南方医科大学学报

南方医科大学学报 ›› 2023, Vol. 43 ›› Issue (5): 839-851.doi: 10.12122/j.issn.1673-4254.2023.05.21

• • 上一篇    下一篇

深度注意力机制结合临床特征预测肝细胞癌微血管浸润

巩 高，曹 石，肖 慧，方威扬，阙与清，刘子蔚，陈超敏   

  1. 南方医科大学生物医学工程学院，广东 广州 510515；南昌大学第一附属医院，江西 南昌 330006；南方医科大学附属顺德医院，广东 佛山 528308
  • 出版日期:2023-05-20 发布日期:2023-06-12

Prediction of microvascular invasion in hepatocellular carcinoma with magnetic resonance imaging using models combining deep attention mechanism with clinical features

GONG Gao, CAO Shi, XIAO Hui, FANG Weiyang, QUE Yuqing, LIU Ziwei, CHEN Chaomin   

  1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; First Affiliated Hospital of Nanchang University, Nanchang 330006, China; Shunde Hospital Affiliated to Southern Medical University, Foshan 528308, China
  • Online:2023-05-20 Published:2023-06-12

RichHTML

14

PDF

319

摘要： 目的 探讨磁共振成像（MRI）评估微血管浸润（MVI）存在的一致性和诊断性能，以及深度学习注意力机制和临床特征在MVI分类预测中的有效性。方法 选取2017年1月~2020年2月南方医科大学附属顺德医院158例患者数据进行回顾性实验，包括常规MRI序列（T1WI、T2WI、DWI）、增强MRI序列（AP、PP、EP、HBP）、合成MRI序列（T1mapping-pre、T1mapping-20min）得到MRI图像以及可能与MVI相关的临床数据。基于EfficientNetB0和注意力模块分别建立单序列深度学习模型和融合模型，并且通过深度学习可视化技术显示肝细胞癌微血管浸润的高危区域。结果 基于T1mapping-20min序列和临床特征的融合模型结果要优于其他融合模型。准确度为83.76%，AUC为85.01%，敏感度为83.78%，特异度为87.02%，且深度可视化技术可以显示MVI高危区域。结论 本研究成功建立基于多个MRI序列的单序列模型和融合模型，并验证了深度学习算法结合注意力机制和临床特征对MVI分类预测的有效性。

关键词: 微血管浸润；肝细胞癌；磁共振成像；注意力机制；临床特征

Abstract: Objective To investigate the consistency and diagnostic performance of magnetic resonance imaging (MRI) for detecting microvascular invasion (MVI) of hepatocellular carcinoma (HCC) and the validity of deep learning attention mechanisms and clinical features for MVI grade prediction. Methods This retrospective study was conducted among 158 patients with HCC treated in Shunde Hospital Affiliated to Southern Medical University between January, 2017 and February, 2020. The imaging data and clinical data of the patients were collected to establish single sequence deep learning models and fusion models based on the EfficientNetB0 and attention modules. The imaging data included conventional MRI sequences (T1WI, T2WI, and DWI), enhanced MRI sequences (AP, PP, EP, and HBP) and synthesized MRI sequences (T1mapping-pre and T1mapping-20 min), and the high-risk areas of MVI were visualized using deep learning visualization techniques. Results The fusion model based on T1mapping-20min sequence and clinical features outperformed other fusion models with an accuracy of 0.8376, a sensitivity of 0.8378, a specificity of 0.8702, and an AUC of 0.8501 for detecting MVI. The deep fusion models were also capable of displaying the high- risk areas of MVI. Conclusion The fusion models based on multiple MRI sequences can effectively detect MVI in patients with HCC, demonstrating the validity of deep learning algorithm that combines attention mechanism and clinical features for MVI grade prediction.

Key words: microvascular invasion; hepatocellular carcinoma; magnetic resonance imaging; attention mechanism; clinical features