Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Huanhuxi Road, Hexi Distinct, 300060, Tianjin, China.
Tianjin's Clinical Research Center for Cancer, Tianjin, 300060, China.
Eur J Nucl Med Mol Imaging. 2023 Jun;50(7):1869-1880. doi: 10.1007/s00259-023-06150-2. Epub 2023 Feb 20.
To develop and validate the predictive value of an F-fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) model for breast cancer neoadjuvant chemotherapy (NAC) efficacy based on the tumor-to-liver ratio (TLR) radiomic features and multiple data pre-processing methods.
One hundred and ninety-three breast cancer patients from multiple centers were retrospectively included in this study. According to the endpoint of NAC, we divided the patients into pathological complete remission (pCR) and non-pCR groups. All patients underwent F-FDG PET/CT imaging before NAC treatment, and CT and PET images volume of interest (VOI) segmentation by manual segmentation and semi-automated absolute threshold segmentation, respectively. Then, feature extraction of VOI was performed with the pyradiomics package. A total of 630 models were created based on the source of radiomic features, the elimination of the batch effect approach, and the discretization method. The differences in data pre-processing approaches were compared and analyzed to identify the best-performing model, which was further tested by the permutation test.
A variety of data pre-processing methods contributed in varying degrees to the improvement of model effects. Among them, TLR radiomic features and Combat and Limma methods that eliminate batch effects could enhance the model prediction overall, and data discretization could be used as a potential method that can further optimize the model. A total of seven excellent models were selected and then based on the AUC of each model in the four test sets and their standard deviations, we selected the optimal model. The optimal model predicted AUC between 0.7 and 0.77 for the four test groups, with p-values less than 0.05 for the permutation test.
It is necessary to enhance the predictive effect of the model by eliminating confounding factors through data pre-processing. The model developed in this way is effective in predicting the efficacy of NAC for breast cancer.
基于肿瘤与肝脏比值（TLR）的放射组学特征和多种数据预处理方法，开发并验证一种用于乳腺癌新辅助化疗（NAC）疗效的 F-氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（F-FDG PET/CT）模型的预测价值。
本研究回顾性纳入了来自多个中心的 193 例乳腺癌患者。根据 NAC 的终点，我们将患者分为病理完全缓解（pCR）和非 pCR 组。所有患者在 NAC 治疗前均接受 F-FDG PET/CT 成像，分别通过手动分割和半自动绝对阈值分割对 CT 和 PET 图像进行感兴趣区（VOI）分割。然后，使用 pyradiomics 包对 VOI 进行特征提取。总共基于放射组学特征的来源、消除批次效应的方法和离散化方法创建了 630 个模型。比较和分析了不同的数据预处理方法，以确定表现最佳的模型，然后通过置换检验对其进行进一步测试。
多种数据预处理方法在不同程度上有助于提高模型效果。其中，TLR 放射组学特征和消除批次效应的 Combat 和 Limma 方法可以整体增强模型预测，数据离散化可以作为进一步优化模型的潜在方法。共选择了七个优秀的模型，然后基于每个模型在四个测试组中的 AUC 及其标准差，选择了最优模型。最优模型在四个测试组中的预测 AUC 在 0.7 到 0.77 之间，置换检验的 p 值均小于 0.05。
通过数据预处理消除混杂因素可以增强模型的预测效果。通过这种方式开发的模型可有效预测乳腺癌 NAC 的疗效。
