Early Evaluation of Ovarian Cancer Prognosis by Fusing Radiographic and Histopathologic Imaging Information

通过融合放射学和组织病理学成像信息对卵巢癌预后进行早期评估

• 批准号: 10334987
• 负责人: Yuchen Qiu
• 金额: $ 24.49万
• 依托单位: UNIVERSITY OF OKLAHOMA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-15 至 2026-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10334987
• 关键词: Address; Algorithms; BRCA mutations; Bayesian Modeling; Biological Markers; CA-125 Antigen; Cancer Center; Cancer Patient; Cancer Prognosis; Characteristics; Clinical; Clinical Markers; Confusion; Data; Data Analyses; Data Set; Databases; Decision Making; Diagnosis; Engineering; Evaluation; Guidelines; Gynecologic Oncology; Histopathology; Hybrids; Image; Learning; Machine Learning; Malignant Female Reproductive System Neoplasm; Malignant Neoplasms; Malignant neoplasm of ovary; Medical Imaging; Medical center; Methods; Modeling; Network-based; Oklahoma; Oncologist; Outcome; Pathologic; Pathology; Patients; Performance; Pharmaceutical Preparations; Physicians; Prediction of Response to Therapy; Progression-Free Survivals; Prospective Studies; Radiology Specialty; Recurrence; Research; Research Personnel; Research Project Grants; Research Support; Sampling; Scheme; Statistical Data Interpretation; Statistical Methods; Technology; Testing; Toxic effect; Training; Treatment Efficacy; Tumor Volume; United States National Institutes of Health; Universities; Validation; X-Ray Computed Tomography; base; cancer cell; cancer imaging; cancer therapy; chemotherapy; clinical practice; college; computer aided detection; deep neural network; digital; feature selection; graphical user interface; hazard; image processing; imaging biomarker; improved; interest; machine learning model; multidisciplinary; multimodality; novel; operation; overtreatment; particle; pathology imaging; patient prognosis; patient response; patient stratification; patient subsets; personalized chemotherapy; predictive modeling; prognostic; prognostic value; prospective; quantitative imaging; radiological imaging; radiologist; radiomics; response; side effect; support tools; support vector machine; technology development; technology validation; tool; transfer learning; translational cancer research; treatment response; treatment strategy; tumor; tumor heterogeneity; vector; Address; Algorithms; BRCA mutations; Bayesian Modeling; Biological Markers; CA-125 Antigen; Cancer Center; Cancer Patient; Cancer Prognosis; Characteristics; Clinical; Clinical Markers; Confusion; Data; Data Analyses; Data Set; Databases; Decision Making; Diagnosis; Engineering; Evaluation; Guidelines; Gynecologic Oncology; Histopathology; Hybrids; Image; Learning; Machine Learning; Malignant Female Reproductive System Neoplasm; Malignant Neoplasms; Malignant neoplasm of ovary; Medical Imaging; Medical center; Methods; Modeling; Network-based; Oklahoma; Oncologist; Outcome; Pathologic; Pathology; Patients; Performance; Pharmaceutical Preparations; Physicians; Prediction of Response to Therapy; Progression-Free Survivals; Prospective Studies; Radiology Specialty; Recurrence; Research; Research Personnel; Research Project Grants; Research Support; Sampling; Scheme; Statistical Data Interpretation; Statistical Methods; Technology; Testing; Toxic effect; Training; Treatment Efficacy; Tumor Volume; United States National Institutes of Health; Universities; Validation; X-Ray Computed Tomography; base; cancer cell; cancer imaging; cancer therapy; chemotherapy; clinical practice; college; computer aided detection; deep neural network; digital; feature selection; graphical user interface; hazard; image processing; imaging biomarker; improved; interest; machine learning model; multidisciplinary; multimodality; novel; operation; overtreatment; particle; pathology imaging; patient prognosis; patient response; patient stratification; patient subsets; personalized chemotherapy; predictive modeling; prognostic; prognostic value; prospective; quantitative imaging; radiological imaging; radiologist; radiomics; response; side effect; support tools; support vector machine; technology development; technology validation; tool; transfer learning; translational cancer research; treatment response; treatment strategy; tumor; tumor heterogeneity; vector

