SBIR Phase II: An AI-Enhanced Angiographic System to Guide Endovascular Treatment of Intracranial Aneurysms

这项小企业创新研究（SBIR）二期项目的更广泛影响是改善接受神经血管内介入治疗颅内动脉瘤（IAs）的患者的手术效果。IAs影响了6%的人口，尽管管理有所改善，但IA破裂导致致命性出血性中风，占脑血管死亡的25%左右。大多数破裂的内出血患者（约65%）死于初始出血或直接并发症。在幸存者中，约50%的人残疾，日常活动依赖他人。当IAs出现症状且药物治疗或生活方式改变无效时，治疗可涉及神经血管内干预。虽然这些手术方法提供了可靠和快速的病变通道，并发症比开颅手术少，但它们不能实现完全的IA愈合，多达30%的病例需要反复干预。该项目中开发的人工智能技术将通过分析血管造影单元获得的图像来实时评估手术进展。该解决方案将提供在患者离开手术室之前无法实现IAs愈合的可能性。这个小企业创新研究（SBIR）二期项目将支持世界上第一个人工智能平台的开发，该平台可以为图像引导神经干预治疗颅内动脉瘤提供实时知情决策支持。该技术使用在图像引导血管内手术和机器学习方法中从常规获得的血管造影中提取的成像生物标志物，以解释患者病理、神经介入治疗方法和成像设备特征的巨大异质性。该平台包括多个创新方面：1)一种全自动方法来识别IA的位置和范围，(2)瞬时提取成像生物标志物，(3)手术后1年的预后，在不到一秒的时间内允许神经介入医生重新调整血管内治疗，以及(4)与血管造影系统完全集成，而不考虑制造商。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 Innovation Research (SBIR) Phase II project is improving the surgical outcome for patients undergoing neuro-endovascular interventions for the treatment of intracranial aneurysms (IAs). IAs affect 6% of the population and IA rupture results in lethal hemorrhagic strokes, which account for ~25% of cerebrovascular deaths despite improvements in management. Most ruptured IA patients (~65%) die due to the initial bleed or its immediate complications. Of the survivors, ~50% are left disabled and dependent on others for daily activities. When IAs become symptomatic and medical therapy or lifestyle changes are ineffective, treatment could involve neuro-endovascular interventions. Although these surgical approaches provide reliable and fast access to the lesion with fewer complications than open skull surgery, they do not achieve complete IA healing, with as many as 30% of the cases requiring repeated interventions. The artificial intelligence technology developed in this project will allow real-time assessment of the surgery progress by analyzing images acquired through the angiographic unit. The solution will provide the odds of failure to achieve healing of the IAs before the patient leaves the surgical suite.This Small Business Innovation Research (SBIR) Phase II project will support development of the world’s first artificial intelligence platform that enables real-time informed decision support for image-guided neuro interventions to treat intracranial aneurysms. The technology uses imaging biomarkers extracted from routinely acquired angiograms during image-guided endovascular procedures and machine learning methods to account for large heterogeneity in patient pathology, neuro-interventionalist approach, and imaging equipment characteristics. The platform includes multiple innovative aspects: 1) a fully automated method to identify the location and extent of the IA, (2) instantaneous extraction of the imaging biomarkers, (3) prognosis of the surgical outcome at one-year post-procedure in a fraction of a second to allow neuro-interventionalist to readjust the endovascular therapy, and (4) full integration with the angiographic systems regardless of the manufacturer.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.