Deep Learning Based Model Observer by U-Net.
Deep Learning Based Model Observer by U-Net.
复制标题
U-Net 基于深度学习的模型观察器。
DOI：
10.1117/12.2549687
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Brankov,JovanG
中科院分区：
文献类型：
--
作者：
Lorente,Iris;Abbey,CraigK;Brankov,JovanG
模型观测器（MO）是一种算法，旨在通过为诊断任务提供人类准确度的测量来评估和优化新的医学成像重建方法的参数。与计算机辅助诊断系统相比，MO的设计并不是为了超越人类诊断，而只是为了找到一个缺陷，如果放射科医生将能够检测到它。这些算法可以节省和加快寻找最佳的重建参数，通过减少与专家放射科医生，这是昂贵的和长期的会话的数量。卷积神经网络（CNN或ConvNet）已成功用于计算机视觉领域的图像分类，分割和视频分析。在本文中，我们提出并测试了几个U-网配置MO的缺陷定位任务的合成图像与不同级别的相关噪声背景。初步结果表明，基于CNN的MO具有潜力，其准确性与人类的准确性相关。
Model Observers (MO) are algorithms designed to evaluate and optimize the parameters of new medical imaging reconstruction methodologies by providing a measure of human accuracy for a diagnostic task. In contrast with a computer-aided diagnosis system, MOs are not designed to outperform human diagnosis but only to find a defect if a radiologist would be able to detect it. These algorithms can economize and expedite the finding of optimal reconstruction parameters by reducing the number of sessions with expert radiologists, which are costly and prolonged. Convolutional Neural Networks (CNN or ConvNet) have been successfully used in the computer vision field for image classification, segmentation and video analytics. In this paper, we propose and test several U-Net configurations as MO for a defect localization task on synthetic images with different levels of correlated noisy backgrounds. Preliminary results show that the CNN based MO has potential and its accuracy correlates well with that of the human.