文献速递头颈MR

基于多参数MRI的颈部脓肿深度学习自动分割研究

Deep learning-based automated segmentation of neck abscesses on multiparametric MRI.
PubMed 文献 · Eur J Radiol · 2026-08-14

本研究纳入226例经手术证实的颈部脓肿患者,利用nnU-Net v2深度学习模型在MRI上进行自动分割。比较了仅使用增强后T1加权图像(T1C)与T1C、T2脂肪抑制(T2FS)和ADC三通道融合两种输入配置的性能。结果显示自动分割与手动分割在体积和定量测量上具有良好至极好的一致性,T1C单序列模型非劣效于三通道融合模型。

要点

  • 深度学习可自动分割MRI上的颈部脓肿,DSC达0.828±0.124
  • T1C单序列模型非劣效于多序列融合模型,可简化扫描流程
  • 自动测量的脓肿体积与手动测量一致性极好(ICC≥0.933)

核心结论

  • 基于多参数MRI的颈部脓肿深度学习自动分割具有可行性,体积和定量测量与手动分割一致性好至极好
  • T1C单序列模型非劣效于三通道融合模型,可作为避免配准混杂因素的简约单序列替代方案

研究设计与样本

  • 单中心回顾性研究,纳入226例经手术证实的颈部脓肿患者,来自急诊MRI数据库
  • 采用nnU-Net v2深度学习分割模型,以五折交叉验证评估性能
  • 两种输入配置:仅T1C增强图像,以及T1C、T2FS和ADC三通道融合(T2FS和ADC刚性配准至T1C空间)

诊断标准与关键数值

  • 融合模型五折交叉验证平均DSC为0.828±0.124(226例)
  • T1C单序列模型平均DSC为0.813±0.153,非劣效于融合模型(p=0.005)
  • 体积一致性:融合模型ICC=0.970,T1C单序列模型ICC=0.933

临床应用与阅片要点

  • 临床可优先考虑T1C单序列自动分割,避免多序列配准带来的额外误差和操作复杂性
  • 自动体积测量可用于颈部脓肿严重程度评估,与手动测量一致性高
  • 深度学习分割结果可作为急诊MRI阅片的辅助工具,加速脓肿范围判断

局限性

  • 单中心回顾性设计,缺乏外部验证
  • 参考标准为手动分割而非病理大体标本测量

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 and evaluate automated deep learning (DL) segmentation of acute neck abscesses on MRI and to assess agreement between automated and manual quantitative measurements relevant to severity assessment.

MATERIALS AND METHODS: In 226 patients with surgically confirmed neck abscesses from a single-center emergency MRI database, a DL segmentation model (nnU-Net v2) was trained using two input configurations: (1) post-contrast T1-weighted images (T1C) only and (2) a three-channel fusion of T1C, T2-weighted fat saturated (T2FS), and apparent diffusion coefficient (ADC) maps, with T2FS and ADC rigidly registered to T1C space. Performance was evaluated using five-fold cross-validation. Spatial overlap (Dice similarity coefficient [DSC]), volumetric agreement (intraclass correlation coefficient [ICC]), and quantitative feature agreement were compared between automated and manual segmentations.

RESULTS: The fusion model achieved a mean DSC of 0.828 ± 0.124 across all 226 cases in five-fold cross-validation. The T1C-only model achieved a mean DSC of 0.813 ± 0.153 and was non-inferior to the fusion model (p = 0.005). Volumetric agreement was excellent for both models (fusion ICC = 0.970, T1C-only ICC = 0.933). Quantitative features showed good to excellent agreement.

CONCLUSION: Automated DL segmentation of neck abscesses on multiparametric MRI is feasible and yields volumetric and quantitative measurements in good to excellent agreement with manual segmentation. The T1C-only model was non-inferior to the three-channel fusion model, offering a parsimonious single-sequence alternative that avoids registration-related confounds.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Viertonen, Sirén, Reima, et al. Deep learning-based automated segmentation of neck abscesses on multiparametric MRI. Eur J Radiol. 2026. PMID: 42607500. doi:10.1016/j.ejrad.2026.113165

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。