基于磁共振成像（MRI）的影像组学作为一种生物标志物，通过预测前列腺癌从活检到根治性前列腺切除术的升级来指导治疗。
Radiomics Based on MRI as a Biomarker to Guide Therapy by Predicting Upgrading of Prostate Cancer From Biopsy to Radical Prostatectomy.
作者信息
Zhang Gu-Mu-Yang, Han Yu-Qi, Wei Jing-Wei, Qi Ya-Fei, Gu Dong-Sheng, Lei Jing, Yan Wei-Gang, Xiao Yu, Xue Hua-Dan, Feng Feng, Sun Hao, Jin Zheng-Yu, Tian Jie
机构信息
Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, China.
School of Life Science and Technology, Xidian University, Xi'an, China.
出版信息
J Magn Reson Imaging. 2020 Oct;52(4):1239-1248. doi: 10.1002/jmri.27138. Epub 2020 Mar 17.
BACKGROUND
Biopsy Gleason score (GS) is crucial for prostate cancer (PCa) treatment decision-making. Upgrading in GS from biopsy to radical prostatectomy (RP) puts a proportion of patients at risk of undertreatment.
PURPOSE
To develop and validate a radiomics model based on multiparametric magnetic resonance imaging (mp-MRI) to predict PCa upgrading.
STUDY TYPE
Retrospective, radiomics.
POPULATION
A total of 166 RP-confirmed PCa patients (training cohort, n = 116; validation cohort, n = 50) were included.
FIELD STRENGTH/SEQUENCE: 3.0T/T -weighted (T W), apparent diffusion coefficient (ADC), and dynamic contrast enhancement (DCE) sequences.
ASSESSMENT
PI-RADSv2 score for each tumor was recorded. Radiomic features were extracted from T W, ADC, and DCE sequences and Mutual Information Maximization criterion was used to identify the optimal features on each sequence. Multivariate logistic regression analysis was used to develop predictive models and a radiomics nomogram and their performance was evaluated.
STATISTICAL TESTS
Student's t or chi-square were used to assess the differences in clinicopathologic data between the training and validation cohorts. Receiver operating characteristic (ROC) curve analysis was performed and the area under the curve (AUC) was calculated.
RESULTS
In PI-RADSv2 assessment, 67 lesions scored 5, 70 lesions scored 4, and 29 lesions scored 3. For each sequence, 4404 features were extracted and the top 20 best features were selected. The radiomics model incorporating signatures from the three sequences achieved better performance than any single sequence (AUC: radiomics model 0.868, T W 0.700, ADC 0.759, DCE 0.726). The combined mode incorporating radiomics signature, clinical stage, and time from biopsy to RP outperformed the clinical model and radiomics model (AUC: combined model 0.910, clinical model 0.646, radiomics model 0.868). The nomogram showed good performance (AUC 0.910) and calibration (P-values: training cohort 0.624, validation cohort 0.294).
DATA CONCLUSION
Radiomics based on mp-MRI has potential to predict upgrading of PCa from biopsy to RP.
LEVEL OF EVIDENCE
3 TECHNICAL EFFICACY: Stage 5 J. Magn. Reson. Imaging 2020;52:1239-1248.
背景
活检 Gleason 评分（GS）对于前列腺癌（PCa）治疗决策至关重要。从活检到根治性前列腺切除术（RP）过程中 GS 的升级会使一部分患者面临治疗不足的风险。
目的
开发并验证一种基于多参数磁共振成像（mp-MRI）的放射组学模型，以预测 PCa 的升级情况。
研究类型
回顾性放射组学研究。
研究对象
共纳入 166 例经 RP 确诊的 PCa 患者（训练队列，n = 116；验证队列，n = 50）。
场强/序列：3.0T/T2加权（T2W）、表观扩散系数（ADC）和动态对比增强（DCE）序列。
评估
记录每个肿瘤的 PI-RADSv2 评分。从 T2W、ADC 和 DCE 序列中提取放射组学特征，并使用互信息最大化标准确定每个序列上的最佳特征。采用多变量逻辑回归分析建立预测模型和放射组学列线图，并评估其性能。
统计检验
采用 Student's t 检验或卡方检验评估训练队列和验证队列之间临床病理数据的差异。进行受试者操作特征（ROC）曲线分析并计算曲线下面积（AUC）。
结果
在 PI-RADSv2 评估中，67 个病灶评分为 5 分，70 个病灶评分为 4 分，29 个病灶评分为 3 分。对于每个序列，提取了 4404 个特征，并选择了前 20 个最佳特征。结合三个序列特征的放射组学模型比任何单个序列表现更好（AUC：放射组学模型 0.868，T2W 0.700，ADC 0.759，DCE 0.726）。结合放射组学特征、临床分期以及从活检到 RP 的时间的联合模型优于临床模型和放射组学模型（AUC：联合模型 0.910，临床模型 0.646，放射组学模型 0.868）。列线图表现良好（AUC 0.910）且具有良好的校准度（P 值：训练队列 0.624，验证队列 0.294）。
数据结论
基于 mp-MRI 的放射组学有潜力预测 PCa 从活检到 RP 的升级情况。
证据水平
3 级 技术效能：5 级 《磁共振成像杂志》2020 年；52:1239 - 1248。
Zotero 插件