Integrating Clinical, Pathologic, and Immune Features to Predict Breast Cancer Recurrence and Chemotherapy Benefit

整合临床、病理和免疫特征来预测乳腺癌复发和化疗获益

• 批准号: 10723924
• 负责人: Frederick Matthew Howard
• 金额: $ 20.11万
• 依托单位: UNIVERSITY OF CHICAGO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-07 至 2028-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10723924
• 关键词: American Cancer Society; Antiestrogen Therapy; Artificial Intelligence; Biological Assay; Biological Markers; Biopsy; Cancer Etiology; Cancer Prognosis; Cell Density; Cells; Cessation of life; Chicago; Clinical; Clinical Data; Clinical Research; Data; Databases; Diagnosis; Disease; Disparity; ERBB2 gene; Gene Expression; Gene Expression Profile; Gene Expression Profiling; Goals; Guidelines; Hematoxylin and Eosin Staining Method; Histology; Hormone Receptor; Image; Image Analysis; Immune; Immunofluorescence Immunologic; Immunological Models; Immunology; Institution; Malignant Neoplasms; Modeling; Pathologic; Pathologist; Pathology; Patient Care; Patient Selection; Patients; Performance; Positioning Attribute; Prognosis; Recommendation; Recurrence; Recurrent Malignant Neoplasm; Research Personnel; Resource-limited setting; Retrospective cohort; Risk; Sampling; Selection for Treatments; Stains; Techniques; Test Result; Testing; Time; Training; Tumor-Infiltrating Lymphocytes; United States; Universities; Validation; Woman; Work; biobank; biomarker validation; breast cancer diagnosis; cancer diagnosis; cancer prevention; cancer recurrence; cancer survival; career; chemotherapy; clinical implementation; clinical practice; clinical predictors; clinically relevant; cohort; combat; cost effective; cost effective treatment; data streams; deep learning; deep learning model; design; digital; digital pathology; experience; genomic biomarker; health care disparity; hormone receptor-positive; hormone therapy; implementation science; improved; individualized medicine; malignant breast neoplasm; model development; mortality; novel; participant enrollment; patient subsets; personalized medicine; predictive marker; prognostic; prognostic model; quantitative imaging; receptor expression; treatment response

Abstract Breast cancer is the leading cause of cancer death for women globally, with over 2.3 million cases diagnosed each year. Most cases are hormone receptor positive and effectively treated with anti-estrogen therapy, but some patients have aggressive disease and are at risk for recurrence and death without chemotherapy. Gene expression based recurrence assays, such as OncotypeDX, were designed to predict recurrence on hormonal therapy and are used to select patients for chemotherapy. However, these assays are expensive (> $3,000 per test), take considerable time to perform leading to treatment delays, and testing is underutilized or frankly unavailable in low resource settings in the US and globally. Conversely, every patient with breast cancer has a biopsy to confirm the diagnosis, which is routinely analyzed by pathologist to determine subtype of breast cancer and grade. Deep learning is an emerging technique for quantitative image analysis, and can identify non-intuitive features from pathology, including gene expression patterns. In preliminary work, I have demonstrated that deep learning on pathology samples can provide rapid and cost-effective prediction of OncotypeDX score using readily available data, and can identify patients at low risk of recurrence on hormonal therapy. However, OncotypeDX remains an imperfect predictor of chemotherapy benefit, as it was developed to predict recurrence on hormonal therapy. By refining my deep learning biomarker to incorporate clinical and immune features of breast cancer, I can improve accuracy in prediction of chemotherapy benefit and thus the ability to personalize treatment. First, I will capitalize on the recent expansion of clinical data in the National Cancer Data Base to develop a more accurate clinical models of prognosis and chemotherapy benefit. Next, I will use multiplex immunofluorescence to better characterize spatial and cell density features associated with chemotherapy benefit, and use deep learning models to infer these features from standard hematoxylin and eosin stained digital pathology. Finally, I will integrate these clinical and immune models with my existing deep learning pathologic model and validate the integrated model in a multi-institutional cohort. The result of this work will result in a prognostic and predictive deep learning biomarker that makes accurate predictions from readily available clinical, pathologic, and inferred immune features. This approach has the potential to reduce chemotherapy delays due to rapid turnaround time, combat healthcare disparities through improved availability of testing, and improve personalization of treatment by tailoring a biomarker for prediction of chemotherapy benefit.

摘要 乳腺癌是全球女性癌症死亡的主要原因，有超过230万例病例 每年诊断。大多数病例为激素受体阳性，并有效地用抗雌激素治疗 治疗，但有些患者患有侵袭性疾病，并有复发和死亡的风险， 化疗基于基因表达的复发测定，如OncotypeDX，被设计用于预测 激素治疗复发，并用于选择化疗的患者。然而，这些测定是 昂贵（每次测试> 3，000美元），需要相当长的时间来执行，导致治疗延迟， 在美国和全球的低资源环境中，未得到充分利用或坦率地说无法利用。相反，每个病人 患有乳腺癌的患者需要进行活检以确认诊断，病理学家通常会对其进行分析，以确定 乳腺癌的亚型和分级。深度学习是一种新兴的定量图像分析技术， 并且可以识别来自病理学的非直观特征，包括基因表达模式。在前期工作中，我 已经证明，对病理学样本的深度学习可以提供快速和具有成本效益的预测， OncotypeDX评分使用现成的数据，可以识别激素治疗复发风险低的患者 疗法 然而，OncotypeDX仍然是一个不完美的化疗获益预测因子，因为它的开发是为了 预测激素治疗的复发通过完善我的深度学习生物标志物， 乳腺癌的免疫特征，我可以提高预测化疗效果的准确性， 个性化治疗的能力。首先，我将利用最近国家临床数据的扩展， 癌症数据库，以开发更准确的预后和化疗获益的临床模型。接下来我 将使用多重免疫荧光，以更好地表征空间和细胞密度的特点， 化疗的好处，并使用深度学习模型从标准苏木素和 伊红染色数字病理学。最后，我将把这些临床和免疫模型与我现有的深度 学习病理模型，并在多机构队列中验证整合模型。这项工作的结果 将产生一种预后和预测性的深度学习生物标志物， 可用的临床、病理和推断的免疫特征。这种方法有可能减少 由于快速周转时间导致的化疗延迟，通过改善可用性来消除医疗保健差异 通过定制生物标志物来预测化疗， 效益