基于CT和MRI的多模态深度学习模型预测肝细胞癌微血管侵犯
本研究纳入本机构287例及另一机构58例肝细胞癌患者,构建基于CT和MRI的多模态深度学习模型预测微血管侵犯。多模态模型AUC为0.844,优于单期CT、单序列MRI、单模态深度学习及临床模型(P<0.05),联合临床特征后AUC升至0.871。
要点
- 多模态深度学习模型预测肝细胞癌微血管侵犯的AUC为0.844。
- 联合临床特征后AUC由0.844提升至0.871。
- 多模态模型优于单期CT、单序列MRI、单模态深度学习及临床模型(P<0.05)。
核心结论
- 多模态深度学习模型是术前无创预测肝细胞癌微血管侵犯的有价值技术。
研究设计与样本
- 回顾性纳入本机构287例及另一机构58例肝细胞癌患者,其中119例仅CT数据、116例仅MRI数据用于单模态深度学习模型开发,110例同时具备CT和MRI数据者分为训练队列(n=66)和验证队列(n=44)。
诊断标准与关键数值
- 多模态深度学习模型预测微血管侵犯的AUC为0.844。
- 单期CT模型AUC为0.706-0.776,单序列MRI模型AUC为0.706-0.717,均低于多模态模型(P<0.05)。
- 单模态深度学习模型AUC:全期CT为0.722,全序列MRI为0.731,均低于多模态模型(P<0.05)。
- 临床模型AUC为0.648,低于多模态模型(P<0.05)。
- 多模态模型联合临床特征后AUC由0.844升至0.871。
临床应用与阅片要点
- 多模态深度学习模型可作为一种无创技术用于术前预测肝细胞癌微血管侵犯。
- 将深度学习特征与临床指标联合构建的列线图,其总体净获益大于多模态深度学习模型(P<0.05)。
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
PURPOSE: To investigate the value of a multimodal deep learning (MDL) model based on computed tomography (CT) and magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC).
METHODS: A total of 287 patients with HCC from our institution and 58 patients from another individual institution were included. Among these, 119 patients with only CT data and 116 patients with only MRI data were selected for single-modality deep learning model development, after which select parameters were migrated for MDL model development with transfer learning (TL). In addition, 110 patients with simultaneous CT and MRI data were divided into a training cohort (n = 66) and a validation cohort (n = 44). We input the features extracted from DenseNet121 into an extreme learning machine (ELM) classifier to construct a classification model.
RESULTS: The area under the curve (AUC) of the MDL model was 0.844, which was superior to that of the single-phase CT (AUC = 0.706-0.776, P < 0.05), single-sequence MRI (AUC = 0.706-0.717, P < 0.05), single-modality DL model (AUCall-phase CT = 0.722, AUCall-sequence MRI = 0.731; P < 0.05), clinical (AUC = 0.648, P < 0.05), but not to that of the delay phase (DP) and in-phase (IP) MRI and portal venous phase (PVP) CT models. The MDL model achieved better performance than models described above (P < 0.05). When combined with clinical features, the AUC of the MDL model increased from 0.844 to 0.871. A nomogram, combining deep learning signatures (DLS) and clinical indicators for MDL models, demonstrated a greater overall net gain than the MDL models (P < 0.05).
CONCLUSION: The MDL model is a valuable noninvasive technique for preoperatively predicting MVI in HCC.
引用
- Lei Y, Feng B, Wan M, et al. Predicting microvascular invasion in hepatocellular carcinoma with a CT- and MRI-based multimodal deep learning model. Abdom Radiol (NY). 2024. PMID: 38433144. doi:10.1007/s00261-024-04202-1
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。