Department of General Surgery, Shengjing Hospital of China Medical University, Shenyang, Liaoning, People's Republic of China.
Department of Oncology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, People's Republic of China.
Cancer Med. 2024 Oct;13(20):e70287. doi: 10.1002/cam4.70287.
The purpose of this study is to construct models for predicting platinum resistance in high-grade serous ovarian cancer (HGSOC) derived from quantitative spatial heterogeneity indicators obtained from F-FDG PET/CT images.
A retrospective study was conducted on patients diagnosed with HGSOC. Quantitative indicators of spatial heterogeneity were generated using conventional features and Haralick texture features from both CT and PET images. Three groups of predictive models (conventional, heterogeneity, and integrated) were built. Each group's optimal model was the one with the highest area under curve (AUC). Postoperative immunohistochemical staining for Ki-67 and p53 was conducted. The correlation between the heterogeneity indicators and scores for Ki-67 and p53 was assessed by Spearman's correlation coefficient (ρ).
A total of 286 patients (54.6 ± 9.3 years) were enrolled. And 107 spatial heterogeneity indicators were extracted. The optimal models for each group were obtained using the Gradient Boosting Machine (GBM) algorithm. There was an AUC of 0.790 (95% CI: 0.696, 0.885) in the conventional model for the validation set, and an AUC of 0.904 (95% CI: 0.842, 0.966) in the heterogeneity model for the validation set. The integrated model achieved the highest predictive performance, with an AUC value of 0.928 (95% CI: 0.872, 0.984) for the validation set. Spearman's correlation showed that HU_Kurtosis had the strongest correlation with p53 scores with ρ = 0.718, while cluster site entropy had the strongest correlation with Ki-67 scores with ρ = 0.753.
Adding quantitative spatial heterogeneity indicators derived from PET/CT images can improve the prediction of platinum resistance in patients with HGSOC. Spatial heterogeneity indicators were related to Ki-67 and p53 scores.
本研究旨在构建基于 F-FDG PET/CT 图像定量空间异质性指标预测高级别浆液性卵巢癌（HGSOC）铂耐药的模型。
对诊断为 HGSOC 的患者进行回顾性研究。使用 CT 和 PET 图像的常规特征和 Haralick 纹理特征生成定量空间异质性指标。建立三组预测模型（常规、异质性和综合）。每组的最佳模型是 AUC 最高的模型。对术后 Ki-67 和 p53 的免疫组织化学染色进行检测。采用 Spearman 相关系数（ρ）评估异质性指标与 Ki-67 和 p53 评分之间的相关性。
共纳入 286 例患者（54.6±9.3 岁），提取了 107 个空间异质性指标。使用梯度提升机（GBM）算法获得每组的最优模型。验证集中常规模型的 AUC 为 0.790（95%CI：0.696，0.885），验证集中异质性模型的 AUC 为 0.904（95%CI：0.842，0.966）。综合模型的预测性能最高，验证集的 AUC 值为 0.928（95%CI：0.872，0.984）。Spearman 相关显示，HU_Kurtosis 与 p53 评分的相关性最强，ρ=0.718，而聚类站点熵与 Ki-67 评分的相关性最强，ρ=0.753。
添加源自 PET/CT 图像的定量空间异质性指标可以提高预测 HGSOC 患者铂耐药的能力。空间异质性指标与 Ki-67 和 p53 评分相关。
