Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
复制标题
DOI：
10.1007/s11548-019-01939-9
复制
发表时间：
2019-06-01
影响因子：
3
通讯作者：
Maier-Hein, Lena
中科院分区：
文献类型：
--
作者：
Adler, Tim J.;Ardizzone, Lynton;Maier-Hein, Lena
目的光学成像作为手术室先进传感的关键技术正在发展。最近的研究表明，机器学习算法可用于解决将逐像素多光谱反射率测量值转换为基础组织参数（如氧合）的逆问题。然而，与这样的算法结合使用的特定硬件的评估，并没有适当地解决的可能性，该问题可能是不适定的。MethodsWe提出了一种新的方法来评估的光学成像方式，这是敏感的不同类型的不确定性，可能会发生推断组织参数时。基于可逆神经网络的概念，我们的框架超越了点估计，并将每个多光谱测量映射到一个完整的后验概率分布，该分布能够通过多种模式表示解决方案中的模糊性。硬件设置的性能指标，然后可以计算从posterior.ResultsApplication的相机选择生理参数估计的特定用例的评估框架，产生以下见解：（1）从多光谱图像的组织氧合估计是一个适定性的问题，而（2）血液体积分数可能无法恢复而不模糊。(3)在一般情况下，模糊性可能会减少通过增加的光谱带的数量在camera.ConclusionOur方法可以帮助优化光学相机的设计，在特定的应用程序的方式。
PurposeOptical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed.MethodsWe present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors.ResultsApplication of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera.ConclusionOur method could help to optimize optical camera design in an application-specific manner.