Department of Computing Science, University of Alberta and Alberta Machine Intelligence Institute, Edmonton, Canada.
Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
J Pathol. 2022 May;257(1):17-28. doi: 10.1002/path.5864. Epub 2022 Feb 22.
We assessed the utility of quantitative features of colon cancer nuclei, extracted from digitized hematoxylin and eosin-stained whole slide images (WSIs), to distinguish between stage II and stage IV colon cancers. Our discovery cohort comprised 100 stage II and stage IV colon cancer cases sourced from the University Hospitals Cleveland Medical Center (UHCMC). We performed initial (independent) model validation on 51 (143) stage II and 79 (54) stage IV colon cancer cases from UHCMC (The Cancer Genome Atlas's Colon Adenocarcinoma, TCGA-COAD, cohort). Our approach comprised the following steps: (1) a fully convolutional deep neural network with VGG-18 architecture was trained to locate cancer on WSIs; (2) another deep-learning model based on Mask-RCNN with Resnet-50 architecture was used to segment all nuclei from within the identified cancer region; (3) a total of 26 641 quantitative morphometric features pertaining to nuclear shape, size, and texture were extracted from within and outside tumor nuclei; (4) a random forest classifier was trained to distinguish between stage II and stage IV colon cancers using the five most discriminatory features selected by the Wilcoxon rank-sum test. Our trained classifier using these top five features yielded an AUC of 0.81 and 0.78, respectively, on the held-out cases in the UHCMC and TCGA validation sets. For 197 TCGA-COAD cases, the Cox proportional hazards model yielded a hazard ratio of 2.20 (95% CI 1.24-3.88) with a concordance index of 0.71, using only the top five features for risk stratification of overall survival. The Kaplan-Meier estimate also showed statistically significant separation between the low-risk and high-risk patients, with a log-rank P value of 0.0097. Finally, unsupervised clustering of the top five features revealed that stage IV colon cancers with peritoneal spread were morphologically more similar to stage II colon cancers with no long-term metastases than to stage IV colon cancers with hematogenous spread. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
我们评估了从数字化苏木精和伊红染色全切片图像（WSI）中提取的结肠癌核的定量特征，以区分 II 期和 IV 期结肠癌。我们的发现队列包括来自克利夫兰大学医院（UHCMC）的 100 例 II 期和 IV 期结肠癌病例。我们在 UHCMC（癌症基因组图谱的结肠癌腺癌，TCGA-COAD）队列中对 51 例（143 例）II 期和 79 例（54 例）IV 期结肠癌病例进行了初步（独立）模型验证。我们的方法包括以下步骤：（1）使用具有 VGG-18 架构的全卷积深度神经网络来定位 WSI 上的癌症；（2）使用基于 Mask-RCNN 的另一个深度学习模型，该模型具有 Resnet-50 架构，用于从识别出的癌症区域内分割所有细胞核；（3）从肿瘤内和肿瘤外的核中提取总共 26641 个与核形状、大小和纹理相关的定量形态计量特征；（4）使用 Wilcoxon 秩和检验选择的五个最具鉴别力的特征，训练随机森林分类器来区分 II 期和 IV 期结肠癌。在 UHCMC 和 TCGA 验证集中的保留病例上，我们使用这前五个特征训练的分类器分别产生了 0.81 和 0.78 的 AUC。对于 197 例 TCGA-COAD 病例，Cox 比例风险模型仅使用前五个特征进行总体生存风险分层，得出风险比为 2.20（95%CI 1.24-3.88），一致性指数为 0.71。Kaplan-Meier 估计也显示低风险和高风险患者之间存在统计学显著差异，对数秩 P 值为 0.0097。最后，前五个特征的无监督聚类显示，具有腹膜播散的 IV 期结肠癌在形态上与无长期转移的 II 期结肠癌更为相似，而与血行播散的 IV 期结肠癌则不相似。2022 年，The Journal of Pathology 由 John Wiley & Sons Ltd 代表英国和爱尔兰病理学学会出版。
