Precision imaging for risk stratification and personalized therapy of oropharyngeal cancer

口咽癌风险分层和个性化治疗的精准成像

• 批准号: 10445148
• 负责人: Quynh-Thu Xuan Le
• 金额: $ 63.31万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-05 至 2027-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10445148
• 关键词: Address; Anatomy; Architecture; Attention; Biological; Biological Factors; Cancer Patient; Clinical; Clinical Data; Clinical Trials; Complement; Data; Data Set; Detection; Diagnosis; Disease; Disease Progression; Dissection; Distant; Distant Metastasis; Enrollment; Epidemic; Evaluation; Exhibits; Future; Gene Expression; Goals; HPV oropharyngeal cancer; Habitats; Heterogeneity; Histologic; Histology; Human Papillomavirus; Human papilloma virus infection; Image; Image Analysis; Incidence; Individual; Invaded; Malignant Neoplasms; Modality; Modeling; Molecular; Morphology; Neoplasm Metastasis; Oncology; Outcome; Pathology; Pathway interactions; Patient Selection; Patients; Pattern; Performance; Performance Status; Phenotype; Primary Neoplasm; Prognosis; Prognostic Factor; Quality of life; Radiation Therapy Oncology Group; Radiogenomics; Randomized Clinical Trials; Reduce health disparities; Regional Disease; Relapse; Resource-limited setting; Risk; Smoking History; Stream; Testing; Texture; Therapeutic; Tissues; Toxic effect; Training; Underserved Population; Validation; Variant; X-Ray Computed Tomography; base; chemoradiation; clinical prognostic; cohort; deep learning; deep learning model; design; disorder risk; draining lymph node; health disparity; imaging approach; imaging biomarker; improved; improved outcome; innovation; knowledge base; lymph nodes; malignant oropharynx neoplasm; multimodal data; multitask; neglect; novel; oral HPV infection; oral lesion; overtreatment; personalized medicine; personalized predictions; precision medicine; preservation; prognostic; prognostic assays; prognostic model; prognostic signature; prognostic value; prospective; prospective test; quantitative imaging; radiological imaging; radiomics; randomized trial; response; risk stratification; standard care; success; therapy outcome; therapy resistant; treatment response; treatment strategy; tumor; tumor heterogeneity; virtual

ABSTRACT During the past few decades, there has been a rapid increase in the incidence of oropharyngeal cancer (OPC), which is attributable to the epidemic of oral human papillomavirus (HPV) infection. Patients with HPV-positive OPC respond well to concurrent chemoradiotherapy and have a more favorable prognosis than HPV-negative patients. However, standard treatment is associated with significant toxicity and likely represents over-treatment for many patients with HPV-positive disease. Several randomized clinical trials have tested novel deintensification strategies with the goal to reduce toxicity and improve patients’ quality of life while preserving the high cure rate. These trials enroll patients based on cancer stage and smoking history. However, current clinical prognostic factors are rather crude and do not accurately predict disease progression on an individual level. Reliable prognostic models are critically needed for personalized risk-adaptive therapy of OPC. To address this unmet need, we propose quantitative CT features to characterize intratumoral spatial heterogeneity and disease invasion/spread, which are known drivers of treatment resistance and disease progression. In addition to knowledge-based image features, we will develop complementary data-driven deep learning models to predict disease progression by using a retrospective multi- institutional dataset of 1771 patients. Further, we will integrate imaging with clinical data to improve prediction and establish their validity by rigorous prospective validation in 1780 patients enrolled in 3 randomized clinical trials. Finally, we will employ a radiogenomic approach to elucidate biological basis of the imaging signatures. If successful, the proposed models will allow more accurate prediction of prognosis and improve risk stratification of OPC. This has significant therapeutic implications by optimizing the selection of patients for treatment deintensification, which will increase the likelihood of success of future clinical trials and pave the way for precision medicine in OPC. Because the information is derived from standard CT scans, this would be readily integrated into current clinical workflow, widely applicable to underserved populations in low-resource settings, and therefore would help reduce health disparity in the US.

摘要 在过去的几十年里，口咽癌的发病率迅速上升。 癌症(OPC)，可归因于口腔人乳头瘤病毒(HPV)感染的流行。 HPV阳性的OPC患者对同期放化疗反应良好，并有更多的 预后优于HPV阴性患者。然而，标准治疗与 明显的毒性，可能代表着许多HPV阳性疾病患者的过度治疗。 几项随机临床试验已经测试了新的去强化策略，目标是 减少毒性，提高患者的生活质量，同时保持较高的治愈率。这些试验 根据癌症分期和吸烟史招募患者。然而，目前的临床预后 这些因素相当粗略，并不能准确地预测个体水平上的疾病进展。 OPC的个体化风险适应治疗迫切需要可靠的预后模型。至 为了解决这一未得到满足的需求，我们提出了定量CT特征来表征肿瘤内的空间 异质性和疾病入侵/传播，这是治疗耐药性和 疾病的发展。除了基于知识的图像功能外，我们还将开发补充 数据驱动的深度学习模型通过使用多个回溯性数据来预测疾病进展 1771名患者的机构数据集。此外，我们将把成像与临床数据结合起来，以改善 在3月份登记的1780名患者中通过严格的前瞻性验证预测并建立其有效性 随机临床试验。最后，我们将使用放射基因组学方法来阐明生物学 成像特征的基础。如果成功，建议的模型将允许更准确的 预测预后，改善OPC的危险分层。这有很大的治疗作用 通过优化非强化治疗患者的选择产生的影响，这将增加 未来临床试验成功的可能性，并为OPC的精准医学铺平道路。 由于信息来自标准的CT扫描，这将很容易地集成到 目前的临床工作流程，广泛适用于低资源环境中服务不足的人群，以及 因此，这将有助于缩小美国的健康差距。