Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients.
Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients.
复制标题
基于放射素学的机器学习模型，用于预测稀有癌症的整体和无进展生存：原发性中枢神经系统淋巴瘤患者的案例研究。
DOI：
10.3390/bioengineering10030285
复制
发表时间：
2023-02-22
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
原发性中枢神经系统淋巴瘤（PCNSL）是一种预后不良的侵袭性肿瘤。尽管治疗进展显著提高了总生存率（OS），但许多患者对基于hd - mtx的化疗没有反应（15-25%）或在初始反应后复发（25-50%）。这种治疗不良反应背后的原因尚不清楚。因此，迫切需要开发改进的PCNSL预测模型。在这项研究中，我们研究了放射组学特征是否可以改善PCNSL患者的预后预测。共有80名确诊为PCNSL的患者入组。选取具有完整磁共振成像（MRI）序列的患者亚组进行分层分析。在放射组学特征提取和选择之后，对不同的机器学习（ML）模型进行OS和无进展生存（PFS）预测测试。为了评估所选特征的稳定性，使用23例患者在三个不同时间点扫描的图像来计算类间相关系数（ICC），并评估原始图像和归一化图像中每个特征的可重复性。从z分数归一化图像中提取的特征明显比从非归一化图像中提取的特征更稳定，平均改善约38% （p值<）。ROC曲线下面积（AUC）显示，基于放射组学的预测优于基于当前临床预后因素的预测，OS和PFS分别提高了23%和50%。这些结果表明，从归一化MR图像中提取放射组学特征可以改善PCNSL患者的预后分层，并为进一步研究其在驱动治疗选择方面的潜在作用铺平了道路。
Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of patients do not respond to HD–MTX-based chemotherapy (15–25%) or experience relapse (25–50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (p-value < ). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.
登录
查看更多内容
影响因子：
15.9
作者：
Barajas RF;Politi LS;Anzalone N;Schöder H;Fox CP;Boxerman JL;Kaufmann TJ;Quarles CC;Ellingson BM;Auer D;Andronesi OC;Ferreri AJM;Mrugala MM;Grommes C;Neuwelt EA;Ambady P;Rubenstein JL;Illerhaus G;Nagane M;Batchelor TT;Hu LS
通讯作者：
Hu LS
影响因子：
9.9
作者：
Houillier, Caroline;Soussain, Carole;Gyan, Emmanuel
通讯作者：
Gyan, Emmanuel
DOI：
10.1148/ryai.2020190199
发表时间：
2021-01-01
期刊：
RADIOLOGY-ARTIFICIAL INTELLIGENCE
影响因子：
--
作者：
Hoebel, Katharina, V;Patel, Jay B.;Kalpathy-Cramer, Jayashree
通讯作者：
Kalpathy-Cramer, Jayashree
影响因子：
24.7
作者：
Ferreri, Andres J. M.;Cwynarski, Kate;Illerhaus, Gerald
通讯作者：
Illerhaus, Gerald
影响因子：
--
作者：
Chen, Chaoyue;Zhuo, Hongyu;Ma, Xuelei
通讯作者：
Ma, Xuelei