文献速递骨肌MR

深度学习影像组学模型预测后路腰椎椎间融合术疗效的研究

A Study on Predicting the Efficacy of Posterior Lumbar Interbody Fusion Surgery Using a Deep Learning Radiomics Model.
PubMed 文献 · Acad Radiol · 2025-05-30

本研究回顾性纳入461例因退行性腰椎疾病行PLIF手术的患者,按8:2分为训练集(n=368)和测试集(n=93),基于矢状位T2WI提取影像组学和深度学习特征,构建临床、影像组学、深度学习及联合模型预测手术疗效。联合模型在测试集AUC为0.866(95%CI:0.778-0.955),优于各单一模型;基于10mm掩膜扩展的影像组学模型测试集AUC为0.749(95%CI:0.631-0.866),深度学习模型测试集AUC为0.803(95%CI:0.705-0.902)。

要点

  • 联合临床、影像组学和深度学习特征的模型对PLIF术后疗效预测性能最佳(测试集AUC=0.866)。
  • 深度学习模型在单一模型中预测性能最好(测试集AUC=0.803),优于影像组学模型。
  • 影像组学模型采用矢状位T2WI ROI外扩10mm掩膜时测试集AUC为0.749。

诊断标准与关键数值

  • 影像组学模型(基于MRI ROI外扩10mm掩膜)训练集AUC=0.814(95%CI:0.761-0.866),测试集AUC=0.749(95%CI:0.631-0.866)。
  • 深度学习模型训练集AUC=0.995(95%CI:0.991-0.999),测试集AUC=0.803(95%CI:0.705-0.902)。
  • 联合模型训练集AUC=0.993(95%CI:0.987-0.999),测试集AUC=0.866(95%CI:0.778-0.955)。
  • 临床特征中患者年龄、体重及手术节段术前椎间距离是影响融合结局的危险因素。

局限性

  • 单中心回顾性研究,样本来源单一,可能存在选择偏倚。
  • 训练集与测试集AUC差异较大,深度学习模型训练集AUC高达0.995,提示可能存在过拟合。
  • 掩膜扩展程度仅探索至10mm,未报告其他扩展程度的具体结果。

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

RATIONALE AND OBJECTIVES: This study seeks to develop a combined model integrating clinical data, radiomics, and deep learning (DL) for predicting the efficacy of posterior lumbar interbody fusion (PLIF) surgery.

MATERIALS AND METHODS: A retrospective review was conducted on 461 patients who underwent PLIF for degenerative lumbar diseases. These patients were partitioned into a training set (n=368) and a test set (n=93) in an 8:2 ratio. Clinical models, radiomics models, and DL models were constructed based on logistic regression and random forest, respectively. A combined model was established by integrating these three models. All radiomics and DL features were extracted from sagittal T2-weighted images using 3D slicer software. The least absolute shrinkage and selection operator method selected the optimal radiomics and DL features to build the models. In addition to analyzing the original region of interest (ROI), we also conducted different degrees of mask expansion on the ROI to determine the optimal ROI. The performance of the model was evaluated by using the receiver operating characteristic curve (ROC) and the area under the ROC curve. The differences in AUC were compared by DeLong test.

RESULTS: Among the clinical characteristics, patient age, body weight, and preoperative intervertebral distance at the surgical segment are risk factors affecting the fusion outcome. The radiomics model based on MRI with expanded 10 mm mask showed excellent performance (training set AUC=0.814, 95% CI: (0.761-0.866); test set AUC=0.749, 95% CI: [0.631-0.866]). Among all single models, the DL model had the best diagnostic prediction performance, with AUC values of (0.995, 95% CI: [0.991-0.999]) for the training set and (0.803, 95% CI: [0.705-0.902]) for the test set. Compared to all the models, the combined model of clinical features, radiomics features, and DL features had the best diagnostic prediction performance, with AUC values of (0.993, 95% CI: [0.987-0.999]) for the training set and (0.866, 95% CI: [0.778-0.955]) for the test set.

CONCLUSION: The proposed clinical feature-deep learning radiomics model can effectively predict the postoperative efficacy of patients undergoing PLIF surgery and has good clinical applicability.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Fang L, Pan Y, Zheng H, et al. A Study on Predicting the Efficacy of Posterior Lumbar Interbody Fusion Surgery Using a Deep Learning Radiomics Model. Acad Radiol. 2025. PMID: 40450398. doi:10.1016/j.acra.2025.05.026

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。