Advanced Medical Image Reconstruction

背景

Background Medical imaging plays a major role in the diagnosis and treatment of cardiovascular disease. The process of generating a medical image consists of two parts; data acquisition and image reconstruction. Image reconstruction transforms the acquired raw data signals into images that can be interpreted by clinician to aid in the diagnosis of a disease or used to guide a procedure. The raw data is frequently corrupted by instrument imperfections and patient motion. It is also common for datasets to be incomplete since there is a limited amount of time, radiation dose, or other patient exposure available for data acquisition. Consequently, modern image reconstruction software is fairly complex. The source code for these complex image reconstruction algorithms is most often proprietary information retained by the medical device manufacturers and scientists working in the field of medical image reconstruction are forced to implement their own versions of existing algorithms that they then build on and improve. Because of this reimplementation and a lack of open standards, much of the published literature on medical image reconstruction is not reproducible. The overarching goal of this project is to develop novel image reconstruction algorithms and to do that in such a way that other scientists (and device manufacturers) can reproduce the presented results and use the methods in future work. The Laboratory of Imaging Technology, NHLBI is particularly focused on Magnetic Resonance Imaging (MRI) techniques, but the developed principles apply to other technqiques as well. Goals/Objectives The Laboratory of Imaging Technology developes and maintains two major software packages that support ongoing research projects. The first is the ISMRM Raw Data format (https://ismrmrd.github.io), which is an open raw data standard for MR experiments. It is a requirement for sharing algorithms and methods that there is common understanding of how to describe the raw data and this package provides the framework for this. We also aim to maintain data conversion tools from major device manufacturers proprietary formats to this vendor independent format. The second software package is the Gadgetron (https://gadgetron.github.io), which is an advance image reconstruction package that contains toolboxes and a streaming pipeline architecture for processing the raw data that is acquired by the imaging instrument. We aim to expand this software package and support the growing user base around the world. The are a number of technical innovations are we are currently pursuing: * Expansion of the ISMRMRD format to include waveforms and telemetry from other instruments. * Formal definition and implementation of an ISMRMRD communication protocol. * The use of cloud computing for MRI reconstruction. * MRI raw data compression. * Correct of measurment system imperfections. * Tight integration of the Gadgetron with specific vendor instruments. In addition to these infrastructure goals, we are developing and testing new image reconstruction techniques to solve specific clinical questions: * Real-time imaging sequence for interventional MRI. * Real-time measurements of blood flow. * Motion corrected, free-breathing techniques for measuring cardiac function and parametric maps. * Quantitative assessment of myocardial perfusion. Progress in fiscal year 2016 In the past year, we have made significant progress in our approach to cloud based MRI reconstruction. We have demonstrated in the past that cloud based image reconstruction using the Gadgetron can be used to achieve clinically practical image reconstruction times. More recently, we have demonstrated that such an approch can improve the clinical workflow when studying pediatric patients. As we aim to deploy such technology at collaboration sites across the world, we made improvements to the infrastructure such that it can be deployed in several major cloud providers (Amazon AWS and Miscrosoft Azure). Our new architecture which has the capability to scale automatically to accomodate demand is know as the Gadgetron Lighthouse. We have also made significant progress in the area of system imperfection correction. Specifically, several steps needed for correction of gradient imperfections have been implemented and we are starting to test the utility of these technqiues for a wide range of real-time imaging applications including spiral and radial trajectories. In the area of myocardial perfusion, we have made significant progress towards a fully automated, inline package for quantitative myocardial perfusion. This is an expansive and ongoing project that we aim to continue in the coming year.