文献速递腹部MR

基于标准T2加权MRI的两阶段深度学习方法检测晚期肝纤维化

Advanced liver fibrosis detection using a two-stage deep learning approach on standard T2-weighted MRI.
PubMed 文献 · Abdom Radiol (NY) · 2025-08-19

研究开发并验证了一种基于标准T2加权MRI的深度学习模型,用于自动检测晚期肝纤维化。模型在病理证实的独立测试集(n=23)上敏感度0.778、特异度0.800、AUC 0.811,显著优于无分割的直接分类(AUC 0.743)。作者认为该全自动流程可能为非侵入性替代方案。

要点

  • 两阶段模型在病理证实测试集上AUC 0.811,优于直接分类AUC 0.743。
  • 分割质量影响分类准确性:分割评分1的准确率0.818,评分3仅0.625。
  • DenseNet121(AUC 0.795)和SwinTransformer(AUC 0.782)性能略低于本文模型。

核心结论

  • 全自动深度学习流程利用标准非增强T2加权MRI有效检测晚期肝纤维化,可能提供非侵入性替代方案;分割优先策略较直接分类有显著性能提升。

研究设计与样本

  • 开发并验证深度学习模型,使用公共CirrMRI600+数据集(n=374,其中肝硬化318例、健康者56例)和本机构慢性肝病数据集(n=187);采用nnU-Net肝脏分割模型与Masked Attention ResNet分类模型两阶段流程;以LSM>12 kPa定义晚期纤维化(n=104),健康者及LSM≤12 kPa者为非晚期纤维化(n=116);验证仅在23例经病理确认纤维化分期(METAVIR≥F3为晚期)的独立测试集上进行。

诊断标准与关键数值

  • 在病理证实的独立测试集(n=23)上,两阶段模型敏感度0.778、特异度0.800、AUC 0.811、准确率0.783;直接分类无分割AUC 0.743;DenseNet121 AUC 0.795,SwinTransformer AUC 0.782;肝脏分割测试集平均Dice评分0.960±0.009、IoU 0.923±0.016;分割评分1的病例准确率0.818,分割评分3的准确率0.625。

临床应用与阅片要点

  • 作者认为该分割优先的全自动流程可能作为非侵入性替代方案用于检测晚期肝纤维化;分割质量影响分类准确性,分割评分1的准确率0.818高于评分3的0.625。

局限性

  • 验证仅在23例经病理确认的独立测试集上进行。

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 validate a deep learning model for automated detection of advanced liver fibrosis using standard T2-weighted MRI.

METHODS: We utilized two datasets: the public CirrMRI600 + dataset (n = 374) containing T2-weighted MRI scans from patients with cirrhosis (n = 318) and healthy subjects (n = 56), and an in-house dataset of chronic liver disease patients (n = 187). A two-stage deep learning pipeline was developed: first, an automated liver segmentation model using nnU-Net architecture trained on CirrMRI600 + and then applied to segment livers in our in-house dataset; second, a Masked Attention ResNet classification model. For classification model training, patients with liver stiffness measurement (LSM) > 12 kPa were classified as advanced fibrosis (n = 104). In contrast, healthy subjects from CirrMRI600 + and patients with LSM ≤ 12 kPa were classified as non-advanced fibrosis (n = 116). Model validation was exclusively performed on a separate test set of 23 patients with histopathological confirmation of the degree of fibrosis (METAVIR ≥ F3 indicating advanced fibrosis). We additionally compared our two-stage approach with direct classification without segmentation, and evaluated alternative architectures including DenseNet121 and SwinTransformer.

RESULTS: The liver segmentation model performed excellently on the test set (mean Dice score: 0.960 ± 0.009; IoU: 0.923 ± 0.016). On the pathologically confirmed independent test set (n = 23), our two-stage model achieved strong diagnostic performance (sensitivity: 0.778, specificity: 0.800, AUC: 0.811, accuracy: 0.783), significantly outperforming direct classification without segmentation (AUC: 0.743). Classification performance was highly dependent on segmentation quality, with cases having excellent segmentation (Score 1) showing higher accuracy (0.818) than those with poor segmentation (Score 3, accuracy: 0.625). Alternative architectures with masked attention showed comparable but slightly lower performance (DenseNet121: AUC 0.795; SwinTransformer: AUC 0.782).

CONCLUSIONS: Our fully automated deep learning pipeline effectively detects advanced liver fibrosis using standard non-contrast T2-weighted MRI, potentially offering a non-invasive alternative to current diagnostic approaches. The segmentation-first approach provides significant performance gains over direct classification.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Gupta P, Singh S, Gulati A, et al. Advanced liver fibrosis detection using a two-stage deep learning approach on standard T2-weighted MRI. Abdom Radiol (NY). 2025. PMID: 40828398. doi:10.1007/s00261-025-05160-y

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。