Predicting Metastatic Progression of High Risk Localized Prostate Cancer

预测高风险局限性前列腺癌的转移进展

• 批准号: 10684561
• 负责人: Isla Pearl Garraway
• 金额: --
• 依托单位: VA GREATER LOS ANGELES HEALTHCARE SYSTEM
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10684561
• 关键词: Algorithms; Artificial Intelligence; Biological Markers; Categories; Cessation of life; Clinic; Clinical; Clinical Data; Clinical Management; Clinical Trials; Collection; Complex; Computer Vision Systems; Data; Data Collection; Data Set; Data Sources; Databases; Development; Diagnosis; Diagnostic; Diagnostic Imaging; Digital Radiography; Digital biomarker; Disease; Disease remission; Extramural Activities; Eye; FOLH1 gene; Future; Genomics; Goals; Guidelines; Healthcare Systems; Hematoxylin and Eosin Staining Method; Histopathology; Human; Image; Individual; Information Systems; Infrastructure; Integrated Health Care Systems; Intervention; Knowledge; Link; Machine Learning; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of prostate; Methods; Modeling; Molecular; National Comprehensive Cancer Network; Needle biopsy procedure; Neoplasm Metastasis; Operative Surgical Procedures; Outcome; Pathologic; Pathology; Patients; Pattern; Positron-Emission Tomography; Prostate; Protocols documentation; Radiation; Recurrence; Research Personnel; Risk; Science; Skin Carcinoma; Slide; Staging; Stains; Statistical Data Interpretation; Stratification; Structure; Testing; Tissues; Training; United States Department of Veterans Affairs; Validation; Veterans; Veterans Health Administration; Visual; artificial intelligence algorithm; biobank; cancer care; convolutional neural network; cost; data repository; data resource; data warehouse; digital imaging; digital pathology; digital repositories; feature selection; follow-up; health data; high risk; improved; improved outcome; machine learning model; military veteran; multidimensional data; multimodal data; multiple omics; novel; outcome prediction; precision oncology; predictive modeling; prognostic; prognostic model; prognostication; prostate biopsy; prostate cancer risk; radiological imaging; radiomics; repository; social health determinants; success; tool; transcriptomics; treatment strategy; tumor

ABSTRACT. Prostate cancer (CaP) is the most commonly diagnosed malignancy other than non-melanoma skin cancer amongst Veterans. Approximately 7% of US CaP cases are diagnosed and treated in the Veteran population. High risk (HR), localized CaP represents 20-25% of the approximately 250,000 new cases of CaP expected in the US in 2022. The outcomes of HR CaP are variable, with some patients remaining in remission and others suffering from metastatic progression and death. Our ability to discriminate between patients who will fare well following curative-intent treatment versus those destined for lethal metastatic progression remains poor. Our overall objective is to apply artificial intelligence (AI) algorithms to generate novel predictors of metastasis-free survival (MFS), the only validated surrogate for overall survival in localized CaP, from a large repository of digital pathology and radiographic images. We will then combine these AI-derived biomarkers with clinical-pathologic and social determinants of health (SDoH) variables collected from Veterans with HR CaP to develop and test multivariable prognostic models that improve our ability to predict MFS. AI, including computer vision and machine learning approaches, allows extraction of image patterns for sub- visual based characterization of CaP. Routine diagnostic prostate needle biopsy pathology slides that have been digitized as well as digital radiographic images (e.g. MRI) can be leveraged for machine learning derived from either (1) hand-crafted features (guided by existing domain knowledge) which are then used as the inputs to develop the machine-learning model based on the selected features, or (2) the raw data itself, which are used as inputs to develop the model through convolutional neural networks or other methods in an unsupervised manner. The former leverages existing domain knowledge and may require less input data, whereas the latter is not limited by prior knowledge, but requires more training data. We hypothesize that machine learning models based on multimodal data derived from MRI and digital pathology can be combined with clinic-pathologic and SDoH data to generate “super classifiers” that more accurately predict outcome without the need for costly tissue destructive methods. We propose to establish a collection of digital pathology and prostate MRI images along with clinic-pathologic and SDoH data from >5,000 Veterans with HR CaP who have been treated with curative intent and a minimum of 5 years of follow-up using our existing approved biorepository protocol. Subsequently, we will determine the most robust AI algorithm for each data source, and then test combinations of algorithms to generate a “superclassifier” that integrates AI-derived predictive models with standard clinico-pathologic and SDoH variables to predict MFS. Improved prognostication could illuminate strategies for treatment intensification or de- intensification that can be formally tested in future clinical trials. The substantial infrastructure and databases generated by this proposal as part of our repository will be accessible by intramural VA and extramural investigators for future approved studies.

抽象的。 前列腺癌（CAP）是最常见的恶性肿瘤，除非非黑色素瘤皮肤癌 在退伍军人中。在退伍军人人口中，约有7％的美国CAP病例被诊断和治疗。 高风险（HR），局部上限代表约250,000例新的CAP案例的20-25％ 美国在2022年。人力资源帽的结果可变，有些患者仍处于缓解状态，而另一些患者 患有转移性进展和死亡。我们区分良好表现的患者的能力 经过治愈的治疗与注定致命转移进展的治疗仍然很差。我们的 总体目标是应用人工智能（AI）算法来生成无转移的新预测指标 生存（MFS），这是唯一来自局部帽总体生存的替代物，来自大型数字存储库 病理和射线照相图像。然后，我们将将这些AI衍生的生物标志物与临床病理相结合 以及从具有人力资源帽的退伍军人收集的健康变量（SDOH）变量以开发和测试 多变量预后模型，可以提高我们预测MF的能力。 AI，包括计算机视觉和机器学习方法，可以提取图像模式以进行子图。 基于视觉的CAP表征。常规的诊断前列腺针头活检病理学幻灯片已经 数字化以及数字射线照相图像（例如MRI）可以利用从 （1）手工制作的功能（以现有域知识为指导），然后用作输入 根据所选功能开发机器学习模型，或（2）使用的原始数据本身 作为通过无监督的卷积神经网络或其他方法来开发模型的输入 方式。前者利用现有的域知识，可能需要更少的输入数据，而以后 不受先验知识的限制，而是需要更多的培训数据。我们假设机器学习模型 基于从MRI和数字病理学得出的多模式数据，可以与临床病理学和 SDOH数据生成“超级分类器”，该数据更准确地预测结果而无需昂贵的组织 破坏性方法。 我们建议建立数字病理学和前列腺MRI图像的集合以及临床病理学 来自> 5,000名退伍军人的SDOH数据，他们接受了治疗意图和最低治疗的人力资源帽 使用我们现有批准的生物措施协议进行5年的随访。随后，我们将确定 对于每个数据源，最强大的AI算法，然后测试算法的组合以生成一个 将AI衍生的预测模型与标准临床病理学和SDOH集成的“超级分类器” 变量预测MF。改善预后可能会阐明治疗加强或脱颖而出的策略 可以在以后的临床试验中正式测试的强化。实质基础架构和数据库 该提案作为我们存储库的一部分生成 未来批准研究的研究者。