Efficient and cost-effective breast cancer risk stratification using whole slide histopathology images

使用全玻片组织病理学图像进行高效且经济的乳腺癌风险分层

• 批准号: 10649978
• 负责人: Metin Nafi Gurcan
• 金额: $ 19.09万
• 依托单位: WAKE FOREST UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-06 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10649978
• 关键词: Age; Attention; Biological Assay; Biological Markers; Biopsy; Breast Cancer Patient; Breast Cancer Risk Factor; Breast Cancer therapy; Cancer Prognosis; Categories; Cell Nucleus; Cells; Classification; Clinical; Clinical Research; Clinical Trials; Consumption; Data; Developing Countries; Diagnosis; Diagnostic; Disease; Duct (organ) structure; ERBB2 gene; Effectiveness; Ensure; Epithelium; Estrogen Receptors; Estrogen receptor positive; Estrogens; Gene Expression; Genes; Health; Hematoxylin and Eosin Staining Method; Histologic; Histology; Histopathology; Human; Image; Image Analysis; Internet; Interobserver Variability; Learning; Malignant Neoplasms; Measures; Methods; Mission; Modeling; Nature; Outcome; Patients; Performance; Play; Population; Premature Menopause; Progesterone; Progesterone Receptors; Prognosis; Public Health; Recurrence; Recurrence Score; Regional Anatomy; Research; Resource-limited setting; Resources; Reverse Transcriptase Polymerase Chain Reaction; Risk; Slide; Stains; Stratification; Time; Tissues; Training; Tumor Tissue; Tumor stage; United States; United States National Institutes of Health; Validation; Woman; breast imaging; chemotherapy; cohort; cost; cost effective; design; detection method; diagnostic accuracy; erbB-2 Receptor; high risk; hormone receptor-positive; imaging biomarker; improved; large datasets; malignant breast neoplasm; mortality; novel strategies; oncotype; optimal treatments; overexpression; patient stratification; personalized care; prevent; progesterone receptor positive; receptor; risk stratification; rural area; side effect; tool; tumor; web-based tool; whole slide imaging

Efficient and cost-effective breast cancer risk stratification using whole-slide histopathology images Breast cancer prognosis depends highly on receptor status, as optimal treatment depends on the presence or absence of overexpression of estrogen, progesterone, or HER-2/neu receptors. To prevent over-treating patients with chemotherapy, it is crucial to quantify the risk of recurrence for estrogen receptor (ER) positive (ER+), HER2 negative (HER2-) breast cancer. A common assessment method to meet this need is the Oncotype DX (ODX) Recurrence Score. Unfortunately, ODX and similar gene assays are expensive, time-consuming, and tissue destructive. As an alternative, we propose estimating the ODX recurrence score using routine, ubiquitous, and inexpensive hematoxylin and eosin (H&E) staining of biopsies. There are other efforts to predict ODX recurrence risk from H&E. These automated methods detect histological primitives (e.g., nuclei) often in specific, also automatically detected, anatomical regions (e.g., ducts, tubules, lumen, epithelium, and stroma). Classification is performed into two or three risk categories, often collapsing two categories into one. The performance of these models is promising but still modest. One way to improve the performance of the models is to train on larger datasets; however, annotating larger datasets is challenging. Here, we propose an automated method to predict ODX recurrence risk without annotations. If successful, this method would have a wide range of applications, including but not limited to the availability of an inexpensive, web-based tool to predict ODX in developing countries or rural areas with internet access where standard Oncotype Dx assay would be cost-prohibitive or take too long to obtain. Furthermore, our method would find use in clinical research where valuable tumor tissue could be saved by obtaining correlative research data based on standard H&E-stained slides.

使用全玻片组织病理学进行高效且经济有效的乳腺癌风险分层 图片 乳腺癌的预后在很大程度上取决于受体状态，因为最佳治疗取决于 雌激素、孕激素或 HER-2/neu 受体过度表达的存在或不存在。 为了防止过度治疗患者化疗，量化化疗风险至关重要 雌激素受体 (ER) 阳性 (ER+)、HER2 阴性 (HER2-) 乳腺癌复发。一个 满足这种需求的常用评估方法是 Oncotype DX (ODX) 复发评分。 不幸的是，ODX 和类似的基因检测方法昂贵、耗时，并且组织 具有破坏性。作为替代方案，我们建议使用常规方法估计 ODX 复发评分， 普遍存在且廉价的苏木精和伊红 (H&E) 活检活检染色。还有其他的 预测 H&E 的 ODX 复发风险的努力。这些自动化方法检测组织学 基元（例如，细胞核）通常位于特定的、自动检测到的解剖区域（例如， 导管、小管、管腔、上皮和间质）。分类为两级或三级风险 类别，通常将两个类别合并为一个类别。这些模型的性能是 有希望但仍然谦虚。提高模型性能的一种方法是训练 更大的数据集；然而，注释更大的数据集具有挑战性。在这里，我们提出一个 无需注释即可预测 ODX 复发风险的自动化方法。如果成功的话，这 该方法将具有广泛的应用，包括但不限于可用性 廉价、基于网络的工具，可通过互联网预测发展中国家或农村地区的 ODX 标准 Oncotype Dx 检测成本高昂或需要很长时间才能获得。 此外，我们的方法将在临床研究中得到应用，其中有价值的肿瘤组织可以 通过获取基于标准 H&E 染色载玻片的相关研究数据来保存。