南方医科大学学报

南方医科大学学报 ›› 2023, Vol. 43 ›› Issue (11): 1955-1964.doi: 10.12122/j.issn.1673-4254.2023.11.17

• • 上一篇    下一篇

基于多序列MRI的3D关系注意力网络预测HLA-B27阴性中轴性脊柱关节病

邹青清，王梦虹，陆紫箫，赵英华，冯前进   

  1. 南方医科大学生物医学工程学院//广东省医学图像处理重点实验室，广东 广州 510515；南方医科大学第三附属医院（广东省骨科医院）放射科，广东 广州 510630
  • 出版日期:2023-11-20 发布日期:2023-12-08

Multi-sequence relation attention network for diagnosing HLA-B27-negative axial spondyloarthritis

ZOU Qingqing, WANG Menghong, LU Zixiao, ZHAO Yinghua, FENG Qianjin   

  1. School of Biomedical Engineering, Southern Medical University//Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China; Academy of Orthopedics, Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China
  • Online:2023-11-20 Published:2023-12-08

RichHTML

12

PDF

184

摘要： 目的 建立一种新的3D多序列关系注意力网络，通过探索不同磁共振成像（MRI）序列图像的互补和相关信息，提升对人类白细胞抗原（HLA）-B27阴性中轴性脊柱关节病（axSpA）的诊断性能。方法 回顾性收集2010年1月~2021年8月南方医科大学第三附属医院（TAH组）的375例和南海医院（NHH组）的49例HLA-B27阴性参与者（TAH组：164例axSpA，211例非axSpA；NHH组：27例axSpA，22例非axSpA）的两种参数MRI，包括T1加权图像（T1WI）和压脂序列MRI（FS-MRI），以及相关临床数据。提出一个基于多序列MRI的3D关系注意力网络MSFANet，实现对HLA-B27阴性axSpA与非axSpA的自动鉴别诊断。MSFANet由一个浅层共享特征模块和一个类感知特征学习模块组成，其中类感知特征学习模块采用3D多序列关系注意力机制对多序列MRI特征进行细化和融合。提出一种混合损失函数，通过学习不同支路的损失权重系数来提升MSFANet对序列特征的识别能力，从而增强分类性能。结果 实验结果表明，MSFANet优于其它几种最先进的多序列融合算法，其中内部验证集上的AUC、准确度、敏感度和特异度分别达到了0.840，77.93%，83.70%和70.29%，独立外部验证集（NHH）上的上述性能分别达到了0.783，74.47%，82.43%和70.40%。各项差异均具有统计学意义（P<0.05）。此外，消融实验显示，相同框架下，MSFANet的性能优于基于单序列MRI的模型，证实了融合多序列MRI的有效性和必要性。深度可视化技术显示MSFANet在分类过程中集中于学习图像异常区域的信息。结论 本研究成功构建基于多序列MRI的3D深度神经网络对HLA-B27阴性axSpA和非axSpA进行鉴别诊断，并验证了采用多序列关系注意力机制对提升网络分类性能的有效性。

关键词: 中轴性脊柱关节病诊断, HLA-B27阴性, 磁共振成像, 3D多序列关系注意力机制, 混合损失

Abstract: Objective To develop a new 3D multi-sequence relation attention network for exploring the complementary and correlation information of different magnetic resonance imaging (MRI) modalities and improving the diagnostic performance of HLA-B27-negative axial spondyloarthropathy (axSpA). Methods We retrospectively collected T1-weighted imaging (T1WI) and fat suppuration MRI (FS-MRI) data and clinical data of 375 HLA-B27-negative patients from the Third Affiliated Hospital of Southern Medical University (including 164 axSpA and 211 non-axSpA patients) and 49 patients from Nanhai Hospital (including 27 axSpA and 22 non-axSpA patients) between January, 2010 and August, 2021. A 3D relation attention network MSFANet based on multi-sequence MRI was used for automatic diagnosis of axSpA against non-axSpA in these patients. MSFANet consisted of a shallow shared feature learning module and a class-aware feature learning module, and latter module used a 3D multi-sequence relation attention mechanism to refine and fuse multi-sequence MRI features. A hybrid loss function was used to enhance the recognition ability of MSFANet by learning the loss weight coefficients of different branches to improve the classification performance. Results The experimental results demonstrated that MSFANet outperformed several state-of-the-art fusion algorithms (P<0.05) with AUC, accuracy, sensitivity, and specificity of 0.840, 77.93%, 83.70%, and 70.29% in the internal validation set, and of 0.783, 74.47%, 82.43% and 70.40% in the independent external validation set, respectively. The ablation studies showed that under the same architecture, the fusion model was superior to single-sequence models, which confirmed the effectiveness and necessity of fusing multi- sequence MRI. The visualization results demonstrated that MSFANet could focus on learning information from abnormal areas on MRI during the classification. Conclusion We successfully constructed a 3D deep neural network based on multi-sequence MRI for differential diagnosis of HLA-B27-negative axSpA against non-axSpA and verified the effectiveness of the multi-sequence relation attention mechanism for promoting classification performance of the network.

Key words: axSpA diagnosis, HLA-B27 negative, magnetic resonance imaging, 3D multi-sequence relation attention, hybrid loss