表观扩散系数图纹理特征在预测肌层浸润性膀胱癌放化疗反应中的价值
回顾性分析45例肌层浸润性膀胱癌患者,在放化疗前1.5T MRI的ADC图上提取纹理特征,用随机森林和支持向量机建模预测病理完全缓解。23例达病理完全缓解,所选特征包括ADC第一四分位数、灰度共生矩阵相关性和同质性;支持向量机模型AUC为0.96,优于平均ADC值的0.76。
要点
- ADC图纹理特征(第一四分位数ADC、GLCM相关性、GLCM同质性)与放化疗后病理完全缓解相关。
- 支持向量机模型预测放化疗反应的AUC为0.96(95%CI 0.91-1.00),优于平均ADC值的0.76。
- 纹理分析可能作为影像生物标志物优化肌层浸润性膀胱癌放化疗患者选择。
核心结论
- ADC图纹理特征可作为预测肌层浸润性膀胱癌放化疗敏感性的影像生物标志物,纹理分析可能优化患者选择。
研究设计与样本
- 回顾性研究,纳入45例肌层浸润性膀胱癌患者,均在接受放化疗后行膀胱切除术;以膀胱切除标本的组织学评估为参考标准判断放化疗反应;两名放射科医师在治疗前1.5T MRI的ADC图上确定指标病灶的感兴趣体积,使用LIFEx软件进行纹理分析。
关键影像表现/征象
- 达到病理完全缓解的患者第一四分位数ADC值为0.66×10-3 mm2/s,未达到者为0.81×10-3 mm2/s,两组差异有统计学意义(p<0.05)。
- 达到病理完全缓解的患者GLCM相关性为0.53,未达到者为0.70,两组差异有统计学意义(p<0.05)。
- 特征选择确定第一四分位数ADC、GLCM相关性和GLCM同质性为预测放化疗反应的重要特征。
诊断标准与关键数值
- 随机森林模型纳入所选纹理特征,预测放化疗反应的AUC为0.82(95%CI 0.67-0.97)。
- 支持向量机模型纳入所选纹理特征,预测放化疗反应的AUC为0.96(95%CI 0.91-1.00)。
- 平均ADC值预测放化疗反应的AUC为0.76(95%CI 0.61-0.90);支持向量机模型AUC优于平均ADC值(p=0.0037)。
临床应用与阅片要点
- 治疗前1.5T MRI的ADC图纹理分析可用于预测肌层浸润性膀胱癌放化疗后的病理完全缓解。
- 第一四分位数ADC、GLCM相关性和GLCM同质性是需要关注的重要纹理特征。
- 支持向量机模型在预测放化疗反应方面表现出较高性能,可能有助于优化患者选择。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: To examine the usefulness of the texture analysis (TA) of apparent diffusion coefficient (ADC) maps in predicting the chemoradiotherapy (CRT) response of muscle-invasive bladder cancer (MIBC).
METHODS: We reviewed 45 MIBC patients who underwent cystectomy after CRT. CRT response was assessed through histologic evaluation of cystectomy specimens. Two radiologists determined the volume of interest for the index lesions on ADC maps of pretherapeutic 1.5-T MRI and performed TA using the LIFEx software. Forty-six texture features (TFs) were selected based on their contribution to the prediction of CRT sensitivity. To evaluate diagnostic performance, diagnostic models from the selected TFs were created using random forest (RF) and support vector machine (SVM), respectively.
RESULTS: Twenty-three patients achieved pathologic complete response (pCR) to CRT. The feature selection identified first quartile ADC (Q1 ADC), gray-level co-occurrence matrix (GLCM) correlation, and GLCM homogeneity as important in predicting CRT response. Patients who achieved pCR showed significantly lower Q1 ADC and GLCM correlation values (0.66 × 10-3 mm2/s and 0.53, respectively) than those who did not (0.81 × 10-3 mm2/s and 0.70, respectively; p < 0.05 for both). The AUCs of the RF and SVM models incorporating the selected TFs were 0.82 (95% confidence interval [CI]: 0.67-0.97) and 0.96 (95% CI: 0.91-1.00), respectively, and the AUC of the SVM model was better than that of the mean ADC value (0.76, 95% CI: 0.61-0.90; p = 0.0037).
CONCLUSION: TFs can serve as imaging biomarkers in MIBC patients for predicting CRT sensitivity. TAs of ADC maps can potentially optimize patient selection for CRT.
KEY POINTS: • Texture analysis of ADC maps and feature selection identified important texture features for classifying pathologic tumor response in patients with muscle-invasive bladder cancer. • The machine learning model incorporating the texture features set, which included first quartile ADC, GLCM correlation, and GLCM homogeneity, showed high performance in predicting chemoradiotherapy response. • Texture features could serve as imaging biomarkers that optimize eligible patient selection for chemoradiotherapy in muscle-invasive bladder cancer.
引用
- Kimura K, Yoshida S, Tsuchiya J, et al. Usefulness of texture features of apparent diffusion coefficient maps in predicting chemoradiotherapy response in muscle-invasive bladder cancer. Eur Radiol. 2021. PMID: 34120230. doi:10.1007/s00330-021-08110-6
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。