Veasey Benjamin P, Broadhead Justin, Dahle Michael, Seow Albert, Amini Amir A
University of Louisville Louisville KY 40208 USA.
IEEE Open J Eng Med Biol. 2020 Sep 11;1:257-264. doi: 10.1109/OJEMB.2020.3023614. eCollection 2020.
We propose a convolutional attention-based network that allows for use of pre-trained 2-D convolutional feature extractors and is extendable to multi-time-point classification in a Siamese structure. Our proposed framework is evaluated for single- and multi-time-point classification to explore the value that temporal information, such as nodule growth, adds to malignancy prediction. Our results show that the proposed method outperforms a comparable 3-D network with less than half the parameters on single-time-point classification and further achieves performance gains on multi-time-point classification. Attention-based, Siamese 2-D pre-trained CNNs lead to fast training times and are effective for malignancy prediction from single-time-point or multiple-time-point imaging data.
我们提出了一种基于卷积注意力的网络，该网络允许使用预训练的二维卷积特征提取器，并且可以扩展为暹罗结构的多时间点分类。我们提出的框架针对单时间点和多时间点分类进行了评估，以探索诸如结节生长等时间信息对恶性肿瘤预测的价值。我们的结果表明，所提出的方法在单时间点分类上优于参数不到其一半的可比三维网络，并且在多时间点分类上进一步实现了性能提升。基于注意力的暹罗二维预训练卷积神经网络训练速度快，对于从单时间点或多时间点成像数据进行恶性肿瘤预测是有效的。
