文献速递腹部技术与安全US

深度学习用于无创检测MASLD中的脂肪变性和纤维化:一项采用新Fibroscan标注超声数据集的多中心研究

Deep learning for non-invasive detection of steatosis and fibrosis in MASLD: a multicenter study with a new fibroscan-labelled ultrasound dataset.
PubMed 文献 · Abdom Radiol (NY) · 2025-11-24

本研究利用常规B型超声图像开发并验证深度学习模型,以Fibroscan测量为参考标准,无创评估MASLD患者的肝脂肪变性和纤维化。模型在交叉验证中脂肪变性AUROC为0.83、纤维化为0.86,外部测试集分别为0.70和0.88,时间独立测试集分别为0.82和0.91,表现优于专家放射科医师。

要点

  • 深度学习模型可从常规B型超声图像分类MASLD脂肪变性(S0-S1 vs S2-S3)和纤维化(F0-F1 vs F2-F4)。
  • 纤维化分类在外部测试集AUROC达0.88,时间独立测试集达0.91。
  • 脂肪变性分类外部测试集AUROC为0.70(95%CI 0.43-0.93)。

核心结论

  • 深度学习模型可在多样人群和临床环境中从超声图像准确识别脂肪变性和纤维化。

研究设计与样本

  • 多中心研究,使用三个MASLD患者超声数据集:私有临床数据集DS1(n=111例患者,1131张图像);公共BEHSOF库中Behbood Clinic子集DS2(n=95例患者,1328张图像)用于训练/验证;Taleghani Hospital子集DS3(n=18例患者,185张图像)用于外部测试;另在时间独立测试集DS4(n=23例患者,155张图像)上验证。参考标准为Fibroscan衍生测量。深度学习模型包括EfficientNet-B4和Vision Transformers,采用5折交叉验证训练。

诊断标准与关键数值

  • 脂肪变性分类任务为S0-S1 vs S2-S3,纤维化分类任务为F0-F1 vs F2-F4。脂肪变性分类AUROC:交叉验证0.83(95%CI 0.78-0.88),外部测试集0.70(95%CI 0.43-0.93),时间独立测试集0.82(95%CI 0.66-0.98)。纤维化分类AUROC:交叉验证0.86(95%CI 0.81-0.91),外部测试集0.88(95%CI 0.71-1.00),时间独立测试集0.91(95%CI 0.77-1.00)。专家放射科医师观察者间一致性κ=0.58-0.65。

临床应用与阅片要点

  • AI模型在脂肪变性和纤维化分类上均优于专家放射科医师,但脂肪变性分类在外部测试集AUROC为0.70(95%CI 0.43-0.93),置信区间较宽。

局限性

  • 脂肪变性分类在外部测试集AUROC为0.70(95%CI 0.43-0.93),置信区间较宽。

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: This study aimed to develop and validate deep learning models for non-invasive assessment of hepatic steatosis and fibrosis using conventional B-mode ultrasound images, with Fibroscan-derived measurement as reference standard.

METHODS: We utilized a multi-source approach comprising three distinct ultrasound datasets of patients with MASLD: a private clinical dataset (DS1, n = 111 patients, 1131 images), and two subsets from the public BEHSOF repository-Behbood Clinic subset (DS2, n = 95 patients, 1328 images) for training/validation, and Taleghani Hospital subset (DS3, n = 18 patients, 185 images) for external testing. Additionally, we validated on a temporally independent test set (DS4, n = 23 patients, 155 images). Deep learning models, including EfficientNet-B4 and Vision Transformers, were trained to classify steatosis (S0-S1 vs. S2-S3) and fibrosis (F0-F1 vs. F2-F4), respectively, using 5-fold cross-validation. Performance was assessed and compared with expert radiologists.

RESULTS: For steatosis classification, our models achieved an AUROC of 0.83 (95% CI: 0.78-0.88) in cross-validation and 0.70 (95% CI: 0.43-0.93) on the external test set. For fibrosis, AUROC reached 0.86 (95% CI: 0.81-0.91) in cross-validation and 0.88 (95% CI: 0.71-1.00) on the external test set. On the temporally independent test set, performance was better with AUROCs of 0.82 (95% CI: 0.66-0.98) for steatosis and 0.91 (95% CI: 0.77-1.00) for fibrosis. The AI models consistently outperformed expert radiologists, whose interobserver agreement was moderate (κ = 0.58-0.65).

CONCLUSION: This study demonstrates that deep learning models can accurately identify steatosis and fibrosis from ultrasound images across diverse populations and clinical settings.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Bose K, Mudgil P, Gupta P, et al. Deep learning for non-invasive detection of steatosis and fibrosis in MASLD: a multicenter study with a new fibroscan-labelled ultrasound dataset. Abdom Radiol (NY). 2025. PMID: 41284028. doi:10.1007/s00261-025-05309-9

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。