Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, ON, Canada.
Biological Sciences Platform, Sunnybrook Research Institute, Toronto, ON, Canada.
Breast Cancer Res Treat. 2021 Apr;186(2):379-389. doi: 10.1007/s10549-020-06093-4. Epub 2021 Jan 23.
Neoadjuvant chemotherapy (NAC) is used to treat patients with high-risk breast cancer. The tumor response to NAC can be classified as either a pathological partial response (pPR) or pathological complete response (pCR), defined as complete eradication of invasive tumor cells, with a pCR conferring a significantly lower risk of recurrence. Predicting the response to NAC, however, remains a significant clinical challenge. The objective of this study was to determine if analysis of nuclear features on core biopsies using artificial intelligence (AI) can predict response to NAC.
Fifty-eight HER2-positive or triple-negative breast cancer patients were included in this study (pCR n = 37, pPR n = 21). Multiple deep convolutional neural networks were developed to automate tumor detection and nuclear segmentation. Nuclear count, area, and circularity, as well as image-based first- and second-order features including mean pixel intensity and correlation of the gray-level co-occurrence matrix (GLCM-COR) were determined.
In univariate analysis, the pCR group had fewer multifocal/multicentric tumors, higher nuclear intensity, and lower GLCM-COR compared to the pPR group. In multivariate binary logistic regression, tumor multifocality/multicentricity (OR = 0.14, p = 0.012), nuclear intensity (OR = 1.23, p = 0.018), and GLCM-COR (OR = 0.96, p = 0.043) were each independently associated with likelihood of achieving a pCR, and the model was able to successful classify 79% of cases (62% for pPR and 89% for pCR).
Analysis of tumor nuclear features using digital pathology/AI can significantly improve models to predict pathological response to NAC.
新辅助化疗（NAC）用于治疗高危乳腺癌患者。NAC 的肿瘤反应可分为病理部分缓解（pPR）或病理完全缓解（pCR），定义为完全消除浸润性肿瘤细胞，pCR 显著降低复发风险。然而，预测 NAC 的反应仍然是一个重大的临床挑战。本研究旨在确定使用人工智能（AI）对核心活检中的核特征进行分析是否可以预测 NAC 的反应。
本研究纳入 58 例 HER2 阳性或三阴性乳腺癌患者（pCR n=37，pPR n=21）。开发了多个深度卷积神经网络来自动进行肿瘤检测和核分割。确定核计数、面积和圆形度，以及基于图像的一阶和二阶特征，包括平均像素强度和灰度共生矩阵（GLCM-COR）的相关性。
在单因素分析中，pCR 组多灶/多中心肿瘤较少，核强度较高，GLCM-COR 较低。在多变量二项逻辑回归中，肿瘤多灶性/多中心性（OR=0.14，p=0.012）、核强度（OR=1.23，p=0.018）和 GLCM-COR（OR=0.96，p=0.043）均与实现 pCR 的可能性独立相关，该模型能够成功分类 79%的病例（pPR 为 62%，pCR 为 89%）。
使用数字病理学/AI 分析肿瘤核特征可以显著提高预测 NAC 病理反应的模型。
