Chen Chen, Gao Dan, Yue Huan, Wang Huijing, Qu Rui, Hu Xiaochi, Luo Libo
Breast and Thyroid Center, The First People's Hospital of Zunyi (The Third Affiliated Hospital of Zunyi Medical University), Zunyi, Guizhou, China.
Clinical Laboratory, The First People's Hospital of Zunyi (The Third Affiliated Hospital of Zunyi Medical University), Zunyi, Guizhou, China.
PLoS One. 2025 May 9;20(5):e0321717. doi: 10.1371/journal.pone.0321717. eCollection 2025.
Checkpoint kinase 1 (CHEK1) is often overexpressed in solid tumors. Nonetheless, the prognostic significance of CHEK1 in breast cancer (BrC) remains unclear. This study used pathomics leverages machine learning to predict BrC prognosis based on CHEK1 gene expression..
Initially, hematoxylin-eosin (H&E)-stained images obtained from The Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) were segmented using Otsu's method. Further, the sub-image features were extracted using machine learning algorithms based on PyRadiomics, mRMRe, and Gradient Boosting Machine (GBM). The predicted CHEK1 expression levels were represented as the pathomics score (PS) and validated using the corresponding RNA-seq data. The prognostic significance of both CHEK1 and PS was evaluated using Kaplan-Meier (KM), and univariate and multivariate Cox regression. The model was assessed by comparing CHEK1 expression by immunohistochemistry (IHC) with PS in BrC tissue microarray (TMA).
A 633 × 10 sub-image set was eligible for training and a 158 × 10 set for validation. 1,488 features were extracted and 8 recursive feature elimination (RFE)-screened features were used to generate the model. A high PS was associated with CHEK1 overexpression, significantly correlating with survival outcomes, especially within 96 months post-diagnosis. Further, patients with high PS responded to anti-programmed cell death protein 1 (anti-PD-1) and anti-cytotoxic T lymphocyte antigen-4 (anti-CTLA4) treatments. In TMA validation, the IHC analysis estimated that high PS similarly predicted poorer prognosis and correlated with higher CHEK1 expression.
The novel pathomics model reliably predicted CHEK1 expression using machine learning algorithms, which might provide potential clinical utility for prognosis and treatment guidance.
检查点激酶1（CHEK1）在实体瘤中常过度表达。然而，CHEK1在乳腺癌（BrC）中的预后意义仍不清楚。本研究利用病理学，借助机器学习基于CHEK1基因表达预测BrC预后。
首先，使用大津法对从癌症基因组图谱乳腺浸润性癌（TCGA-BRCA）获得的苏木精-伊红（H&E）染色图像进行分割。此外，使用基于PyRadiomics、最小冗余最大相关（mRMRe）和梯度提升机（GBM）的机器学习算法提取子图像特征。预测的CHEK1表达水平表示为病理学评分（PS），并使用相应的RNA测序数据进行验证。使用Kaplan-Meier（KM）以及单变量和多变量Cox回归评估CHEK1和PS的预后意义。通过比较免疫组织化学（IHC）检测的BrC组织微阵列（TMA）中的CHEK1表达与PS来评估该模型。
一个633×10的子图像集符合训练要求，一个158×10的集用于验证。提取了1488个特征，并使用8个递归特征消除（RFE）筛选的特征来生成模型。高PS与CHEK1过表达相关，与生存结果显著相关，尤其是在诊断后96个月内。此外，高PS的患者对抗程序性细胞死亡蛋白1（抗PD-1）和抗细胞毒性T淋巴细胞抗原4（抗CTLA4）治疗有反应。在TMA验证中，IHC分析估计高PS同样预测较差的预后，并与较高的CHEK1表达相关。
新的病理学模型使用机器学习算法可靠地预测了CHEK1表达，这可能为预后和治疗指导提供潜在的临床应用价值。
