当前位置: X-MOL 学术Med. Image Anal. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automatic Grading Assessments for Knee MRI Cartilage Defects via Self-ensembling Semi-supervised Learning with Dual-Consistency
Medical Image Analysis ( IF 10.9 ) Pub Date : 2022-06-18 , DOI: 10.1016/j.media.2022.102508
Jiayu Huo 1 , Xi Ouyang 1 , Liping Si 2 , Kai Xuan 3 , Sheng Wang 1 , Weiwu Yao 4 , Ying Liu 5 , Jia Xu 6 , Dahong Qian 7 , Zhong Xue 8 , Qian Wang 9 , Dinggang Shen 10 , Lichi Zhang 3
Affiliation  

Knee cartilage defects caused by osteoarthritis are major musculoskeletal disorders, leading to joint necrosis or even disability if not intervened at early stage. Deep learning has demonstrated its effectiveness in computer-aided diagnosis, but it is time-consuming to prepare a large set of well-annotated data by experienced radiologists for model training. In this paper, we propose a semi-supervised framework to effectively use unlabeled data for better evaluation of knee cartilage defect grading. Our framework is developed based on the widely-used mean-teacher classification model, by designing a novel dual-consistency strategy to boost the consistency between the teacher and student models. The main contributions are three-fold: (1) We define an attention loss function to make the network focus on the cartilage regions, which can both achieve accurate attention masks and boost classification performance simultaneously; (2) Besides enforcing the consistency of classification results, we further design a novel attention consistency mechanism to ensure the focusing of the student and teacher networks on the same defect regions; (3) We introduce an aggregation approach to ensemble the slice-level classification outcomes for deriving the final subject-level diagnosis. Experimental results show that our proposed method can significantly improve both classification and localization performances of knee cartilage defects. Our code is available on https://github.com/King-HAW/DC-MT.



中文翻译:

通过具有双重一致性的自组装半监督学习对膝关节 MRI 软骨缺损进行自动分级评估

骨关节炎引起的膝关节软骨缺损是主要的肌肉骨骼疾病,如不及早干预,可导致关节坏死甚至致残。深度学习已证明其在计算机辅助诊断中的有效性,但由经验丰富的放射科医生准备大量注释良好的数据以进行模型训练非常耗时。在本文中,我们提出了一个半监督框架,以有效地使用未标记数据来更好地评估膝关节软骨缺损分级。我们的框架是基于广泛使用的平均教师分类模型开发的,通过设计一种新颖的双重一致性策略来提高教师和学生模型之间的一致性。主要贡献有三方面:(1)我们定义了一个注意力损失函数,使网络专注于软骨区域,既可以实现准确的注意力掩码,又可以同时提高分类性能;(2) 除了强制分类结果的一致性外,我们进一步设计了一种新颖的注意力一致性机制,以确保学生和教师网络关注相同的缺陷区域;(3) 我们引入了一种聚合方法来集成切片级别的分类结果,以得出最终的主题级别诊断。实验结果表明,我们提出的方法可以显着提高膝关节软骨缺损的分类和定位性能。我们的代码可在 https://github.com/King-HAW/DC-MT 上找到。我们进一步设计了一种新颖的注意力一致性机制,以确保学生和教师网络关注相同的缺陷区域;(3) 我们引入了一种聚合方法来集成切片级别的分类结果,以得出最终的主题级别诊断。实验结果表明,我们提出的方法可以显着提高膝关节软骨缺损的分类和定位性能。我们的代码可在 https://github.com/King-HAW/DC-MT 上找到。我们进一步设计了一种新颖的注意力一致性机制,以确保学生和教师网络关注相同的缺陷区域;(3) 我们引入了一种聚合方法来集成切片级别的分类结果,以得出最终的主题级别诊断。实验结果表明,我们提出的方法可以显着提高膝关节软骨缺损的分类和定位性能。我们的代码可在 https://github.com/King-HAW/DC-MT 上找到。实验结果表明,我们提出的方法可以显着提高膝关节软骨缺损的分类和定位性能。我们的代码可在 https://github.com/King-HAW/DC-MT 上找到。实验结果表明,我们提出的方法可以显着提高膝关节软骨缺损的分类和定位性能。我们的代码可在 https://github.com/King-HAW/DC-MT 上找到。

更新日期:2022-06-18
down
wechat
bug