Abstract
The ideal observer (IO) sets an upper performance limit among all observers and has been advocated for assessing and optimizing imaging systems. For general joint detection and estimation (detection-estimation) tasks, estimation ROC (EROC) analysis has been established for evaluating the performance of observers. However, in general, it is difficult to accurately approximate the IO that maximizes the area under the EROC curve. In this study, a hybrid method that employs machine learning is proposed to accomplish this. Specifically, a hybrid approach is developed that combines a multi-task convolutional neural network and a Markov-Chain Monte Carlo (MCMC) method in order to approximate the IO for detection-estimation tasks. Unlike traditional MCMC methods, the hybrid method is not limited to use of specific utility functions. In addition, a purely supervised learning-based sub-ideal observer is proposed. Computer-simulation studies are conducted to validate the proposed method, which include signal-known-statistically/background-known-exactly and signal-known-statistically/background-known-statistically tasks. The EROC curves produced by the proposed method are compared to those produced by the MCMC approach or analytical computation when feasible. The proposed method provides a new approach for approximating the IO and may advance the application of EROC analysis for optimizing imaging systems.
Highlights
Objective, or task-based, measures of image quality (IQ)are advocated for use in the assessment and optimization of medical imaging systems [1]–[5]
Unlike traditional Markov-Chain Monte Carlo (MCMC) methods for approximating the ideal observer (IO), the hybrid method is not limited to use of specific utility functions
The area under the EROC curve (AEROC) values were 0.565±0.010, 0.565±0.010, and 0.570 ± 0.010 corresponding to the approximated IO, the sub-ideal numerical observers (NOs), and the analytical computation, respectively
Summary
Unlike traditional physical measures of IQ, task-based measures of IQ quantify the ability of an observer to perform a specific task such as detection or estimation of a signal To compute such measures of IQ when developing and refining new imaging technologies, numerical observers (NOs) have been widely employed [2], [4]. Unlike the of case binary detection tasks for which MCMC methods or supervised learning methods can be employed to establish NOs, [9], [17], there is a lack of available NOs for approximating the IO for detectionestimation tasks. The proposed methods provide a new capability for approximating the IO for detection-estimation tasks and may advance the application of EROC analysis for optimizing imaging systems.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
