Visual Analytics and Imaging Laboratory (VAI Lab)
Computer Science Department, Stony Brook University, NY
Abstract: Motivated by growing concerns with regards to the x-ray dose delivered to the patient, low-dose computed tomography (CT) has gained substantial interest in recent years. However, achieving high-quality CT reconstructions from the limited projection data collected at reduced x-ray radiation is challenging, and iterative algorithms have been shown to perform much better than conventional analytical schemes in these cases. A problem with iterative methods in general is that they require users to set many parameters, and if set incorrectly high reconstruction time and/or lowimage quality are likely consequences. Since theinteractions among parameters can be complex and thus effective settings can be difficult to identify for a given scanning scenario, these choices are often left to a highly-experienced human expert. To help alleviate this problem, we devise a computer-based assistant for this purpose, called dose, quality and speed (DQS)-advisor. It allows users to balance the three most importantCTmetrics -- DQS -- by ways of an intuitive visual interface. Using a known gold-standard, the system uses the ant-colony optimization algorithm to generate the most effective parameter settings for a comprehensive set of DQS configurations. A visual interface then presents the numerical outcome of this optimization, while a matrix display allows users to compare the corresponding images. The interface allows users to intuitively trade-off GPU-enabled reconstruction speed with quality and dose, while the system picks the associated parameter settings automatically. Further, once the knowledge has been generated, it can be used to correctly set the parameters for any new CT scan taken at similar scenarios.
Teaser: The visual interface showing the quality vs. dose plot. The numbers inserted into the plot refer to the image matrix (the Light Box) on the right. Image 1 is the image of the highest quality but requires a high dose. Images 3 and 4 require much less dose but have streak artifacts or blurred features, respectively. Image 2 seems to be a good compromise – lower dose than image 1 but still offering good quality. It could serve as a starting point for further exploration of the plot, where the user would mouse-click at desirable plot locations and insert the corresponding images into the Light Box.
Paper: Z. Zheng, E. Papenhausen, K. Mueller, "DQS Advisor: A Visual Interface and Knowledge-Based System to Balance Dose, Quality, and Reconstruction Speed in Iterative CT Reconstruction with Application to NLM-Regularization," Physics in Medicine and Biology, 58(21):7857-73, 2013. pdf