当前位置: X-MOL 学术Pattern Recogn. › 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.)
MIXCAPS: A capsule network-based mixture of experts for lung nodule malignancy prediction
Pattern Recognition ( IF 8 ) Pub Date : 2021-03-19 , DOI: 10.1016/j.patcog.2021.107942
Parnian Afshar , Farnoosh Naderkhani , Anastasia Oikonomou , Moezedin Javad Rafiee , Arash Mohammadi , Konstantinos N. Plataniotis

Lung cancer is among the most common and deadliest cancers with a low 5-year survival rate. Timely diagnosis of lung cancer is, therefore, of paramount importance as it can save countless lives. In this regard, Computed Tomography (CT) scan is widely used for early detection of lung cancer, where human judgment is currently considered as the gold standard approach. Recently, there has been a surge of interest on development of automatic solutions via radiomics, as human-centered diagnosis is subject to inter-observer variability and is highly burdensome. Hand-crafted radiomics, serving as a radiologist assistant, requires fine annotations and pre-defined features. Deep learning radiomics solutions, however, have the promise of extracting the most useful features on their own in an end-to-end fashion without having access to the annotated boundaries. Among different deep learning models, Capsule Networks are proposed to overcome shortcomings of the Convolutional Neural Networks (CNNs) such as their inability to recognize detailed spatial relations. Capsule networks have so far shown satisfying performance in medical imaging problems. Capitalizing on their success, in this study, we propose a novel capsule network-based mixture of experts, referred to as the MIXCAPS. The proposed MIXCAPS architecture takes advantage of not only the capsule network’s capabilities to handle small datasets, but also automatically splitting dataset through a convolutional gating network. MIXCAPS enables capsule network experts to specialize on different subsets of the data. Our results show that MIXCAPS outperforms a single capsule network, a single CNN, a mixture of CNNs, and an ensemble of capsule networks, with an average accuracy of 90.7%, average sensitivity of 89.5%, average specificity of 93.4% and average area under the curve of 0.956. Our experiments also show that there is a relation between the gate outputs and a couple of hand-crafted features, illustrating explainable nature of the proposed MIXCAPS. To further evaluate generalization capabilities of the proposed MIXCAPS architecture, additional experiments on a brain tumor dataset are performed showing potentials of MIXCAPS for detection of tumors related to other organs.



中文翻译:

MIXCAPS:基于胶囊网络的专家混合物,用于肺结节恶性预测

肺癌是最常见,最致命的癌症,其5年生存率很低。因此,及时诊断肺癌至关重要,因为它可以挽救无数生命。在这方面,计算机断层扫描(CT)扫描被广泛用于肺癌的早期检测,目前,人们的判断被认为是金标准方法。近来,由于以人为中心的诊断受观察者间差异的影响并且负担沉重,因此通过放射线学开发自动解决方案的兴趣激增。手工制作的放射线学,作为放射科医生的助手,需要精细的注释和预定义的功能。深度学习放射学解决方案,但是,承诺可以以端到端的方式自行提取最有用的功能,而无需访问带注释的边界。在不同的深度学习模型中,提出了胶囊网络来克服卷积神经网络(CNN)的缺点,例如它们无法识别详细的空间关系。迄今为止,胶囊网络在医学成像问题上已显示出令人满意的性能。利用他们的成功,在这项研究中,我们提出了一种基于胶囊网络的新型专家混合物,称为MIXCAPS。提出的MIXCAPS体系结构不仅利用了胶囊网络的能力来处理小型数据集,而且还通过卷积门控网络自动分割了数据集。MIXCAPS使胶囊网络专家能够专注于数据的不同子集。我们的结果表明,MIXCAPS的性能优于单个胶囊网络,单个CNN,CNN的混合以及胶囊网络的整体,其平均精度为90.7 的平均灵敏度 89.5 的平均特异性 93.4曲线下的平均面积为0.956。我们的实验还表明,门输出与几个手工制作的功能之间存在关联,说明了所提出的MIXCAPS的可解释性。为了进一步评估提出的MIXCAPS体系结构的泛化能力,在脑肿瘤数据集上进行了额外的实验,显示了MIXCAPS在检测与其他器官相关的肿瘤方面的潜力。

更新日期:2021-04-01
down
wechat
bug