Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer
Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer
复制标题
DOI：
10.1001/jamanetworkopen.2019.7700
复制
发表时间：
2019-07-01
影响因子：
13.8
通讯作者：
Kimmel, Ron
中科院分区：
文献类型：
--
作者：
Shamai, Gil;Binenbaum, Yoav;Kimmel, Ron
重要性 免疫组织化学 (IHC) 是用于鉴定分子生物标志物的最广泛使用的检测方法。然而，IHC 既耗时又昂贵，取决于组织处理方案，并且依赖于病理学家的主观解释。机器学习的图像分析在病理学的各种应用中正在取得进展，但尚未被提议取代基于化学的分子检测分析。 目的 仅依赖于数字化苏木精 - 伊红 (H&E) 染色标本中所见的组织结构，评估癌症组织中生物标志物分子表达的预测可行性。 设计、设置和参与者 这项单一机构回顾性诊断研究评估了温哥华综合医院患者的乳腺癌组织微阵列库医院，不列颠哥伦比亚省，加拿大。该研究和分析于2015年7月1日至2018年7月1日进行。开发了一种称为基于形态学的分子分析（MBMP）的机器学习方法。使用 Logistic 回归探索组织形态学和生物标志物表达之间的相关性，并使用深度卷积神经网络来预测检查组织中的生物标志物表达。 主要结果和测量 用于评估分子生物标志物的 MBMP 的阳性预测值 (PPV)、阴性预测值 (NPV) 和接受者操作特征曲线下面积测量。 结果 该数据库由 20 600 个数字化、公开可用的 H&E 染色切片组成。来自 2 个队列的 5356 名乳腺癌患者。第 1 组（412 名患者）的诊断中位年龄为 61 岁，第 2 组（4944 名患者）的诊断中位年龄为 62 岁，中位随访时间分别为 12.0 年和 12.4 年。组织组织形态学与所有 19 种检测的生物标志物的分子表达显着相关，包括雌激素受体 (ER)、孕激素受体 (PR) 和 ERBB2（以前称为 HER2）。预测队列 1 207 名验证患者中的 105 名 (50.7%) 和队列 2 2046 名验证患者中的 1059 名 (51.8%) 的 ER 表达，PPV 分别为 97% 和 98%，NPV 分别为 68% 和 76%，准确度分别为 91% 和 92%，不劣于传统 IHC （PPV，91%-98%；NPV，51%-78%；准确度，81%-90%）。如果数据更多，诊断准确性就会提高。通过 IHC 对 ER 阴性/PR 阳性状态的患者进行形态学分析，结果显示与 ER 阳性状态的患者相似（Bhattacharyya 距离，0.03），而不是 ER 阴性/PR 阴性状态的患者（Bhattacharyya 距离，0.25）。这表明 IHC 结果为假阴性，并需要对这些患者进行抗激素治疗。 结论和相关性 对于本研究中至少一半的患者，MBMP 似乎可以预测生物标志物表达，且不劣于 IHC。结果表明，随着用于训练的数据的扩展，预测准确性可能会提高。基于形态学的分子分析可以用作基于数字化 H&E 染色图像的大规模分子分析的通用方法，从而可以使用快速、准确且廉价的方法同时分析癌症组织中的多个生物标志物。
IMPORTANCE Immunohistochemistry (IHC) is the most widely used assay for identification of molecular biomarkers. However, IHC is time consuming and costly, depends on tissue-handling protocols, and relies on pathologists' subjective interpretation. Image analysis by machine learning is gaining ground for various applications in pathology but has not been proposed to replace chemical-based assays for molecular detection.OBJECTIVE To assess the prediction feasibility of molecular expression of biomarkers in cancer tissues, relying only on tissue architecture as seen in digitized hematoxylin-eosin (H&E)-stained specimens.DESIGN, SETTING, AND PARTICIPANTS This single-institution retrospective diagnostic study assessed the breast cancer tissue microarrays library of patients from Vancouver General Hospital, British Columbia, Canada. The study and analysis were conducted from July 1, 2015, through July 1, 2018. A machine learning method, termed morphological-based molecular profiling (MBMP), was developed. Logistic regression was used to explore correlations between histomorphology and biomarker expression, and a deep convolutional neural network was used to predict the biomarker expression in examined tissues.MAIN OUTCOMES AND MEASURES Positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristics curve measures of MBMP for assessment of molecular biomarkers.RESULTS The database consisted of 20 600 digitized, publicly available H&E-stained sections of 5356 patients with breast cancer from 2 cohorts. The median age at diagnosis was 61 years for cohort 1 (412 patients) and 62 years for cohort 2 (4944 patients), and the median follow-up was 12.0 years and 12.4 years, respectively. Tissue histomorphology was significantly correlated with the molecular expression of all 19 biomarkers assayed, including estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (formerly HER2). Expression of ER was predicted for 105 of 207 validation patients in cohort 1 (50.7%) and 1059 of 2046 validation patients in cohort 2 (51.8%), with PPVs of 97% and 98%, respectively, NPVs of 68% and 76%, respectively, and accuracy of 91% and 92%, respectively, which were noninferior to traditional IHC (PPV, 91%-98%; NPV, 51%-78%; and accuracy, 81%-90%). Diagnostic accuracy improved given more data. Morphological analysis of patients with ER-negative/PR-positive status by IHC revealed resemblance to patients with ER-positive status (Bhattacharyya distance, 0.03) and not those with ER-negative/PR-negative status (Bhattacharyya distance, 0.25). This suggests a false-negative IHC finding and warrants antihormonal therapy for these patients.CONCLUSIONS AND RELEVANCE For at least half of the patients in this study, MBMP appeared to predict biomarker expression with noninferiority to IHC. Results suggest that prediction accuracy is likely to improve as data used for training expand. Morphological-based molecular profiling could be used as a general approach for mass-scale molecular profiling based on digitized H&E-stained images, allowing quick, accurate, and inexpensive methods for simultaneous profiling of multiple biomarkers in cancer tissues.