文献速递腹部泌尿生殖CT

基于深度学习的多类分割模型在增强CT上分割并鉴别乏脂性肾上腺结节:一项双中心研究

A multi-class segmentation model of deep learning on contrast-enhanced computed tomography to segment and differentiate lipid-poor adrenal nodules: a dual-center study.
PubMed 文献 · Eur Radiol · 2025-09-22

这项回顾性双中心研究纳入164例经病理证实的乏脂性腺瘤(LPA)或结节性增生(NH)患者,在1 mm门静脉期增强CT图像上训练并外部验证Mamba-USeg多类分割模型。模型分割肾上腺的mDSC为0.855,分割LPA和NH结节的mDSC分别为0.869和0.863,均显著优于MultiResUNet和CPFNet;逐层分类对LPA的敏感度95.3%、特异度92.7%,对NH的敏感度94.2%、特异度91.5%,外部患者分类准确率91.7%。

要点

  • Mamba-USeg在门静脉期增强CT上同时分割并分类乏脂性腺瘤与结节性增生,分割性能显著优于MultiResUNet和CPFNet。
  • 逐层分类对LPA敏感度95.3%、特异度92.7%,对NH敏感度94.2%、特异度91.5%。
  • 外部中心患者分类准确率为91.7%(95%CI 76.8-98.9%)。

核心结论

  • 所提出的多类分割模型能在增强CT图像上准确分割并鉴别LPA与NH,性能优于现有方法。

研究设计与样本

  • 回顾性双中心研究,纳入164例病理证实的LPA或NH患者(中位年龄51.0岁,女性93例),内部中心128例训练、外部36例验证;放射科医师在1 mm门静脉期CT图像上标注肾上腺和结节,以病理为参考标准,比较Mamba-USeg与MultiResUNet、CPFNet。

诊断标准与关键数值

  • 逐层分割mDSC:肾上腺0.855,LPA结节0.869,NH结节0.863。逐层分类:LPA敏感度95.3%(95%CI 91.3-96.6%)、特异度92.7%(95%CI 91.9-93.6%);NH敏感度94.2%(95%CI 89.7-97.7%)、特异度91.5%(95%CI 90.4-92.4%);外部患者分类准确率91.7%(95%CI 76.8-98.9%)。

临床应用与阅片要点

  • 模型可同时分割并分类肾上腺结节,作者认为其显著有助于临床决策,从而减少肾上腺增生患者的不必要手术。

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

OBJECTIVES: To develop a deep-learning model for segmenting and classifying adrenal nodules as either lipid-poor adenoma (LPA) or nodular hyperplasia (NH) on contrast-enhanced computed tomography (CECT) images.

MATERIALS AND METHODS: This retrospective dual-center study included 164 patients (median age 51.0 years; 93 females) with pathologically confirmed LPA or NH. The model was trained on 128 patients from the internal center and validated on 36 external cases. Radiologists annotated adrenal glands and nodules on 1-mm portal-venous phase CT images. We proposed Mamba-USeg, a novel state-space models (SSMs)-based multi-class segmentation method that performs simultaneous segmentation and classification. Performance was evaluated using the mean Dice similarity coefficient (mDSC) for segmentation and sensitivity/specificity for classification, with comparisons made against MultiResUNet and CPFNet.

RESULTS: From per-slice segmentation, the model yielded an mDSC of 0.855 for the adrenal gland; for nodule segmentation, it achieved mDSCs of 0.869 (LPA) and 0.863 (NH), significantly outperforming two previous models-MultiResUNet (LPA, p < 0.001; NH, p = 0.014) and CPFNet (LPA, p = 0.003; NH, p = 0.023). Classification performance from per slice demonstrated sensitivity of 95.3% (95% confidence interval [CI] 91.3-96.6%) and specificity of 92.7% (95% CI: 91.9-93.6%) for LPA, and sensitivity of 94.2% (95% CI: 89.7-97.7%) and specificity of 91.5% (95% CI: 90.4-92.4%) for NH. The classification accuracy for patients from external sources was 91.7% (95% CI: 76.8-98.9%).

CONCLUSION: The proposed multi-class segmentation model can accurately segment and differentiate between LPA and NH on CECT images, demonstrating superior performance to existing methods.

KEY POINTS: Question Accurate differentiation between LPA and NH on imaging remains clinically challenging yet critically important for guiding appropriate treatment approaches. Findings Mamba-Useg, a multi-class segmentation model utilizing pixel-level analysis and majority voting strategies, can accurately segment and classify adrenal nodules as LPA or NH. Clinical relevance The proposed multi-class segmentation model can simultaneously segment and classify adrenal nodules, outperforming previous models in accuracy; it significantly aids clinical decision-making and thereby reduces unnecessary surgeries in adrenal hyperplasia patients.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Bai X, Wu Z, Lu L, et al. A multi-class segmentation model of deep learning on contrast-enhanced computed tomography to segment and differentiate lipid-poor adrenal nodules: a dual-center study. Eur Radiol. 2025. PMID: 40981992. doi:10.1007/s00330-025-12007-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。