EAGER: Development of 3D Second Harmonic Generation Tomography and Deep Learning Algorithms for Classification of Human Ovarian Cancer

该建议将解决区分正常组织和癌前组织变化的问题，这对成功治疗卵巢癌至关重要。卵巢癌的预后非常差，除非在早期发现，这是非常困难的。目前的临床成像技术缺乏足够的分辨率、特异性和敏感性来有效区分正常和病变的癌组织。迫切需要对疾病的病因和进展有新的认识。为此，PI将开发新的二次谐波（SHG）成像工具。他们将把目前的SHG显微镜扩展到断层扫描，以更好地表征3D胶原结构。他们将a)进行SHG激发层析成像；B)开发新的重构算法；c)将三维数据纳入相应的分类方案，并探索使用深度学习算法来细化分类分析。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。

This proposal will address the problem of distinguishing between normal tissue and precancer tissue changes, critical for successful treatment of ovarian cancer. Ovarian cancer has a very poor prognosis unless detected at the earliest stage, which is extremely difficult. Current clinical imaging techniques lack sufficient resolution, specificity, and sensitivity for effective differentiation of normal and diseased cancerous tissue. There is a pressing need for new insight into disease etiology and progression. The PI will develop new Second Harmonic Generation (SHG) imaging tools for this purpose. They will extend current SHG microscopy to tomography for better characterization of 3D collagen structure. They will a) develop SHG excitation tomography; b) develope new reconstruction algorithms; and c) incorporate the 3D data into a respective classification scheme, and explore the use of deep learning algorithms to refine the classification analysis.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.