文献速递腹部技术与安全CT

深度学习在腹部CT上自动识别肠梗阻

Deep learning for automatic bowel-obstruction identification on abdominal CT.
PubMed 文献 · Eur Radiol · 2024-02-22

研究开发并验证了一种3D混合卷积神经网络,用于腹部CT上疑似肠梗阻的自动二分类(是/否)。内部数据集1345例CT中670例由腹部放射科医生标注,外部数据集88例CT由放射科医生标注;最佳模型内部F1 0.92、平衡准确率0.86、敏感度0.93,外部F1 0.89、平衡准确率0.89、敏感度0.89;按敏感度校准后内部敏感度1.00、特异度0.84、F1 0.88,外部敏感度0.98、特异度0.76、F1 0.87。

要点

  • 3D混合卷积网络在外部测试集F1 0.89、敏感度0.89,可自动二分类肠梗阻是/否。
  • 按敏感度校准后外部敏感度0.98、特异度0.76、F1 0.87,内部敏感度1.00、特异度0.84、F1 0.88。
  • 该模型有望用于患者选择和CT优先级排序,加快肠梗阻诊断流程。

核心结论

  • 3D混合卷积神经网络在疑似肠梗阻患者的腹部CT自动二分类(肠梗阻是/否)上展现出较大潜力。

研究设计与样本

  • 研究论文;内部数据集为2015-2022年1273例疑似肠梗阻患者的1345份腹部CT,其中670份由一名经验丰富的腹部放射科医生标注肠梗阻是/否;外部数据集为88份经放射科医生标注的CT;搭建腹部-盆腔定位模型与体部裁剪模型组成预处理流程,训练并测试多种神经网络架构,以F1和平衡准确率评估性能。

关键影像表现/征象

  • 预处理流程先定位腹部-盆腔区域,再围绕身体裁剪3D扫描。

诊断标准与关键数值

  • 在Kinetics 400数据集上预训练的混合卷积网络表现最佳:内部数据集F1 0.92、平衡准确率0.86、敏感度0.93。
  • 同一模型外部数据集F1 0.89、平衡准确率0.89、敏感度0.89。
  • 按敏感度校准后内部数据集敏感度1.00、特异度0.84、F1 0.88。
  • 按敏感度校准后外部数据集敏感度0.98、特异度0.76、F1 0.87。

临床应用与阅片要点

  • 作者指出该3D混合CNN可自动完成肠梗阻分类,可能实现患者选择和CT优先级排序,改善放射科医生工作流程。
  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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: Automated evaluation of abdominal computed tomography (CT) scans should help radiologists manage their massive workloads, thereby leading to earlier diagnoses and better patient outcomes. Our objective was to develop a machine-learning model capable of reliably identifying suspected bowel obstruction (BO) on abdominal CT.

MATERIALS AND METHODS: The internal dataset comprised 1345 abdominal CTs obtained in 2015-2022 from 1273 patients with suspected BO; among them, 670 were annotated as BO yes/no by an experienced abdominal radiologist. The external dataset consisted of 88 radiologist-annotated CTs. We developed a full preprocessing pipeline for abdominal CT comprising a model to locate the abdominal-pelvic region and another model to crop the 3D scan around the body. We built, trained, and tested several neural-network architectures for the binary classification (BO, yes/no) of each CT. F1 and balanced accuracy scores were computed to assess model performance.

RESULTS: The mixed convolutional network pretrained on a Kinetics 400 dataset achieved the best results: with the internal dataset, the F1 score was 0.92, balanced accuracy 0.86, and sensitivity 0.93; with the external dataset, the corresponding values were 0.89, 0.89, and 0.89. When calibrated on sensitivity, this model produced 1.00 sensitivity, 0.84 specificity, and an F1 score of 0.88 with the internal dataset; corresponding values were 0.98, 0.76, and 0.87 with the external dataset.

CONCLUSION: The 3D mixed convolutional neural network developed here shows great potential for the automated binary classification (BO yes/no) of abdominal CT scans from patients with suspected BO.

CLINICAL RELEVANCE STATEMENT: The 3D mixed CNN automates bowel obstruction classification, potentially automating patient selection and CT prioritization, leading to an enhanced radiologist workflow.

KEY POINTS: • Bowel obstruction's rising incidence strains radiologists. AI can aid urgent CT readings. • Employed 1345 CT scans, neural networks for bowel obstruction detection, achieving high accuracy and sensitivity on external testing. • 3D mixed CNN automates CT reading prioritization effectively and speeds up bowel obstruction diagnosis.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Vanderbecq Q, Gelard M, Pesquet JC, et al. Deep learning for automatic bowel-obstruction identification on abdominal CT. Eur Radiol. 2024. PMID: 38388719. doi:10.1007/s00330-024-10657-z

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。