文献速递疝与腹壁外科围术期管理与 ERAS

基于图像的深度学习模型预测腹壁重建中的罕见结局

Predicting rare outcomes in abdominal wall reconstruction using image-based deep learning models.
PubMed 文献 · Surgery · 2022-10-11

本研究利用510例腹壁重建患者的术前CT图像(共10,004张),开发并比较传统深度学习模型与生成对抗网络异常框架模型预测补片感染和肺部衰竭的性能。结果显示生成对抗网络异常模型在预测补片感染(ROC 0.73 vs 0.61, P<.01)和肺部衰竭(ROC 0.70 vs 0.59, P<.01)方面优于传统模型,主要通过提高敏感性实现。

要点

  • 生成对抗网络异常模型预测补片感染和肺部衰竭的ROC值分别为0.73和0.70,优于传统模型。
  • 对罕见但严重并发症的风险分层可借助GAN异常检测框架改善。

核心结论

  • 与传统深度学习模型相比,生成对抗网络异常深度学习模型在不平衡数据集上表现更优,主要通过提高模型敏感性实现。

研究设计与样本

  • 使用前瞻性维护的机构数据库识别腹壁重建患者,纳入有术前CT扫描者,共510例患者、10,004张图像。
  • 传统深度学习模型采用8层卷积神经网络和2类训练系统(学习阴性和阳性结局)。
  • 生成对抗网络异常框架模型使用图像增强和异常检测。
  • 主要结局为预测补片感染和肺部衰竭的受试者工作特征曲线(ROC)值。

主要发现

  • 补片感染发生率为3.7%,肺部衰竭发生率为5.6%。
  • 传统模型预测补片感染的ROC为0.61,生成对抗网络异常模型为0.73(P<.01)。
  • 传统模型预测肺部衰竭的ROC为0.59,生成对抗网络异常模型为0.70(P<.01)。

临床怎么用

  • 理解罕见但严重术后并发症的风险患者可改善风险分层、资源利用和知情同意过程。

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)。

原文

BACKGROUND: Deep learning models with imbalanced data sets are a challenge in the fields of artificial intelligence and surgery. The aim of this study was to develop and compare deep learning models that predict rare but devastating postoperative complications after abdominal wall reconstruction. METHODS: A prospectively maintained institutional database was used to identify abdominal wall reconstruction patients with preoperative computed tomography scans. Conventional deep learning models were developed using an 8-layer convolutional neural network and a 2-class training system (ie, learns negative and positive outcomes). Conventional deep learning models were compared to deep learning models that were developed using a generative adversarial network anomaly framework, which uses image augmentation and anomaly detection. The primary outcomes were receiver operating characteristic values for predicting mesh infection and pulmonary failure. RESULTS: Computed tomography scans from 510 patients were used with a total of 10,004 images. Mesh infection and pulmonary failure occurred in 3.7% and 5.6% of patients, respectively. The conventional deep learning models were less effective than generative adversarial network anomaly for predicting mesh infection (receiver operating characteristic 0.61 vs 0.73, P < .01) and pulmonary failure (receiver operating characteristic 0.59 vs 0.70, P < .01). Although the conventional deep learning models had higher accuracies/specificities for predicting mesh infection (0.93 vs 0.78, P < .01/.96 vs .78, P < .01) and pulmonary failure (0.88 vs 0.68, P < .01/.92 vs .67, P < .01), they were substantially compromised by decreased model sensitivity (0.25 vs 0.68, P < .01/.27 vs .73, P < .01). CONCLUSION: Compared to conventional deep learning models, generative adversarial network anomaly deep learning models showed improved performance on imbalanced data sets, predominantly by increasing model sensitivity. Understanding patients who are at risk for rare but devastating postoperative complications can improve risk stratification, resource utilization, and the consent process.

来源:Surgery,查看原文。版权归原作者所有。

引用

  1. Ayuso SA, Elhage SA, Zhang Y, et al. Predicting rare outcomes in abdominal wall reconstruction using image-based deep learning models. Surgery. 2022. PMID: 36229252. doi:10.1016/j.surg.2022.06.048

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。