当前位置: X-MOL 学术Comput. Methods Programs Biomed. › 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.)
Introducing frequency representation into convolution neural networks for medical image segmentation via twin-Kernel Fourier convolution
Computer Methods and Programs in Biomedicine ( IF 4.9 ) Pub Date : 2021-04-14 , DOI: 10.1016/j.cmpb.2021.106110
Xianlun Tang , Jiangping Peng , Bing Zhong , Jie Li , Zhenfu Yan

Background and objective

For medical image segmentation, deep learning-based methods have achieved state-of-the-art performance. However, the powerful spectral representation in the field of image processing is rarely considered in these models.

Methods

In this work, we propose to introduce frequency representation into convolution neural networks (CNNs) and design a novel model, tKFC-Net, to combine powerful feature representation in both frequency and spatial domains. Through the Fast Fourier Transform (FFT) operation, frequency representation is employed on pooling, upsampling, and convolution without any adjustments to the network architecture. Furthermore, we replace original convolution with twin-Kernel Fourier Convolution (t-KFC), a new designed convolution layer, to specify the convolution kernels for particular functions and extract features from different frequency components.

Results

We experimentally show that our method has an edge over other models in the task of medical image segmentation. Evaluated on four datasets—skin lesion segmentation (ISIC 2018), retinal blood vessel segmentation (DRIVE), lung segmentation (COVID-19-CT-Seg), and brain tumor segmentation (BraTS 2019), the proposed model achieves outstanding results: the metric F1-Score is 0.878 for ISIC 2018, 0.8185 for DRIVE, 0.9830 for COVID-19-CT-Seg, and 0.8457 for BraTS 2019.

Conclusion

The introduction of spectral representation retains spectral features which result in more accurate segmentation. The proposed method is orthogonal to other topology improvement methods and very convenient to be combined.



中文翻译:

通过双核傅里叶卷积将频率表示引入卷积神经网络进行医学图像分割

背景和目标

对于医学图像分割,基于深度学习的方法已实现了最先进的性能。但是,在这些模型中很少考虑图像处理领域中强大的光谱表示。

方法

在这项工作中,我们建议将频率表示引入卷积神经网络(CNN),并设计一个新颖的模型tKFC-Net,以在频域和空间域中结合强大的特征表示。通过快速傅立叶变换(FFT)操作,可以在合并,上采样和卷积上采用频率表示,而无需对网络体系结构进行任何调整。此外,我们将双卷傅立叶卷积(t-KFC)(一种新设计的卷积层)替换为原始卷积,以指定用于特定功能的卷积核,并从不同频率分量中提取特征。

结果

我们通过实验表明,在医学图像分割任务中,我们的方法比其他模型更具优势。在四个数据集上进行了评估-皮肤病变分割(ISIC 2018),视网膜血管分割(DRIVE),肺分割(COVID-19-CT-Seg)和脑肿瘤分割(BraTS 2019),该模型获得了出色的结果:公制F1-分数对于ISIC 2018是0.878,对于DRIVE是0.8185,对于COVID-19-CT-Seg是0.9830,对于BraTS 2019是0.8457。

结论

频谱表示法的引入保留了频谱特征,可导致更精确的分割。所提出的方法与其他拓扑改进方法正交,并且非常易于组合。

更新日期:2021-04-26
down
wechat
bug