.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Rationale and Objectives: We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet-a growing repository of well-known deep learning architectures first introduced here. Materials and Methods: Deep convolutional neural network (CNN) models were constructed and trained using a custom multilabel Dice metric loss function and a novel template-based data augmentation strategy. Training (including template generation and data augmentation) employed 205 proton MR images and 73 functional lung MRI. Evaluation was performed using data sets of size 63 and 40 images, respectively. Results: Accuracy for CNN-based proton lung MRI segmentation (in terms of Dice overlap) was left lung: 0.93 +/- 0.03, right lung: 0.94 +/- 0.02, and whole lung: 0.94 +/- 0.02. Although slightly less accurate than our previously reported joint label fusion approach (left lung: 0.95 +/- 0.02, right lung: 0.96 +/- 0.01, and whole lung: 0.96 +/- 0.01), processing time is <1 second per subject for the proposed approach versus similar to 30 minutes per subject using joint label fusion. Accuracy for quantifying ventilation defects was determined based on a consensus labeling where average accuracy (Dice multilabel overlap of ventilation defect regions plus normal region) was 0.94 for the CNN method; 0.92 for our previously reported method; and 0.90, 0.92, and 0.94 for expert readers. Conclusion: The proposed framework yields accurate automated quantification in near real time. CNNs drastically reduce processing time after offline model construction and demonstrate significant future potential for facilitating quantitative analysis of functional lung MRI.
Keyword:
Advanced Normalization Tools
ANTsRNet
Hyperpolarized gas imaging
Neural networks
Proton lung MRI
U-net
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.9
论文数:
8.8K
被引数:
1.0W
机构
引用论文
Hyperpolarized 3He Ventilation Defects Used to Predict Pulmonary Exacerbations in Mild to Moderate Chronic Obstructive Pulmonary Disease.png)
RADIOLOGY
RADIOLOGYIF15.2
PREAI
分享收藏Pulmonary hyperpolarized noble gas MRI: Recent advances and perspectives in clinical application肺超极化惰性气体MRI的临床应用进展与展望
PREAI
分享收藏Adaptive Non-Local Means Denoising of MR Images With Spatially Varying Noise Levels空间变化噪声水平的MR图像自适应非局部均值去噪OAAI
OAAI分享收藏
查看更多内容