Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data
Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data
复制标题
DOI：
10.1016/j.media.2014.04.007
复制
发表时间：
2014-12-01
影响因子：
10.9
通讯作者：
Ionasec, Razvan
中科院分区：
文献类型：
--
作者：
Heimann, Tobias;Mountney, Peter;Ionasec, Razvan
经食管超声（TEE）和x线透视图像数据的融合在结构性心脏病的微创治疗中引起了越来越多的兴趣。为了计算两种成像系统之间所需的转换，我们采用基于判别学习（DL）的方法来定位x射线图像中的TEE换能器。深度学习方法的成功应用强烈依赖于可用的训练数据，这带来了三个挑战：(1)换能器可以以六个自由度移动，这意味着它需要大量的图像来表示其外观，(2)手动标记耗时，(3)手动标记具有固有的错误。本文提出从换能器的单个体积图像中自动生成所需的训练数据。为了使该系统适应真实的x射线数据，我们使用未标记的透视图像来估计特征空间密度的差异，并通过实例加权来纠正协变量移位。针对DL管道的不同阶段，对加权、概率分类和Kullback-Leibler重要性估计（KLIEP）两种方法进行了评价。对1900多张图像的分析表明，我们的方法将测试集交叉验证的检测失败率从7.3%降低到零，并将定位误差从1.5 mm提高到0.8 mm。由于训练数据的自动生成，所提出的系统具有高度的灵活性，可以以最小的努力适应任何医疗设备。(C) 2014 Elsevier B.V.版权所有
The fusion of image data from trans-esophageal echography (TEE) and X-ray fluoroscopy is attracting increasing interest in minimally-invasive treatment of structural heart disease. In order to calculate the needed transformation between both imaging systems, we employ a discriminative learning (DL) based approach to localize the TEE transducer in X-ray images. The successful application of DL methods is strongly dependent on the available training data, which entails three challenges: (1) the transducer can move with six degrees of freedom meaning it requires a large number of images to represent its appearance, (2) manual labeling is time consuming, and (3) manual labeling has inherent errors.This paper proposes to generate the required training data automatically from a single volumetric image of the transducer. In order to adapt this system to real X-ray data, we use unlabeled fluoroscopy images to estimate differences in feature space density and correct covariate shift by instance weighting. Two approaches for instance weighting, probabilistic classification and Kullback-Leibler importance estimation (KLIEP), are evaluated for different stages of the proposed DL pipeline. An analysis on more than 1900 images reveals that our approach reduces detection failures from 7.3% in cross validation on the test set to zero and improves the localization error from 1.5 to 0.8 mm. Due to the automatic generation of training data, the proposed system is highly flexible and can be adapted to any medical device with minimal efforts. (C) 2014 Elsevier B.V. All rights reserved.