超声与超声造影特征融合深度学习诊断≤2cm肝局灶性小病变
本研究回顾性纳入687例接受B型超声和超声造影的肝局灶性病变患者,开发并验证基于ResNet-18及特征融合的深度学习模型。模型在测试集AUC达0.994,敏感度97.53%、特异度94.74%,显著高于四名放射科医生(AUC 0.787-0.930,均P<0.05)。在≤2cm小病灶等亚组中,模型AUC为0.990-0.999,持续优于所有医生。
要点
- 深度学习模型对≤2cm肝局灶性小病变良恶性判别能力强。
- 模型融合B型超声与动脉期、门脉期、延迟期超声造影图像特征。
- 该模型可作为日常阅片中辅助判断小肝病灶良恶性的工具。
核心结论
- 基于B型超声与超声造影特征融合的深度学习模型可为肝局灶性病变良恶性判别提供有效工具。
- 该模型对≤2cm小病灶、不同性别、HBV感染及肝硬化状态亚组均保持高诊断效能。
研究设计与样本
- 回顾性研究纳入2016年9月至2020年3月间687例接受B型超声及超声造影的肝局灶性病变患者。
- 数据集按80%训练集、20%测试集划分,采用基于ResNet-18并整合特征融合的深度学习模型。
- 模型提取并整合B型超声及超声造影动脉期、门脉期、延迟期三个关键时相的深度特征。
- 模型诊断性能与四名放射科医生进行比较,并做小病灶、性别、HBV感染及肝硬化亚组分析。
诊断标准与关键数值
- 测试集中,深度学习模型诊断肝局灶性病变良恶性的AUC为0.994。
- 模型敏感度为97.53%,特异度为94.74%。
- 四名放射科医生AUC范围为0.787-0.930,模型显著高于全部医生,均P<0.05。
- 模型敏感度与特异度较两名高年资医生均无显著差异,均P>0.05。
- 在≤2cm小病灶等亚组中,模型AUC为0.990-0.999。
临床应用与阅片要点
- 可借助该深度学习模型对B型超声及超声造影图像进行特征融合分析,辅助肝小病灶定性。
- 阅片时需重点提供动脉期、门脉期及延迟期三个超声造影时相图像以匹配模型输入条件。
局限性
- 研究为回顾性设计。
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
BACKGROUND: To develop and validate a deep learning (DL) model based on feature fusion with B-mode ultrasound (BMUS) and contrast enhanced ultrasound (CEUS) images for non-invasive diagnosis of benign and malignant focal liver lesions (FLLs), especially for small FLLs (≤2.0 cm).
METHODS: A retrospective dataset of 687 patients who were diagnosed with FLLs by BMUS and underwent CEUS between September 2016 and March 2020 was collected in this study. The dataset was divided into a training set (80%) and a test set (20%). For the feature fusion strategy can leverage the complementary information from each feature to obtain the complete information of an image. We innovatively designed a DL model based on the ResNet-18, integrated with the feature fusion, to extract and consolidate deep feature representations from both BMUS images and three key CEUS phases (arterial, portal venous, and delayed). The performance of the model was compared to that of four radiologists. Subgroup analyses were performed to assess model performance in patients with small FLLs (≤2.0 cm), different genders, hepatitis B virus (HBV) infection status, and cirrhosis.
RESULTS: The DL model achieved an area under the curve (AUC) of 0.994 in the test set, significantly surpassing four participating radiologists (AUCs ranging from 0.787 to 0.930; all p < 0.05). In terms of sensitivity and specificity, the model achieved 97.53% and 94.74%, respectively, showing no significant difference compared to two of the experienced radiologists (all p > 0.05). Furthermore, in subgroup analyses, including patients with small FLLs (≤2.0 cm), different genders, hepatitis B virus (HBV) infection, and cirrhosis status, the model consistently outperformed all four radiologists, achieving AUCs between 0.990 and 0.999 across subgroups.
CONCLUSION: By harnessing BMUS and CEUS images of patients with FLLs, the feature fusion-based DL model offers an effective diagnostic tool for discerning the benign or malignant nature of FLLs.
引用
- Xu, Wei, Zhang, et al. Diagnosis of Small Focal Liver Lesions (≤2 cm): A Deep Learning Approach Based on B-Mode Ultrasound and Contrast-Enhanced Ultrasound. Ultrasound Med Biol. 2026. PMID: 42350195. doi:10.1016/j.ultrasmedbio.2026.01.002
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。