Project 3: Early Evaluation of Ovarian Cancer Prognosis by Fusing Radiographic and Histopathologic Imaging Information ABSTRACT As the most aggressive malignancy in gynecologic oncology, ovarian cancer is highly heterogeneous and the tumor response to a specific chemotherapy vary significantly among patients. However, due to the lack of accurate clinical markers to stratify patients and predict who can and cannot benefit from certain types of chemotherapy drugs or methods, efficacy of treating ovarian cancer patients using chemotherapy is low. In order to address and help solve this clinical challenge, the overarching objective of this project is to develop and validate a new strategy for early prediction of tumor response to chemotherapy using a novel image marker generated by a machine learning model that is trained using quantitative image features computed from computer tomography (CT) and digital histopathology images. Based on the concept of Radiomics, Pathomics and our encouraging preliminary studies, we hypothesize that the state-of-the-art data analysis technology can fuse the valuable prognostic information from both radiographic and pathological images to generate a new image marker, which has a high degree of association with the chemotherapy response of ovarian cancer patients. To validate this hypothesis, we propose 4 specific aims. Aim 1: Based on a diverse patient database at the Stephenson Cancer Center, we will assemble one retrospective and one prospective dataset, containing a total of 420 ovarian cancer patients who have undergone chemotherapies. The dataset will include CT images, histopathological images of tumor samples and other related clinical information of each patient. Aim 2: We will explore and identify tumor heterogeneity-related images features computed from both CT and pathology images after applying a new hybrid image processing scheme to accurately segment tumor volume and cancer cells. Aim 3: We will apply feature selection methods on the initial CT/pathology feature pools to identify two optimal feature vectors. Then, a prediction model (i.e., Bayesian belief network) will be trained to fuse optimal feature vectors and other clinical variables to predict tumor response to therapy at early stage. Aim 4: We will conduct a pilot prospective study to evaluate performance and robustness of the prediction model. Several statistical methods (i.e. Cox proportional hazards analysis, receiver operation characteristic curve, confusion matrix) will be used to evaluate the performance improvement by fusing the CT and pathology image features. We will also validate the added prognostic value provided by the new model in the context of the existing markers. In order to accomplish the proposed aims and research tasks, an interdisciplinary team is assembled, which includes experts in medical imaging, gynecologic oncology, radiology and pathology from the University of Oklahoma. If successful, this project can produce the essential preliminary data and scientific evidence to support the research project leader (RPL) to apply for a more comprehensive research project (i.e., NIH R01) to further optimize and validate a first-of-its-kind, robust, easy-to-use decision-making support tool, which can help clinicians (i.e., radiologists and oncologists) determine the optimal cancer treatment strategy for different patients.

项目3：通过融合射线照相和组织病理学对卵巢癌预后的早期评估 成像信息 抽象的 作为妇科肿瘤学中最具侵略性的恶性肿瘤，卵巢癌是高度异质性的，并且 患者对特定化学疗法的肿瘤反应差异很大。但是，由于缺乏 准确的临床标记，以分层患者并预测谁可以也不能从某些类型的 化学疗法药物或方法，使用化学疗法治疗卵巢癌患者的功效很低。为了 为了解决和帮助解决这一临床挑战，该项目的总体目标是发展和 使用新型图像标记验证一种新的策略，用于早期预测肿瘤对化学疗法的反应 由机器学习模型生成的模型，该模型是使用定量图像功能训练的 计算机断层扫描（CT）和数字组织病理学图像。基于放射线学的概念 以及我们令人鼓舞的初步研究，我们假设最先进的数据分析技术可以 融合来自射线照相和病理图像的有价值的预后信息，以产生新的 图像标记，与卵巢癌的化学疗法反应具有高度关联 患者。为了验证这一假设，我们提出了4个具体目标。目标1：基于多样化的患者数据库 在斯蒂芬森癌症中心，我们将组装一个回顾性和一个前瞻性数据集，其中包含 共有420名接受化学疗法的卵巢癌患者。数据集将包括CT图像， 肿瘤样品和每个患者其他相关临床信息的组织病理学图像。目标2：我们将 探索和识别从CT和病理图像计算的肿瘤异质性的图像特征 在应用新的杂种图像处理方案以准确分割肿瘤体积和癌细胞之后。 AIM 3：我们将在初始CT/病理特征池上应用功能选择方法来识别两个最佳 功能向量。然后，将训练一个预测模型（即贝叶斯信仰网络）以融合最佳功能 向量和其他临床变量预测早期肿瘤对治疗的反应。目标4：我们将进行 一项试点的前瞻性研究，以评估预测模型的性能和鲁棒性。几个统计 方法（即COX比例危害分析，接收器操作特征曲线，混乱矩阵）将 通过融合CT和病理图像特征来评估性能改善。我们也会 验证新模型在现有标记的上下文中提供的附加预后价值。为了 为了完成拟议的目标和研究任务，组装了一个跨学科团队，其中包括 俄克拉荷马大学医学成像，妇科肿瘤学，放射学和病理学专家。如果 成功，该项目可以产生基本的初步数据和科学证据来支持研究 项目负责人（RPL）申请更全面的研究项目（即NIH R01），以进一步优化和 验证首先，强大，易于使用的决策支持工具，该工具可以帮助临床医生（即 放射科医生和肿瘤学家）确定不同患者的最佳癌症治疗策略。