文献速递腹部CT

利用端到端三维多模态网络在CT上无标记区分胰腺病变与正常胰腺

Label-free differentiation of pancreatic pathologies from normal pancreas utilizing end-to-end three-dimensional multimodal networks on CT.
PubMed 文献 · Clin Radiol · 2024-06-12

本研究提出轻量级无标记端到端多模态网络eeMulNet,用于腹部CT上胰腺异常的快速诊断,包含胰腺区域定位与融合文本和图像数据的多模态CT诊断两步。研究纳入715例各类胰腺疾病CT和228例对照组CT,训练集与独立测试集按8:2随机划分(755例训练、188例测试)。在188例独立测试集上AUC为1.0、准确率100%、敏感度100%,平均每例测试耗时41.04秒,分类网络仅耗时0.04秒。

要点

  • eeMulNet在188例独立测试集上AUC为1.0、准确率100%、敏感度100%。
  • 模型平均每例测试耗时41.04秒,其中分类网络仅耗时0.04秒。
  • 模型可能有助于日常影像工作中识别可疑病例并提升胰腺疾病诊断准确性。

核心结论

  • 作者认为eeMulNet模型为胰腺疾病诊断提供了有前景的方法,可能有助于日常影像工作中识别可疑病例并提升胰腺疾病诊断准确性。

研究设计与样本

  • 研究提出轻量级无标记端到端多模态网络eeMulNet,包含胰腺区域定位和融合文本与图像数据的多模态CT诊断两步;数据集为715例各类胰腺疾病CT和228例对照组CT,多模态分类网络的训练集与独立测试集按8:2随机划分(755例训练、188例测试)。

诊断标准与关键数值

  • 在188例独立测试集(正常45例、异常143例)上,eeMulNet的AUC为1.0、准确率100%、敏感度100%。

临床应用与阅片要点

  • 作者认为该模型可支持日常影像工作中可疑病例的识别并提升胰腺疾病诊断准确性。

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

AIMS: To investigate the utilization of an end-to-end multimodal convolutional model in the rapid and accurate diagnosis of pancreatic diseases using abdominal CT images.

MATERIALS AND METHODS: In this study, a novel lightweight label-free end-to-end multimodal network (eeMulNet) model was proposed for the rapid and precise diagnosis of abnormal pancreas. The eeMulNet consists of two steps: pancreatic region localization and multimodal CT diagnosis integrating textual and image data. A research dataset comprising 715 CT scans with various types of pancreas diseases and 228 CT scans from a control group was collected. The training set and independent test set for the multimodal classification network were randomly divided in an 8:2 ratio (755 for training and 188 for testing).

RESULTS: The eeMulNet model demonstrated outstanding performance on an independent test set of 188 CT scans (Normal: 45, Abnormal: 143), with an area under the curve (AUC) of 1.0, accuracy of 100%, and sensitivity of 100%. The average testing duration per patient was 41.04 seconds, while the classification network took only 0.04 seconds.

CONCLUSIONS: The proposed eeMulNet model offers a promising approach for the diagnosis of pancreatic diseases. It can support the identification of suspicious cases during daily radiology work and enhance the accuracy of pancreatic disease diagnosis. The codes and models of eeMulNet are publicly available at Rudeguy1/eeMulNet (github.com).

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang G, Gao Q, Zhan Q, et al. Label-free differentiation of pancreatic pathologies from normal pancreas utilizing end-to-end three-dimensional multimodal networks on CT. Clin Radiol. 2024. PMID: 38969545. doi:10.1016/j.crad.2024.06.006

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。