Zhao Endong, Yang Yun-Feng, Bai Miaomiao, Zhang Hao, Yang Yuan-Yuan, Song Xuelin, Lou Shiyun, Yu Yunxuan, Yang Chao
Department of Radiology, The First Affiliated Hospital of Dalian Medical University, Dalian, Liaoning, China.
Laboratory for Medical Imaging Informatics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China.
Front Med (Lausanne). 2024 Jun 27;11:1345162. doi: 10.3389/fmed.2024.1345162. eCollection 2024.
To investigate the value of interpretable machine learning model and nomogram based on clinical factors, MRI imaging features, and radiomic features to predict Ki-67 expression in primary central nervous system lymphomas (PCNSL).
MRI images and clinical information of 92 PCNSL patients were retrospectively collected, which were divided into 53 cases in the training set and 39 cases in the external validation set according to different medical centers. A 3D brain tumor segmentation model was trained based on nnU-NetV2, and two prediction models, interpretable Random Forest (RF) incorporating the SHapley Additive exPlanations (SHAP) method and nomogram based on multivariate logistic regression, were proposed for the task of Ki-67 expression status prediction.
The mean dice Similarity Coefficient (DSC) score of the 3D segmentation model on the validation set was 0.85. On the Ki-67 expression prediction task, the AUC of the interpretable RF model on the validation set was 0.84 (95% CI:0.81, 0.86; < 0.001), which was a 3% improvement compared to the AUC of the nomogram. The Delong test showed that the z statistic for the difference between the two models was 1.901, corresponding to a value of 0.057. In addition, SHAP analysis showed that the Rad-Score made a significant contribution to the model decision.
In this study, we developed a 3D brain tumor segmentation model and used an interpretable machine learning model and nomogram for preoperative prediction of Ki-67 expression status in PCNSL patients, which improved the prediction of this medical task.
Ki-67 represents the degree of active cell proliferation and is an important prognostic parameter associated with clinical outcomes. Non-invasive and accurate prediction of Ki-67 expression level preoperatively plays an important role in targeting treatment selection and patient stratification management for PCNSL thereby improving prognosis.
探讨基于临床因素、MRI成像特征和影像组学特征的可解释机器学习模型和列线图预测原发性中枢神经系统淋巴瘤（PCNSL）中Ki-67表达的价值。
回顾性收集92例PCNSL患者的MRI图像和临床信息，根据不同医疗中心将其分为训练集53例和外部验证集39例。基于nnU-NetV2训练了一个3D脑肿瘤分割模型，并提出了两个预测模型，即结合SHapley加性解释（SHAP）方法的可解释随机森林（RF）模型和基于多变量逻辑回归的列线图，用于Ki-67表达状态预测任务。
3D分割模型在验证集上的平均骰子相似系数（DSC）得分是0.85。在Ki-67表达预测任务中，可解释RF模型在验证集上的AUC为0.84（95%CI：0.81，0.86；P<0.001），与列线图的AUC相比提高了3%。Delong检验显示，两个模型之间差异的z统计量为1.901，对应P值为0.057。此外，SHAP分析表明Rad-Score对模型决策有显著贡献。
在本研究中，我们开发了一个3D脑肿瘤分割模型，并使用可解释机器学习模型和列线图对PCNSL患者的Ki-67表达状态进行术前预测，改进了该医学任务的预测。
Ki-67代表细胞增殖活性程度，是与临床结局相关的重要预后参数。术前非侵入性准确预测Ki-67表达水平对PCNSL的靶向治疗选择和患者分层管理具有重要作用，从而改善预后。
