文献速递腹部CT

基于三维CT的深度学习模型自动检出与分类胰腺病灶

Detection and characterization of pancreatic lesions with 3D CT data using an automated deep learning-based solution.
PubMed 文献 · Eur J Radiol · 2026-07-17

本研究利用来自18家机构的1037例门静脉期CT数据,开发并验证一种自动分类胰腺病灶为正常、良性或恶性的深度学习算法。内部与外部验证集中恶性病灶的AUC达0.97,总体AUC为0.84。结果显示该模型在检测恶性病灶方面表现较好,但临床适用性仍需进一步验证。

要点

  • 模型对恶性胰腺病灶检出AUC达0.97,可作为胰腺癌早期筛查的辅助工具。
  • 总体精确率与召回率分别仅0.57和0.63,单独使用存在误判风险。
  • 门静脉期CT数据即可建模,便于嵌入常规增强CT流程。

核心结论

  • 采用深度学习算法对CT胰腺病灶进行自动分类为正常、良性或恶性具有可行性。
  • 模型对恶性病灶具有较高检出能力,外部验证集中恶性病灶AUC为0.97。
  • 模型在内部与外部验证集中的最终评分为0.72,表现一致。

研究设计与样本

  • 研究纳入来自18家机构的1037例门静脉期CT扫描数据。
  • 数据划分为训练集732例、内部验证集139例与外部验证集166例。
  • 利用TotalSegmentator算法进行胰腺分割,模型结合其预训练编码器与nnUNet解码器。
  • 采用十折交叉验证,最终预测为十个模型输出的整合。

关键影像表现/征象

  • 模型可对增强CT门静脉期图像中的胰腺病灶进行分类。
  • 恶性病灶在外部验证集中具有突出检出性能,AUC为0.97。
  • 模型输出为正常、良性或恶性三类,非直接生成肉眼可判读的影像征象。

诊断标准与关键数值

  • 总体精确率为0.57,召回率为0.63,AUC为0.84。
  • 恶性病灶检出AUC为0.97。
  • 最终评分为精确率、召回率与AUC的加权平均,内部与外部验证集均为0.72。

临床应用与阅片要点

  • 模型可作为胰腺恶性病灶的筛查辅助工具,但不宜单独用于排除诊断。
  • 门静脉期图像即可供模型分析,便于整合至现有增强CT流程。
  • 阅片时需注意总体精确率与召回率偏低,模型阴性结果不能完全排除病灶。

局限性

  • 模型总体精确率与召回率有限,存在误分类风险。
  • 研究所采用的数据为多中心但未说明设备与扫描参数标准化情况。
  • 原文指出需进一步评估模型的临床适用性及真实场景中的表现。

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

PURPOSE: Pancreatic ductal adenocarcinoma (PDA) is a leading cause of cancer-related deaths, with early diagnosis hampered by nonspecific symptoms and limitations of existing imaging techniques. This study aimed to develop a deep learning (DL) algorithm to automatically classify pancreas lesions on contrast-enhanced CT scans as normal, benign, or malignant, to assist radiologists in detecting early-stage pancreatic cancer.

MATERIALS AND METHODS: A dataset of 1,037 portal-phase CT scans was compiled from 18 institutions. The dataset was divided into a training set (N = 732) and a test set (N = 305), which was further divided into an internal validation test set (N = 139) and an external validation test set (N = 166). After segmentation using the TotalSegmentator algorithm, the pancreas was isolated from each CT scan. A DL model combining TotalSegmentator's pre-trained encoder and nnUNet decoder layers was developed to classify pancreas lesions. Ten-fold cross-validation was applied, and model performance was assessed using precision, recall, area under the curve (AUC) and a final score (FS) representing a weighted average of the previous three metrics. The final prediction combined the outputs of ten models.

RESULTS: Across all validation datasets (139 and 166 patients, respectively, in the internal and external dataset), precision and recall were 0.57 and 0.63, respectively, while AUC was 0.84. In the external validation dataset, malignant lesions were detected with an AUC of 0.97. The model achieved an FS of 0.72 in both internal and external validation datasets, indicating consistent performance across datasets.

CONCLUSION: This study demonstrated the feasibility of using a DL algorithm for automated pancreas lesion classification in CT scans. The model showed strong performance, particularly in detecting malignant lesions. Further research is needed to assess the model's clinical applicability and performance in real-world settings.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Goubalan, Della Corte, Laurent, et al. Detection and characterization of pancreatic lesions with 3D CT data using an automated deep learning-based solution. Eur J Radiol. 2026. PMID: 42476063. doi:10.1016/j.ejrad.2026.113093

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。