Department of Radiology, The Second Xiangya Hospital of Central South University, 139 Renming Middle Road, Changsha, Hunan, China.
Division of Interventional Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania.
J Vasc Interv Radiol. 2020 Jun;31(6):1010-1017.e3. doi: 10.1016/j.jvir.2019.11.032. Epub 2020 May 4.
To develop and validate a deep learning model based on routine magnetic resonance (MR) imaging obtained before uterine fibroid embolization to predict procedure outcome.
Clinical data were collected on patients treated with uterine fibroid embolization at the Hospital of the University of Pennsylvania from 2007 to 2018. Fibroids for each patient were manually segmented by an abdominal radiologist on a T1-weighted contrast-enhanced (T1C) sequence and a T2-weighted sequence of MR imaging obtained before and after embolization. A residual convolutional neural network (ResNet) model to predict clinical outcome was trained using MR imaging obtained before the procedure.
Inclusion criteria were met by 727 fibroids in 409 patients. At clinical follow-up, 85.6% (n = 350) of 409 patients (590 of 727 fibroids; 81.1%) experienced symptom resolution or improvement, and 14.4% (n = 59) of 409 patients (137 of 727 fibroids; 18.9%) had no improvement or worsening symptoms. The T1C trained model achieved a test accuracy of 0.847 (95% confidence interval [CI], 0.745-0.914), sensitivity of 0.932 (95% CI, 0.833-0.978), and specificity of 0.462 (95% CI, 0.232-0.709). In comparison, the average of 4 radiologists achieved a test accuracy of 0.722 (95% CI, 0.609-0.813), sensitivity of 0.852 (95% CI, 0.737-0.923), and specificity of 0.135 (95% CI, 0.021-0.415).
This study demonstrates that deep learning based on a ResNet model achieves good accuracy in predicting outcome of uterine fibroid embolization. If further validated, the model may help clinicians better identify patients who can most benefit from this therapy and aid clinical decision making.
开发和验证一种基于子宫纤维瘤栓塞术前常规磁共振成像（MR）的深度学习模型，以预测手术结果。
本研究收集了 2007 年至 2018 年期间在宾夕法尼亚大学医院接受子宫纤维瘤栓塞治疗的患者的临床数据。由一名腹部放射科医生在 MR 成像的 T1 加权对比增强（T1C）序列和栓塞前后的 T2 加权序列上手动对每个患者的肌瘤进行分割。使用术前获得的 MR 成像训练了一种残差卷积神经网络（ResNet）模型来预测临床结果。
纳入标准符合 409 例患者的 727 个肌瘤。在临床随访中，409 例患者中有 85.6%（n=350）（727 个肌瘤中的 590 个；81.1%）症状得到缓解或改善，14.4%（n=59）的 409 例患者（727 个肌瘤中的 137 个；18.9%）症状无改善或恶化。T1C 训练模型的测试准确率为 0.847（95%置信区间[CI]，0.745-0.914），敏感度为 0.932（95% CI，0.833-0.978），特异度为 0.462（95% CI，0.232-0.709）。相比之下，4 名放射科医生的平均准确率为 0.722（95% CI，0.609-0.813），敏感度为 0.852（95% CI，0.737-0.923），特异度为 0.135（95% CI，0.021-0.415）。
本研究表明，基于 ResNet 模型的深度学习在预测子宫纤维瘤栓塞治疗结果方面具有良好的准确性。如果进一步验证，该模型可能有助于临床医生更好地识别最受益于这种治疗的患者，并辅助临床决策。
