Department of Urology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
Department of Urology, Wuxi Medical Center, Nanjing Medical University, Wuxi, China.
J Magn Reson Imaging. 2024 Dec;60(6):2694-2704. doi: 10.1002/jmri.29342. Epub 2024 Mar 8.
The human epidermal growth factor receptor 2 (HER2) has recently emerged as hotspot in targeted therapy for urothelial bladder cancer (UBC). The HER2 status is mainly identified by immunohistochemistry (IHC), preoperative and noninvasive methods for determining HER2 status in UBC remain in searching.
To investigate whether radiomics features extracted from MRI using machine learning algorithms can noninvasively evaluate the HER2 status in UBC.
Retrospective.
One hundred ninety-five patients (age: 68.7 ± 10.5 years) with 14.3% females from January 2019 to May 2023 were divided into training (N = 156) and validation (N = 39) cohorts, and 43 patients (age: 67.1 ± 13.1 years) with 13.9% females from June 2023 to January 2024 constituted the test cohort (N = 43).
FIELD STRENGTH/SEQUENCE: 3 T, T2-weighted imaging (turbo spin-echo), diffusion-weighted imaging (breathing-free spin echo).
The HER2 status were assessed by IHC. Radiomics features were extracted from MRI images. Pearson correlation coefficient and the least absolute shrinkage and selection operator (LASSO) were applied for feature selection, and six machine learning models were established with optimal features to identify the HER2 status in UBC.
Mann-Whitney U-test, chi-square test, LASSO algorithm, receiver operating characteristic analysis, and DeLong test.
Three thousand forty-five radiomics features were extracted from each lesion, and 22 features were retained for analysis. The Support Vector Machine model demonstrated the best performance, with an AUC of 0.929 (95% CI: 0.888-0.970) and accuracy of 0.859 in the training cohort, AUC of 0.886 (95% CI: 0.780-0.993) and accuracy of 0.846 in the validation cohort, and AUC of 0.712 (95% CI: 0.535-0.889) and accuracy of 0.744 in the test cohort.
MRI-based radiomics features combining machine learning algorithm provide a promising approach to assess HER2 status in UBC noninvasively and preoperatively.
2 TECHNICAL EFFICACY: Stage 3.
人表皮生长因子受体 2（HER2）最近成为尿路上皮膀胱癌（UBC）靶向治疗的热点。HER2 状态主要通过免疫组织化学（IHC）确定，术前和非侵入性方法仍在探索中。
研究使用机器学习算法从 MRI 中提取的放射组学特征是否可以无创评估 UBC 中的 HER2 状态。
回顾性。
本研究纳入了 195 名患者（年龄：68.7±10.5 岁），其中 14.3%为女性，来自 2019 年 1 月至 2023 年 5 月，分为训练（N=156）和验证（N=39）队列，以及 2023 年 6 月至 2024 年 1 月的 43 名患者（年龄：67.1±13.1 岁），其中 13.9%为女性，构成测试队列（N=43）。
磁场强度/序列：3T，T2 加权成像（涡轮自旋回波），弥散加权成像（自由呼吸自旋回波）。
HER2 状态通过 IHC 评估。从 MRI 图像中提取放射组学特征。应用 Pearson 相关系数和最小绝对值收缩和选择算子（LASSO）进行特征选择，并使用最佳特征建立六个机器学习模型，以识别 UBC 中的 HER2 状态。
Mann-Whitney U 检验、卡方检验、LASSO 算法、受试者工作特征分析和 DeLong 检验。
从每个病变中提取了 3045 个放射组学特征，保留了 22 个特征进行分析。支持向量机模型表现最佳，在训练队列中的 AUC 为 0.929（95%CI：0.888-0.970）和准确率为 0.859，在验证队列中的 AUC 为 0.886（95%CI：0.780-0.993）和准确率为 0.846，在测试队列中的 AUC 为 0.712（95%CI：0.535-0.889）和准确率为 0.744。
基于 MRI 的放射组学特征结合机器学习算法为无创和术前评估 UBC 中的 HER2 状态提供了一种有前途的方法。
2 级，技术功效：3 级。
