Motion-Resistant Background Subtraction Angiography with Deep Learning: Real-Time, Edge Hardware Implementation and Product Development

具有深度学习的抗运动背景减影血管造影：实时、边缘硬件实施和产品开发

• 批准号: 10602275
• 负责人: Sameer A Ansari
• 金额: $ 25.69万
• 依托单位: CLEARVOYA LLC
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10602275
• 关键词: 3-Dimensional; Address; Adopted; Adoption; Algorithms; Angiography; Applications Grants; Architecture; Arteries; Artificial Intelligence platform; Awareness; Bite; Blinded; Blood Vessels; Bone Density; Bone Tissue; Breathing; Buffers; Cardiac; Catheters; Characteristics; Clinical; Coagulation Process; Complex; Computer software; Data; Data Set; Devices; Digital Subtraction Angiography; Disease; Dissemination and Implementation; Distress; Environment; Equipment; Evaluation; Excision; Feedback; Foundations; Funding; Future; Goals; Hospitals; Image; Imaging Techniques; Injections; Intention; Intervention; Legal patent; Masks; Memory; Modeling; Morphologic artifacts; Motion; Myocardial Infarction; Neurology; Pathology; Patients; Performance; Physicians; Procedures; Protocols documentation; Pythons; Radiology Specialty; Resistance; Risk; Roentgen Rays; Safety; Series; Side; Site; Speed; Stents; Stream; Stroke; System; Techniques; Technology; TensorFlow; Time; Training; Validation; Vascular Diseases; Vendor; Vision; Visualization; Work; X-Ray Medical Imaging; acute stroke; awake; blood vessel visualization; bone; clinical practice; deep learning; deep learning algorithm; density; diagnosis standard; heart motion; image guided; improved; innovation; minimally invasive; network architecture; neural network; neurosurgery; novel; patient population; patient safety; product development; prospective; prototype; respiratory; serial imaging; soft tissue; stroke intervention; temporal measurement; time use; underserved minority

Catheter Digital Subtraction Angiography (DSA) is an imaging technique that was developed in the 1980s to allow physicians to visualize blood vessels. Today, this technology is utilized for minimally-invasive interventions that treat numerous devastating pathologies, including stroke and myocardial infarction, diseases that disproportionally impact underserved minority patient populations. Catheter angiography is performed by inserting a small catheter into an artery, injecting iodinated contrast through the catheter, and recording a series of X-Ray images as the contrast traverses the patient’s blood vessels. However, superimposed X-Ray densities from bones and soft tissues obscure the imaging details of the blood vessels. In ideal conditions, DSA will provide an image of the vessels alone, unobscured by superimposed bone and soft tissue. Indeed, during angiography of cooperative awake patients, who are instructed to hold their breath to reduce motion, DSA can produce excellent images. However, DSA images are markedly degraded by all voluntary, respiratory, or cardiac motion that occurs during the exam. During routine clinical practice, it is common to discard and repeat angiographic acquisitions due to excessive motion. In situations where patients are unable to remain still, which may be due to difficulty breathing or the distress of an acute stroke, the poor quality of motion-degraded DSA imaging increases the risk of complex procedures such as stroke clot removal and cardiac stenting. We have developed a deep learning algorithm that can perform the task of DSA even in the setting of substantial motion. We utilize a cutting edge Vision-Transformer-based network architecture, which is optimized to use the spatial and temporal information in the images to identify the blood vessels and separate them from the other X-ray densities such as bone and soft tissue. Furthermore, we have developed a novel data-augmentation mechanism to train this data-hungry neural network to outperform DSA and alternative U-Net-based architectures during patient motion. In this grant application, we propose to implement our innovative algorithm on a product-oriented, low-latency, edge hardware device for real-time application in minimally-invasive procedures. Second, we will validate the image quality produced by of this edge hardware product. In the validation step, physicians in Neurology, Radiology, and Neurosurgery will view the results of our Deep Learning Angiography technology side-by-side with DSA on real patient data after the angiogram is complete. At the end of our funding period, we will deliver a validated, low-latency, edge hardware implementation of our Deep Learning Angiography algorithm for real-time use during X-ray guided interventions, which will be integrated into angiography machines in future work.

导管数字减影血管造影术（DSA）是一种成像技术，在20世纪80年代开发， 使医生能够看到血管。今天，这项技术被用于微创干预， 治疗许多毁灭性的病理，包括中风和心肌梗死，这些疾病 影响服务不足的少数患者群体。 导管血管造影术是将一根小导管插入动脉， 通过导管，并记录一系列X射线图像，因为造影剂穿过病人的血管。 然而，来自骨骼和软组织的叠加X射线密度模糊了血管的成像细节。在 在理想的情况下，DSA将仅提供血管图像，不被叠加的骨和软组织遮挡。 事实上，在对清醒的合作患者进行血管造影时，他们被指示屏住呼吸以减少运动， DSA可以产生良好的图像。然而，DSA图像明显退化的所有自愿，呼吸，或心脏 在常规临床实践中，通常会丢弃并重复血管造影， 由于过度运动导致的收购。在患者无法保持静止的情况下，这可能是由于 呼吸困难或急性中风的痛苦，运动退化DSA成像的质量差增加了 复杂手术的风险，如中风凝块清除和心脏支架植入术。 我们已经开发了一种深度学习算法，即使在大量的环境中也可以执行DSA任务。 议案我们利用先进的基于Vision-Transformer的网络架构，该架构经过优化，可以使用空间 以及图像中的时间信息来识别血管并将它们与其他X射线密度分开 例如骨和软组织。此外，我们还开发了一种新的数据增强机制来训练这种方法。 数据饥渴型神经网络在患者运动期间的性能优于DSA和其他基于U-Net的架构。 在这项拨款申请中，我们建议在一个面向产品的，低延迟， 边缘硬件设备，用于微创手术中的实时应用。其次，我们将验证图像 这款五金产品的质量。在验证步骤中，神经科、放射科和 神经外科将在真实的患者身上同时查看我们的深度学习血管造影技术和DSA的结果 血管造影完成后的数据。在我们的融资期结束时，我们将提供一个经过验证的、低延迟的边缘 我们的深度学习血管造影算法的硬件实现，用于在X射线引导下实时使用 在未来的工作中，这些干预措施将被集成到血管造影机中。