Department of Radiation Oncology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Department of Radiological Sciences, University of California, Irvine, CA, USA.
Magn Reson Imaging. 2019 Sep;61:33-40. doi: 10.1016/j.mri.2019.05.003. Epub 2019 May 3.
To predict the neoadjuvant chemoradiation therapy (CRT) response in patients with locally advanced rectal cancer (LARC) using radiomics and deep learning based on pre-treatment MRI and a mid-radiation follow-up MRI taken 3-4 weeks after the start of CRT.
A total of 51 patients were included, 45 with pre-treatment, 41 with mid-radiation therapy (RT), and 35 with both MRI sets. The multi-parametric MRI protocol included T2, diffusion weighted imaging (DWI) with b-values of 0 and 800 s/mm, and dynamic-contrast-enhanced (DCE) MRI. After completing CRT and surgery, the specimen was examined to determine the pathological response based on the tumor regression grade. The tumor ROI was manually drawn on the post-contrast image and mapped to other sequences. The total tumor volume and mean apparent diffusion coefficient (ADC) were measured. Radiomics using GLCM texture and histogram parameters, and deep learning using a convolutional neural network (CNN), were performed to differentiate pathologic complete response (pCR) vs. non-pCR, and good response (GR) vs. non-GR.
Tumor volume decreased and ADC increased significantly in the mid-RT MRI compared to the pre-treatment MRI. For predicting pCR vs. non-pCR, combining ROI and radiomics features achieved an AUC of 0.80 for pre-treatment, 0.82 for mid-RT, and 0.86 for both MRI together. For predicting GR vs. non-GR, the AUC was 0.91 for pre-treatment, 0.92 for mid-RT, and 0.93 for both MRI together. In deep learning using CNN, combining pre-treatment and mid-RT MRI achieved a higher accuracy compared to using either dataset alone, with AUC of 0.83 for predicting pCR vs. non-pCR.
Radiomics based on pre-treatment and early follow-up multi-parametric MRI in LARC patients receiving CRT could extract comprehensive quantitative information to predict final pathologic response.
利用基于预处理 MRI 和 CRT 开始后 3-4 周进行的中期放疗随访 MRI 的放射组学和深度学习，预测局部晚期直肠癌（LARC）患者的新辅助放化疗（CRT）反应。
共纳入 51 例患者，45 例患者有预处理 MRI，41 例患者有中期放疗 MRI，35 例患者同时有这两种 MRI 数据集。多参数 MRI 方案包括 T2、扩散加权成像（DWI），b 值为 0 和 800s/mm2，以及动态对比增强（DCE）MRI。完成 CRT 和手术后，根据肿瘤消退分级对标本进行检查，以确定病理反应。在对比后图像上手动绘制肿瘤 ROI，并将其映射到其他序列。测量总肿瘤体积和平均表观扩散系数（ADC）。使用 GLCM 纹理和直方图参数进行放射组学分析，以及使用卷积神经网络（CNN）进行深度学习，以区分病理完全缓解（pCR）与非 pCR，以及良好缓解（GR）与非 GR。
与预处理 MRI 相比，中期 RT MRI 中的肿瘤体积减小，ADC 增加。对于预测 pCR 与非 pCR，结合 ROI 和放射组学特征，预处理 MRI 的 AUC 为 0.80，中期 RT MRI 的 AUC 为 0.82，两种 MRI 结合的 AUC 为 0.86。对于预测 GR 与非 GR，预处理 MRI 的 AUC 为 0.91，中期 RT MRI 的 AUC 为 0.92，两种 MRI 结合的 AUC 为 0.93。在使用 CNN 的深度学习中，与单独使用任何一个数据集相比，结合预处理和中期 RT MRI 可获得更高的准确性，预测 pCR 与非 pCR 的 AUC 为 0.83。
在接受 CRT 的 LARC 患者中，基于预处理和早期随访多参数 MRI 的放射组学可以提取全面的定量信息，以预测最终的病理反应。
