STTR Phase I: An AI-Enhanced Angiographic System to Guide Endovascular Treatment of Intracranial Aneurysms

这个小企业技术转移（STTR）第一阶段项目的更广泛影响属于将人工智能（AI）方法扩展到医疗保健应用的更大范围。该应用主要集中在图像引导下的颅内动脉瘤（IA）的血管内手术，这可能导致蛛网膜下腔出血，这是最具破坏性的出血性中风类型。目前治疗动脉瘤的趋势表明，与开颅手术相比，血管内入路手术并发症减少，已成为主流手术方式。尽管在器械和手术器械方面取得了巨大的技术进步，但在第一次手术干预后，多达30%的这些病变并未完全愈合，使患者面临因多次手术而导致并发症的额外风险。该项目开发的人工智能自主解决方案将是首批应用程序之一，它可以在每个手术步骤后为六个月的动脉瘤愈合提供术中预测，从而允许手术调整，将破裂和再治疗的风险从30%降低到估计的5%，并节省65,000美元的再治疗费用（在美国每年约为19.5亿美元）。这项小型企业技术转移（STTR）第一阶段项目旨在开发一种全面自主的人工智能方法，为6个月的IA完全愈合提供术中预后。在目前的临床实践中，神经介入医生不能保证装置放置后颅内动脉瘤立即成功愈合。接受治疗的患者必须等待至少3-6个月，才能通过医学影像学重新评估其动脉瘤，并由临床医生决定是否需要重新治疗。在这一关键时期，患者仍有破裂的危险。此外，再治疗对患者的风险较高，也给医院和保险公司带来了经济负担。所提出的算法将与手术设备完全集成，并将允许动态血管造影分析，以获得与动脉瘤囊内血流性质相关的基于物理的参数。这些参数与机器学习算法相结合，提供关于治疗是否足以完全愈合的预测。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Technology Transfer (STTR) Phase I project falls within the larger scope of expanding artificial intelligence (AI) methods into health care applications. The application is focused on image guided endovascular surgical procedures for intracranial aneurysms (IA), which may cause subarachnoid hemorrhage, the most devastating type of hemorrhagic stroke. The current trends in treatment of aneurysms show that endovascular approach has become the mainstay procedure due to reduced surgical complications when compared with open skull surgery. Despite tremendous technological advances in devices and surgical instrumentation, as many as 30% of these lesions are not completely healed after the first surgical intervention, exposing patients to additional risks for complications due to multiple surgical procedures. The AI autonomous solution developed in this project will be the one of the first applications that provides intraoperative prognosis for six-month healing of an aneurysm after each surgical step to allow surgical adjustments, reducing the risk for ruptures and re-treatments from 30% to an estimated 5% and creating savings for the $65,000 in retreatments (roughly $1.95 B annually in the U.S.).This Small Business Technology Transfer (STTR) Phase I project will aim to develop a comprehensive and autonomous AI method that will provide intraoperative prognosis of complete healing for an IA at six months. In current clinical practice, neuro-interventionalists cannot guarantee successful healing of intracranial aneurysms immediately post-device placement. Treated patients have to wait a minimum of 3-6 months before their aneurysm is reassessed on medical imaging and the clinician decides if re-treatment is needed. During this critical time, patients are still at risk of rupture. In addition, re-treatments have higher risk to the patient as well as bear a financial burden on hospitals and insurance companies. The proposed algorithms will be fully integrated with surgical equipment and will allow dynamic angiographic analysis to derive physics-based parameters related to the nature of blood flow inside the aneurysm sac. These parameters are combined with a machine learning algorithm to provide a prediction as to whether the treatment is sufficient for a full healing.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.