Parameter-Free Similarity-Aware Attention Module for Medical Image Classification and Segmentation
Parameter-Free Similarity-Aware Attention Module for Medical Image Classification and Segmentation
复制标题
DOI：
10.1109/tetci.2022.3199733
复制
发表时间：
2023-06
影响因子：
5.3
通讯作者：
Jie Du;Kai Guan;Yanhong Zhou;Yuanman Li;Tianfu Wang
中科院分区：
文献类型：
--
作者：
Jie Du;Kai Guan;Yanhong Zhou;Yuanman Li;Tianfu Wang
医学图像的自动分类与分割在计算机辅助诊断中起着至关重要的作用。深度卷积神经网络（Deep convolutional neural networks, DCNNs）在图像分类和分割方面已显示出其优势。然而，他们在医学图像上并没有取得像在自然图像上那样的成功。本文针对医学图像上的DCNNs存在两个问题：1)特征多样性不足；2)忽视小病变。这两个问题严重影响了分类和分割的性能。为了提高DCNN在医学图像上的性能，提出了相似感知关注（simi-attention）模块，包括特征相似感知通道关注（FCA）和区域相似感知空间关注（RSA）。我们的相似关注提供了三个优势：1)通过我们的FCA和RSA从医学图像中提取多样性和判别性特征，可以实现更高的准确性；2)对于对比度较低、病灶较小的数据，也能准确地对病灶进行聚焦定位；3)由于其模块中没有可训练的参数，因此不会增加骨干模型的复杂性。在4个公共医学分类数据集和2个公共医学分割数据集上对分类和分割任务进行了实验结果。可视化结果表明，我们的相似注意力可以准确地集中在病灶上进行分类，即使对小物体也能产生良好的分割结果。总体性能表明，我们的相似注意力可以显著提高骨干模型的性能，并且在大多数数据集上的分类和分割都优于比较的注意力模型。
Automatic classification and segmentation of medical images play essential roles in computer-aided diagnosis. Deep convolutional neural networks (DCNNs) have shown their advantages on image classification and segmentation. However, they have not achieved the same success on medical images as they have done on natural images. In this paper, two challenges are exploited for DCNNs on medical images, including 1) lack of feature diversity; 2) neglect of small lesions. These two issues heavily influence the classification and segmentation performances. To improve the performance of DCNN on medical images, similarity-aware attention (simi-attention) module is proposed, including a Feature-similarity-aware Channel Attention (FCA) and a Region-similarity-aware Spatial Attention (RSA). Our simi-attention provides three advantages: 1) higher accuracy can be achieved since it extracts both diverse and discriminant features from medical images via our FCA and RSA; 2) the lesions can be exactly focused and located by it even for the data with low intensity contrast and small lesions; 3) it does not increase the complexity of backbone models due to NO trainable parameters in its module. The experimental results are conducted on both classification and segmentation tasks under four public medical classification datasets and two public medical segmentation datasets. The visualization results show that our simi-attention can accurately focuses on the lesions for classification and generate fine segmentation results even for small objects. The overall performances show that our simi-attention can significantly improve the performances of backbone models and outperforms compared attention models on most of datasets for both classification and segmentation.