Liu J, Tu J, Yao L, Peng L, Fang R, Lu Y, He F, Xiong J, Li Y
Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China.
State Key Laboratory of Genetic Engineering, Human Phenome Institute, School of Life Sciences, Fudan University, Shanghai, China.
Clin Radiol. 2025 Jan;80:106746. doi: 10.1016/j.crad.2024.106746. Epub 2024 Nov 8.
To establish a machine learning model based on a radiomic signature for predicting B-cell lymphoma 6 (BCL-6) rearrangement in primary central nervous system lymphoma (PCNSL).
Retrospective study on 102 PCNSL patients (31 with BCL-6 rearrangement positive, 71 with BCL-6 rearrangement negative) were randomly divided into the training and validation sets at a ratio of 7:3. Radiomics models based on contrast-enhanced T1-weighted imaging (CE-T1WI) and fluid-attenuated inversion recovery (FLAIR) in different regions, including VOI and VOI Radiomics features were extracted and selected using LASSO regression, and radiomics score (rad-score) were calculated using the weighted coefficients. Four machine learning models (logistic regression, random forest, support vector machine, K-nearest neighbours) were developed and evaluated based on rad-score. The optimal radiomics model was integrated into the clinical or radiological factors to construct a predictive model through logistic regression analysis. A nomogram was constructed based on independent significant features for individualised prediction.
All rad-scores based on CE-T1WI and FLAIR sequences were significantly associated with BCL6 rearrangement (p < 0.05) in univariate regression analysis. The logistic regression machine learning model performed best with AUCs of 0.935 (training) and 0.923 (validation). Rad-scores from CE-T1WI tumour core and peritumoural oedema were independent significant predictors.
Radiomics signatures based on CE-T1WI and FLAIR sequences have significant value in distinguishing BCL6 rearrangement. The CE-T1WI radiomics model based on VOI and VOI are robust markers for identifying BCL6 rearrangement.
建立基于放射组学特征的机器学习模型，用于预测原发性中枢神经系统淋巴瘤（PCNSL）中的B细胞淋巴瘤6（BCL-6）重排。
对102例PCNSL患者（31例BCL-6重排阳性，71例BCL-6重排阴性）进行回顾性研究，以7:3的比例随机分为训练集和验证集。基于不同区域的对比增强T1加权成像（CE-T1WI）和液体衰减反转恢复序列（FLAIR）构建放射组学模型，包括感兴趣体积（VOI）和VOI。使用最小绝对收缩和选择算子（LASSO）回归提取并选择放射组学特征，并使用加权系数计算放射组学评分（rad-score）。基于rad-score开发并评估了四种机器学习模型（逻辑回归、随机森林、支持向量机、K近邻）。将最佳放射组学模型与临床或放射学因素相结合，通过逻辑回归分析构建预测模型。基于独立显著特征构建列线图进行个体化预测。
在单变量回归分析中，基于CE-T1WI和FLAIR序列的所有rad-score均与BCL6重排显著相关（p<0.05）。逻辑回归机器学习模型表现最佳，训练集和验证集的曲线下面积（AUC）分别为0.935和0.923。CE-T1WI肿瘤核心和瘤周水肿的rad-score是独立的显著预测因子。
基于CE-T1WI和FLAIR序列的放射组学特征在区分BCL6重排方面具有重要价值。基于VOI和VOI的CE-T1WI放射组学模型是识别BCL6重排的可靠标志物。
