Purpose

To evaluate if a machine learning prediction model based on clinical and easily assessable imaging features derived from baseline breast [¹⁸F]FDG-PET/MRI staging can predict pathologic complete response (pCR) in patients with newly diagnosed breast cancer prior to neoadjuvant system therapy (NAST).

Methods

Altogether 143 women with newly diagnosed breast cancer (54 ± 12 years) were retrospectively enrolled. All women underwent a breast [¹⁸F]FDG-PET/MRI, a histopathological workup of their breast cancer lesions and evaluation of clinical data. Fifty-six features derived from positron emission tomography (PET), magnetic resonance imaging (MRI), sociodemographic / anthropometric, histopathologic as well as clinical data were generated and used as input for an extreme Gradient Boosting model (XGBoost) to predict pCR. The model was evaluated in a five-fold nested-cross-validation incorporating independent hyper-parameter tuning within the inner loops to reduce the risk of overoptimistic estimations. Diagnostic model-performance was assessed by determining the area under the curve of the receiver operating characteristics curve (ROC-AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Furthermore, feature importances of the XGBoost model were evaluated to assess which features contributed most to distinguish between pCR and non-pCR.

Results

Nested-cross-validation yielded a mean ROC-AUC of 80.4 ± 6.0% for prediction of pCR. Mean sensitivity, specificity, PPV, and NPV of 54.5 ± 21.3%, 83.6 ± 4.2%, 63.6 ± 8.5%, and 77.6 ± 8.1% could be achieved. Histopathological data were the most important features for classification of the XGBoost model followed by PET, MRI, and sociodemographic/anthropometric features.

Conclusion

The evaluated multi-source XGBoost model shows promising results for reliably predicting pathological complete response in breast cancer patients prior to NAST. However, yielded performance is yet insufficient to be implemented in the clinical decision-making process.

中文翻译：

---

基于临床数据和来自乳腺 [18F]FDG-PET/MRI 的成像数据，通过机器学习预测乳腺癌患者的治疗反应

目的

评估基于来自基线乳腺 [ ¹⁸ F]FDG-PET/MRI 分期的临床和易于评估的成像特征的机器学习预测模型是否可以预测新辅助系统治疗前新诊断乳腺癌患者的病理完全缓解 (pCR) （纳斯）。

方法

总共 143 名新诊断乳腺癌的女性（54±12 岁）被回顾性纳入。所有女性均接受了乳房 [ ¹⁸ F]FDG-PET/MRI 检查、乳腺癌病变的组织病理学检查和临床数据评估。生成了源自正电子发射断层扫描 (PET)、磁共振成像 (MRI)、社会人口学/人体测量学、组织病理学以及临床数据的 56 个特征，并将其用作极端梯度增强模型 (XGBoost) 的输入来预测 pCR。该模型通过五重嵌套交叉验证进行评估，在内循环中结合独立的超参数调整，以降低过度乐观估计的风险。通过确定受试者工作特征曲线（ROC-AUC）的曲线下面积、敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和准确性来评估诊断模型性能。此外，还评估了 XGBoost 模型的特征重要性，以评估哪些特征对区分 pCR 和非 pCR 贡献最大。

结果

嵌套交叉验证预测 pCR 的平均 ROC-AUC 为 80.4 ± 6.0%。平均灵敏度、特异性、PPV 和 NPV 分别为 54.5 ± 21.3%、83.6 ± 4.2%、63.6 ± 8.5% 和 77.6 ± 8.1%。组织病理学数据是 XGBoost 模型分类的最重要特征，其次是 PET、MRI 和社会人口学/人体测量特征。

结论

经评估的多源 XGBoost 模型显示出在 NAST 之前可靠预测乳腺癌患者病理完全缓解的良好结果。然而，所产生的性能还不足以在临床决策过程中实施。