Multi-modal machine learning to guide adjuvant therapy in surgically resectable colorectal cancer

多模式机器学习指导可手术切除结直肠癌的辅助治疗

• 批准号: 10588103
• 负责人: Jeanne Shen
• 金额: $ 62.96万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-05-02 至 2028-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10588103
• 关键词: Address; Adjuvant Chemotherapy; Adjuvant Therapy; Architecture; Area; Biological Markers; Cancer Etiology; Catalogs; Cessation of life; Clinical; Clinical Data; Clinical Medicine; Collaborations; Colorectal Cancer; Companions; Computerized Medical Record; Data; Data Set; Deposition; Development; Diagnosis; Diagnostic; Disease; Disease-Free Survival; Ensure; Evaluation; Excision; Future; Health Care Costs; Human; Image; Institution; Laboratories; Machine Learning; Magnetic Resonance Imaging; Malignant Neoplasms; Methods; Modality; Modeling; Morbidity - disease rate; Oncologist; Oncology; Operative Surgical Procedures; Outcome; Pathologic; Pathologist; Pathology; Patient Triage; Patients; Performance; Pharmaceutical Preparations; Physicians; Precision therapeutics; Radiology Specialty; Records; Recurrence; Research; Research Personnel; Resectable; Resources; Risk; Secure; Stratification; Structure; Testing; Time; Training; Treatment-related toxicity; Validation; X-Ray Computed Tomography; anticancer research; biomedical data science; cancer biomarkers; cancer surgery; cancer type; chemotherapy; cohort; colon cancer patients; computer science; cost; cost efficient; data de-identification; data fusion; data modeling; data sharing; deep learning; deep learning model; electronic structure; empowerment; follow-up; high risk; imaging study; improved; machine learning model; mortality; multimodal data; multimodality; novel; online repository; overtreatment; pathology imaging; precision medicine; primary outcome; prognostic; prognostic assays; prognostication; radiological imaging; radiologist; risk stratification; standard of care; statistics; tool; treatment planning; tumor; unnecessary treatment; whole slide imaging

Project Summary / Abstract Colorectal cancer (CRC) is the third most commonly diagnosed malignancy and the second leading cause of cancer death worldwide. There is an unmet need for accurate, cost-efficient, and broadly accessible risk- stratification tools to identify patients at increased risk of recurrence , who are most likely to benefit from adjuvant therapy. Current standard-of-care risk stratification approaches are inadequate. Every CRC surgical candidate undergoes pathologic and radiologic evaluation of their tumor; these two modalities represent a rich, readily accessible and, thus far, underutilized resource for developing new risk-stratification tools. Deep learning (DL) has demonstrated great potential for augmenting physicians on an increasing range of diagnostic and prognostic tasks in pathology, radiology, and clinical medicine. We hypothesize that applying integrated DL-based analysis to multimodal (pathologic, radiologic, and electronic medical record (EMR)) data will yield greatly improved stratification of CRC patients for adjuvant treatment planning. We propose to build the first comprehensive, publicly-available, expert-annotated multimodal CRC dataset for deep learning, containing annotated CRC pathology whole-slide images (WSI), preoperative CT and MRI images, and structured clinical EMR data. Using this dataset, we will develop both single and multi-modality DL models for risk stratification of surgically-resectable (Stage I-III) CRC patients.To test our hypothesis, we will compare the performance of multi-modality models with that of single-modality models and existing methods of stratification. This project benefits from the complementary expertise and resources of a unique interdisciplinary team spanning the fields of machine learning, pathology, radiology, and oncology.

项目总结/摘要 结直肠癌（CRC）是第三大最常诊断的恶性肿瘤，也是第二大导致结直肠癌的原因。 全球癌症死亡人数对准确、经济高效和广泛可及的风险的需求尚未得到满足- 分层工具，用于识别复发风险增加的患者，这些患者最有可能受益于 辅助治疗目前的标准治疗风险分层方法是不够的。每次CRC手术 候选人经历他们的肿瘤的病理学和放射学评估;这两种模式代表了丰富的， 开发新的风险分层工具所需的现成资源，迄今尚未得到充分利用。深 学习（DL）已被证明具有极大的潜力，可以增强医生对越来越多的诊断范围的认识。 以及病理学、放射学和临床医学中的预后任务。我们假设， 对多模态（病理学、放射学和电子病历（EMR））数据进行基于DL的分析， 大大改善了CRC患者的分层，以制定辅助治疗计划。我们建议建立第一个 用于深度学习的全面、公开、专家注释的多模式CRC数据集，包含 注释的CRC病理学全切片图像（WSI）、术前CT和MRI图像，以及结构化的临床 电子病历数据。使用该数据集，我们将开发单模态和多模态DL模型用于以下疾病的风险分层： 可手术切除（I-III期）的CRC患者。为了验证我们的假设，我们将比较以下患者的表现 多模态模型与单模态模型和现有分层方法的对比。这个项目 受益于跨领域的独特跨学科团队的互补专业知识和资源 of machine机器learning学习，pathology病理学，radiology放射学，and oncology肿瘤学.