CRII: SCH: Multi-modal Soft Tissue Characterization for Non-invasive Breast Imaging

该奖项的全部或部分资金来自《2021年美国救援计划法案》(公法117-2)。乳腺癌是全世界女性中最常见的癌症类型，早期发现是改善治疗后预后的最重要因素之一，这对幸存者的生活质量有很大影响。该项目将利用超声和电阻抗断层扫描的优化框架，发展对软组织行为的基本了解，为乳腺癌筛查的潜在用途提供一种可访问和可靠的工具。人类乳房中胶原蛋白的一个明显特征的规范将为新的乳腺癌生物标记物提供线索。该项目的成功完成将导致先进的乳腺癌筛查技术相关技术的改进，该技术采用多模式表征，如可穿戴传感器、医学成像中的人工智能和护理点诊断系统。研究团队将实施一个优化框架，可以学习软组织的物理响应，以便使用结合超声波和电阻抗断层扫描的集成成像技术非侵入性地可视化人类乳房横断面。第一个具体的目标是建立优化算法和多模式参数，它们为主动响应的软组织提供了一条分界线，以最小的伪影来对抗机电刺激。合成的图像将显示软组织在不同电场模式下对超声波刺激的反应，以及软组织中的温度分布信息。第二个具体目标是进行一项涉及健康受试者的重复测量研究，以确定随着时间的推移影响多模式表征结果的关键因素。这项观察性研究不仅将导致对算法参数的更好理解，以解决算法的患者特定适应所需的时间变异性，同时弥合人体乳腺组织体外和体内机电特性之间的差距。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Breast cancer is the most common type of cancer among women worldwide, and its early detection is one of the most important enabling factors for better post-treatment prognosis which significantly affects the quality of life for survivors. This project will develop a fundamental understanding of soft tissue behaviors using an optimization framework with ultrasound and electrical impedance tomography to provide an accessible and reliable tool for potential usages in breast cancer screening. The specification of a distinct feature of collagen in the human breast will provide a clue for a new breast cancer biomarker. The successful completion of the project will lead to improved technologies associated with an advanced breast cancer screening technique employing multi-modal characterization such as wearable sensors, artificial intelligence in medical imaging, and point-of-care diagnostic systems.The research team will implement an optimization framework that can learn from the physical responses of soft tissue in order to visualize the cross-sectional human breast non-invasively using an integrated imaging technique combining ultrasound and electrical impedance tomography. The first specific aim is to establish the optimization algorithms and multi-modal parameters that present a line of demarcation for actively responding soft tissues against the electro-mechanical stimuli with minimal artifacts. The resultant images will illustrate how the soft tissues respond against ultrasound stimulation under different patterns of electric fields with temperature distribution information across the soft tissues. The second specific aim is to conduct a repeated measure study involving healthy subjects so as to identify critical factors that affect the multi-modal characterization results over time. This observational study will lead to not only an improved understanding of the algorithm parameters required to account for temporal variability for patient-specific adaptation of the algorithm while bridging the gap between ex vivo and in vivo electromechanical characteristics of human breast tissues.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.