Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, No. 3 East Qingchun Road, Hangzhou, 310016, Zhejiang Province, China.
Eur Radiol. 2023 Jan;33(1):1-10. doi: 10.1007/s00330-022-08952-8. Epub 2022 Jun 21.
To investigate the feasibility and efficacy of a deep-learning (DL)-based three-dimensional (3D) super-resolution (SR) MRI radiomics model for preoperative T-staging prediction in rectal cancer (RC).
Seven hundred six eligible RC patients (T1/2 = 287, T3/4 = 419) were retrospectively enrolled in this study and chronologically allocated into a training cohort (n = 565) and a validation cohort (n = 141). We conducted a deep-transfer-learning network on high-resolution (HR) T2-weighted imaging (T2WI) to enhance the z-resolution of the images and acquired the preoperative SRT2WI. The radiomics models named model and model were respectively constructed with high-dimensional quantitative features extracted from manually segmented volume of interests of HRT2WI and SRT2WI through the Least Absolute Shrinkage and Selection Operator method. The performances of the models were evaluated by ROC, calibration, and decision curves.
Model outperformed model (AUC 0.869, sensitivity 71.1%, specificity 93.1%, and accuracy 83.3% vs. AUC 0.810, sensitivity 89.5%, specificity 70.1%, and accuracy 77.3%) in distinguishing T1/2 and T3/4 RC with significant difference (p < 0.05). Both radiomics models achieved higher AUCs than the expert radiologists (0.685, 95% confidence interval 0.595-0.775, p < 0.05). The calibration curves confirmed high goodness of fit, and the decision curve analysis revealed the clinical value.
Model yielded superior predictive performance in preoperative RC T-staging by comparison with model and expert radiologists' visual assessments.
• For the first time, DL-based 3D SR images were applied in radiomics analysis for clinical utility. • Compared with the visual assessment of expert radiologists and the conventional radiomics model based on HRT2WI, the SR radiomics model showed a more favorable capability in helping clinicians assess the invasion depth of RC preoperatively. • This is the largest radiomics study for T-staging prediction in RC.
探究基于深度学习（DL）的三维（3D）超分辨率（SR）磁共振成像（MRI）放射组学模型在直肠癌（RC）术前 T 分期预测中的可行性和效能。
本研究回顾性纳入 706 例符合条件的 RC 患者（T1/2 期=287 例，T3/4 期=419 例），按时间顺序分为训练队列（n=565）和验证队列（n=141）。我们对高分辨率（HR）T2 加权成像（T2WI）进行深度迁移学习网络处理，以提高图像的 z 分辨率，并获取术前短反转时间反转恢复（SRT）WI。通过最小绝对值收缩和选择算子方法，从手动分割 HR T2WI 和 SRT2WI 的感兴趣区提取高维定量特征，分别构建放射组学模型和模型。通过 ROC、校准和决策曲线评估模型的性能。
模型在区分 T1/2 期和 T3/4 期 RC 方面的表现优于模型（AUC 0.869、敏感度 71.1%、特异度 93.1%和准确率 83.3% vs. AUC 0.810、敏感度 89.5%、特异度 70.1%和准确率 77.3%），差异有统计学意义（p<0.05）。放射组学模型的 AUC 均高于专家放射科医生（0.685，95%置信区间 0.595-0.775，p<0.05）。校准曲线证实了良好的拟合度，决策曲线分析显示了其临床价值。
与专家放射科医生的视觉评估和常规基于 HR T2WI 的放射组学模型相比，模型在 RC 术前 T 分期预测中具有更好的预测性能。
首次将基于深度学习的 3D SR 图像应用于放射组学分析，以评估其临床应用价值。
与专家放射科医生的视觉评估和常规基于 HR T2WI 的放射组学模型相比，SR 放射组学模型在帮助临床医生术前评估 RC 侵袭深度方面表现出更优的能力。
这是 RC 术前 T 分期预测中规模最大的放射组学研究。
Zotero 插件
