Kalayeh Mahdi M, Marin Thibault, Brankov Jovan G
Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA (phone: +1-313-567-8819; fax: +1-312-567-3225).
IEEE Trans Nucl Sci. 2013 Jun;60(3):1609-1618. doi: 10.1109/TNS.2013.2257183.
In this paper, we present two new numerical observers (NO) based on machine learning for image quality assessment. The proposed NOs aim to predict human observer performance in a cardiac perfusion-defect detection task for single-photon emission computed tomography (SPECT) images. Human observer (HumO) studies are now considered to be the gold standard for task-based evaluation of medical images. However such studies are impractical for use in early stages of development for imaging devices and algorithms, because they require extensive involvement of trained human observers who must evaluate a large number of images. To address this problem, numerical observers (also called model observers) have been developed as a surrogate for human observers. The channelized Hotelling observer (CHO), with or without internal noise model, is currently the most widely used NO of this kind. In our previous work we argued that development of a NO model to predict human observers' performance can be viewed as a machine learning (or system identification) problem. This consideration led us to develop a channelized support vector machine (CSVM) observer, a kernel-based regression model that greatly outperformed the popular and widely used CHO. This was especially evident when the numerical observers were evaluated in terms of generalization performance. To evaluate generalization we used a typical situation for the practical use of a numerical observer: after optimizing the NO (which for a CHO might consist of adjusting the internal noise model) based upon a broad set of reconstructed images, we tested it on a broad (but different) set of images obtained by a different reconstruction method. In this manuscript we aim to evaluate two new regression models that achieve accuracy higher than the CHO and comparable to our earlier CSVM method, while dramatically reducing model complexity and computation time. The new models are defined in a Bayesian machine-learning framework: a channelized relevance vector machine (CRVM) and a multi-kernel CRVM (MKCRVM).
在本文中，我们提出了两种基于机器学习的新型数值观察者（NO）用于图像质量评估。所提出的数值观察者旨在预测单光子发射计算机断层扫描（SPECT）图像心脏灌注缺损检测任务中的人类观察者表现。人类观察者（HumO）研究现在被认为是基于任务的医学图像评估的金标准。然而，此类研究在成像设备和算法的早期开发阶段并不实用，因为它们需要训练有素的人类观察者广泛参与，这些观察者必须评估大量图像。为了解决这个问题，数值观察者（也称为模型观察者）已被开发出来作为人类观察者的替代物。带或不带内部噪声模型的通道化霍特林观察者（CHO）是目前这类使用最广泛的数值观察者。在我们之前的工作中，我们认为开发一个预测人类观察者表现的数值观察者模型可以被视为一个机器学习（或系统识别）问题。这种考虑促使我们开发了一种通道化支持向量机（CSVM）观察者，这是一种基于核的回归模型，其性能大大优于流行且广泛使用的CHO。当根据泛化性能评估数值观察者时，这一点尤为明显。为了评估泛化能力，我们使用了数值观察者实际应用中的一种典型情况：在基于广泛的一组重建图像优化数值观察者（对于CHO可能包括调整内部噪声模型）之后，我们在通过不同重建方法获得的一组广泛（但不同）的图像上对其进行测试。在本手稿中，我们旨在评估两种新的回归模型，它们的准确性高于CHO且与我们早期的CSVM方法相当，同时显著降低模型复杂度和计算时间。新模型在贝叶斯机器学习框架中定义：通道化相关向量机（CRVM）和多核CRVM（MKCRVM）。
