A Quantitative Risk Model for Predicting Outcome and Identifying Structural Biomarkers of Treatment Targets in Oral Cancer on a Large Multi-Center Patient Cohort

用于预测大型多中心患者队列口腔癌治疗目标的结果和识别结构生物标志物的定量风险模型

• 批准号: 9974099
• 负责人: Scott Doyle
• 金额: $ 38.29万
• 依托单位: STATE UNIVERSITY OF NEW YORK AT BUFFALO
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-23 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/9974099
• 关键词: Active Learning; Address; Aftercare; Aggressive behavior; Algorithms; Architecture; Artificial Intelligence; Biological Markers; Blinded; Cancer Patient; Cessation of life; Clinical; Clinical Trials; Collection; Combined Modality Therapy; Communities; Companions; Consensus; Country; Data; Databases; Disease; Elements; Engineering; Evaluation; Excision; Foundations; Future; Goals; Head and Neck Surgery; Head and neck structure; Histologic; Image; Immune response; Link; Machine Learning; Malignant Neoplasms; Manuals; Medical Economics; Methods; Microscope; Modeling; Operative Surgical Procedures; Oral Stage; Outcome; Pathologist; Pathology; Pathology Report; Patients; Pattern; Performance; Play; Postoperative Period; Productivity; Quality of life; Radiation therapy; Randomized; Recurrence; Reporting; Reproducibility; Research; Resources; Risk; Salvage Therapy; Screening procedure; Semantics; Site; Slide; Specimen; Standardization; Structure; Surgical Pathology; System; Testing; Time; Tissues; Training; Validation; Work; Workload; analysis pipeline; angiogenesis; base; cancer recurrence; cancer type; clinical application; clinical practice; cohort; computational pipelines; deep learning; design; digital; digital pathology; expectation; experience; experimental study; feature extraction; high risk; imaging biomarker; improved; improved outcome; innovation; international center; malignant mouth neoplasm; novel strategies; outcome forecast; outcome prediction; pathology imaging; patient oriented; predictive modeling; pressure; prognostic; prognostic value; quality assurance; quantitative imaging; screening; segmentation algorithm; tool; treatment planning; tumor; uptake

Post-resection prognostication for oral cavity cancers (OCC) is qualitative and potentially ambiguous. A significant subset (25-37%) of Stage I/II patients still develop local recurrence after treatment with surgery alone. The long-term goal of this proposal will be to create a Quantitative Risk Model (QRM) using machine learning and artificial intelligence to predict recurrence risk for Stage I/II patients using image-based biomarkers of aggression. The objective is to develop and validate state-of-the-art systems for biomarker imaging, quantification, and modeling to accurately predict risk of recurrence in cancer patients based on image analytics. The central hypothesis is that a quantitative, artificial intelligence approach to pathology will result in significantly greater prognostic value compared with manual microscope-based analysis. The rationale for this work is that tumor aggression can be predicted from patterns present in pathology images, given the existence of histological risk models that have been clinically validated in the past; however, these risk models are not in widespread use because they are less accurate, robust, and transportable to the larger community of pathologists. This proposal will test the central hypothesis through three specific aims: (1) Develop an analysis pipeline that can accurately predict recurrence risk for Stage I/II OCC patients and identify treatment targets (e.g. adaptive local immune response and angiogenesis); (2) Demonstrate robust performance across a multi-site data cohort collected from seven national and international centers; and (3) Distil the results of QRM analysis to synoptic pathology reporting, demonstrating the ability of QRM to interface with standard clinical reporting tools. The innovation for addressing these aims comes from a unique application of active learning for training artificial intelligence to recognize tissue structures, new features for quantifying tissue architecture based on the interface between tumor and host, and a novel approach for large cross-site validation. Moreover, this proposal develops a unique mapping between computational pathology and commonly-used synoptic reporting variables, enabling rapid uptake of this work into existing clinical workflows. This research is significant because it provides personalized outcome predictions for a niche group of undertreated patients with limited options and can serve as the foundation for designing future clinical trials through identification of treatment targets. Multi-site training and evaluation, combined with AI-to-report mapping, will be broadly applicable to a large group of computational approaches, bridging the gap between engineering research labs and clinical application. The expected outcome of this work is a trained model for predicting Stage I/II OCC recurrence, identification of treatment targets, and mapping to synoptic reports, as well as a broadly-applicable workflow for the broader computational pathology community. This project will have a large positive impact on patients and surgical pathologists by enabling rapid, accurate prognosis and directed treatment plans in an easy-to-use pipeline that integrates seamlessly into existing clinical workflows.

口腔癌（OCC）的切除后预测是定性的且可能不明确。一个 显着亚群（25-37%）的 I/II 期患者在单独手术治疗后仍会出现局部复发。 该提案的长期目标是使用机器学习创建定量风险模型（QRM） 和人工智能使用基于图像的生物标志物来预测 I/II 期患者的复发风险 侵略。目标是开发和验证最先进的生物标志物成像系统， 基于图像分析进行量化和建模，以准确预测癌症患者的复发风险。 中心假设是定量的人工智能病理学方法将导致显着的结果 与基于手动显微镜的分析相比，具有更大的预后价值。这项工作的理由是 考虑到组织学图像的存在，可以根据病理图像中存在的模式来预测肿瘤的侵袭性。 过去已经过临床验证的风险模型；然而，这些风险模型并未得到广泛使用 因为它们的准确性、稳健性和可移植性较差，无法转移到更大的病理学家群体中。这个提议 将通过三个具体目标来检验中心假设：（1）开发一个能够准确地 预测 I/II 期 OCC 患者的复发风险并确定治疗目标（例如适应性局部免疫） 反应和血管生成）； (2) 在从以下来源收集的多站点数据队列中展示稳健的性能 七个国家和国际中心； (3) 将 QRM 分析结果提炼为天气病理学 报告，展示了 QRM 与标准临床报告工具接口的能力。创新为 解决这些目标需要通过主动学习的独特应用来训练人工智能 识别组织结构，基于之间的界面量化组织结构的新功能 肿瘤和宿主，以及一种用于大规模跨位点验证的新方法。此外，该提案还开发了一种独特的 计算病理学和常用的天气报告变量之间的映射，从而实现快速 将这项工作纳入现有的临床工作流程。这项研究意义重大，因为它提供了个性化的 对治疗不足、选择有限的小众患者的结果预测，可以作为 通过确定治疗目标来设计未来临床试验的基础。多地点培训和 评估与人工智能到报告映射相结合，将广泛适用于大量计算 方法，弥合工程研究实验室和临床应用之间的差距。预期结果 这项工作的核心是一个经过训练的模型，用于预测 I/II 期 OCC 复发、识别治疗目标以及 映射到概要报告，以及更广泛的计算病理学的广泛适用的工作流程 社区。该项目将通过实现快速、 在易于使用的管道中提供准确的预后和定向治疗计划，无缝集成到 现有的临床工作流程。