Harnessing Coded Ptychography to Deliver AI-powered Evaluation of Unstained Lung Biopsies at the Point-Of-Care

母公司I期SBIR赠款旨在分析肺FNA的定量相位成像 使用在不同波长的光下捕获的编码重叠关联显微术 （具体目标#1），并证明Al可以正确检测未染色相的细胞 图像（具体目标#2）。让受资助者阿里安娜·普赖尔直接支持 具体目标#2预计将使我们能够为AI寻求更多样化的解决方案空间 模型开发，以检测未染色的QPI成像上的细胞，从而产生更多的 强有力的解决方案，扩大母公司赠款的成果和影响。普莱尔女士 在肺部细胞学的AI模型开发方面的经验，以及她的教育背景 生物医学工程专业的学生使她成为该项目的理想候选人。另夕h 技术经验和指导，直接的临床医生互动和创业 在创业公司工作获得的经验直接支持她的成长和未来 职业目标。

The parent Phase I SBIR grant aims to analyze quantitative phase imaging of lung FNAs using coded ptychography microscopy captured at different wavelengths of light (Specific Aim #1), and demonstrate that Al can correctly detect cells on unstained phase images (Specific Aim #2). Engaging the supplementee, Arianna Pryor, to directly support specific aim #2 is expected to allow us to pursue a more diverse solution space for Al model development to detect cells on the unstained QPI imaging, resulting in a more robust solution and amplifying the results and impact of the parent grant. Ms. Pryer's experience in Al model development for lung cytology, in conjunction with her education in biomedical engineering makes her an ideal candidate for the project. Additionally, the technical experience and mentoring, direct clinician interactions and entrepreneurial experience gained through working in a startup directly supports her growth and future career goals.