Deep learning in cervical cancer radiogenomics

宫颈癌放射基因组学中的深度学习

• 批准号: 10424854
• 负责人: Jin Zhang
• 金额: $ 22.09万
• 依托单位: WASHINGTON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-13 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10424854
• 关键词: 3-Dimensional; Accounting; Address; Affect; Biological; Biological Markers; Biology; Biopsy Specimen; Cancer Patient; Cervix Neoplasms; Cessation of life; Characteristics; Clinical; Clinical Data; Complex; Data; Data Reporting; Data Set; Dimensions; Disease; Early Intervention; Equation; Future; Gene Expression; Genes; Genomics; Genotype; Goals; HPV oropharyngeal cancer; HPV-High Risk; Human Papillomavirus; Image; Investigational Therapies; Lead; Learning; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of cervix uteri; Methodology; Methods; Modality; Modeling; Oncogenic; Organoids; Outcome; Pathway interactions; Patient Outcomes Assessments; Patient-Focused Outcomes; Patients; Pattern; Phenotype; Positron-Emission Tomography; Prediction of Response to Therapy; Predictive Value; Radiation Dose Unit; Radiation therapy; Radiogenomics; Reaction Time; Recurrence; Regimen; Research; Risk; Sample Size; Sampling; Structural Genes; Structure; Survival Rate; The Cancer Genome Atlas; Therapy Clinical Trials; Time; Treatment Failure; Treatment outcome; Tumor Bank; Woman; X-Ray Computed Tomography; advanced disease; autoencoder; base; cancer diagnosis; cancer recurrence; cancer subtypes; cancer survival; cancer type; chemoradiation; clinical phenotype; clinical predictors; clinical trial enrollment; clinically relevant; cohort; complex data; deep learning; deep learning model; design; differential expression; epithelial to mesenchymal transition; experience; feature selection; follow-up; generative adversarial network; genomic data; high dimensionality; improved; insight; network models; neural network; novel; patient stratification; personalized medicine; predicting response; predictive marker; predictive modeling; prognostic; prospective; radiation response; radiomics; research clinical testing; risk prediction model; standard of care; stem; tool; treatment planning; treatment response; treatment risk; tumor

PROJECT SUMMARY/ABSTRACT The overall goal of this proposal is to optimize the use of radiomic and genomic data to develop biomarkers which make clinical predictions that change cancer patient management. While the need for such predictive biomarkers is evident across cancer types, we focus our proposal on the particularly prevalent and damaging condition of recurrent, locally-advanced cervical cancer (LACC). Cervical cancer remains the third most common cancer diagnosis of women, and treatment failure for locally-advanced disease is 30-50% following chemoradiation therapy. There is a pressing need to identify patients at risk for treatment failure to allow for personalized treatment including modified chemoradiation regimens, early escalation of therapy, and clinical trial enrollment. To develop radiogenomic biomarkers for LACC recurrence, this proposal addresses three outstanding methodological needs: limited availability of gene expression data for cancer subtypes, noisy and redundant imaging feature data, and lack of disease-informed, interpretable -omics integration, each addressed in its own specific aim. Aim 1 will use generative adversarial networks (GAN) to augment the small gene expression datasets for all high-risk HPV subtypes. Aim 2 will optimize imaging feature selection using a deep convolutional autoencoder (CAE). Aim 3 will integrate radiogenomic features through a structural equation modeling (SEM) approach incorporating HPV-specific oncogenic mechanisms as latent variables. Together, we expect fulfillment of these aims will create an optimized recurrence biomarker which will out- perform other prediction modalities as well as standard-of-care follow-up imaging. Beyond the specific application to HPV-driven malignancies, our proposal will generate novel tools and methods to integrate any high-dimensional radiogenomic data with hypothesis-driven research findings to improve cancer prediction.

项目摘要/摘要 这项提案的总体目标是优化放射和基因组数据的使用，以开发生物标志物。 它做出的临床预测改变了癌症患者的管理。虽然需要这样的预测性 生物标记物在癌症类型中是显而易见的，我们将重点放在特别普遍和具有破坏性的 复发的局部晚期宫颈癌(LACC)的状况。宫颈癌仍排在第三位 女性的常见癌症诊断和局部晚期疾病的治疗失败以下为30-50% 放化疗。迫切需要确定有治疗失败风险的患者 个体化治疗，包括改良的放化疗方案、早期升级治疗和临床 试行招生。为了开发LACC复发的放射基因组生物标记物，这项建议涉及三个 突出的方法学需求：癌症亚型的基因表达数据有限，噪声和 冗余的成像特征数据，以及缺乏了解疾病、可解释的组学集成 在它自己的具体目标中解决。目标1将使用生成性对抗网络(GAN)来增强小的 所有高危HPV亚型的基因表达数据集。AIM 2将使用 深度卷积自动编码器(CAE)。目标3将通过结构上的 将HPV特异性致癌机制作为潜在变量的方程建模方法。 我们预计，这些目标的实现将创造一个优化的复发生物标记物，它将超越- 执行其他预测模式以及标准护理后续成像。超越具体的 应用于HPV驱动的恶性肿瘤，我们的建议将产生新的工具和方法来集成任何 高维放射基因组数据与假说驱动的研究结果，以改善癌症预测。