Development of a low-cost hardware accelerator for 3D image registration

点击翻译按钮获取中文摘要

Our overall goal is to develop a novel computing solution for automatic and accurate registration (spatial alignment) of 3-dimensional (3D) medical images of any modality and any anatomy (rigid or deformable) in 1 minute or less. Such capability currently does not exist. Existing image registration solutions have limited accuracy and/or limited applicability, preventing wide and routine clinical use. Building on significant prior academic research, we demonstrated the feasibility of creating the proposed technology in Phase I of this project. We now propose to create a fully functional turnkey prototype-a compact, relatively low-cost (manufacturing cost: ~$20,000) PC board-of hardware- accelerated image registration, with commercialization as the ultimate goal. Image registration is a fundamental need in modern medicine-a need that remains unmet. It is the necessary first step before images with complementary information can be fused or images taken at different times can be subtracted to quantify anatomic/physiologic changes. It is also essential when creating a population- based atlas from images of many subjects. Image registration has numerous other applications, including the registration of pre- and intra-operative images in a host of emerging minimally invasive image-guided interventions, especially those to treat cancer. Our 4 specific aims for Phase II are to: (1) create a fully integrated prototype of 1-min image registration; (2) develop software for convenient third-party integration and technology demonstration; (3) perform PACS (picture archival and communication system) integration and analyze enterprise-wide utilization; and (4) develop high- impact model applications. These aims will continue the progress made in Phase I and help create a clinically tested and viable multipurpose image registration computing technology. The proposed Phase II work will also put us in a strong position to secure private capital and licensing agreements and pursue commercialization. Our proposed low-cost, ultrafast, easy-to-use, and accurate computing solution promises to unlock the full potential of medical image registration in virtually all clinical disciplines, including radiology, oncology, neurology, and cardiology.