Abstract: Aiming at the problems of medical ultrasound images such as many noisy points, fuzzy boundaries, and difficulty in defining the cardiac contours, a new Spatial Frequency Divided Attention Network for ultrasound image segmentation (SFDA-Net) was proposed. Firstly, with the help of Octave convolution, the high and low-frequency parallel processing of image in the entire network was realized to obtain more diverse information. Then, the Convolutional Block Attention Module (CBAM) was added for paying more attention to the effective information when image feature recovered, so as to reduce the loss of segmenting the entire target area. Finally Focal Tversky Loss was considered as the objective function to reduce the weights of simple samples and pay more attention on difficult samples, as well as decrease the errors introduced by pixel misjudgment between the categories. Through multiple sets of comparative experiments,it can be seen that with the parameter number lower than that of the original UNet++, SFDA-Net has the segmentation accuracy increased by 6.2 percentage points, Dice sore risen by 8.76 percentage points, mean Pixel Accuracy (mPA) improved to 84.09%, and mean Intersection Over Union (mIoU) increased to 75.79%. SFDA-Net steadily improves the network performance while reducing parameters, and makes the echocardiographic segmentation more accurate.

Key words: echocardiogram, deep learning, image segmentation, spatial frequency division, attention mechanism

摘要： 针对医学超声影像噪点多、边界模糊，器官轮廓很难界定的问题，提出了一种基于空间分频的超声图像分割注意力网络（SFDA-Net）。首先，借助Octave卷积在整个网络中对图像实现了高、低频并行处理，从而获得更加多元的信息。然后，加入卷积块注意模块（CBAM），使图像特征恢复时更加关注有效信息，以减小分割目标整体区域的缺失。最后，使用Focal Tversky Loss作为目标函数，从而降低简单样本的权重并加强对困难样本的关注，以及降低各个类别间因像素误判而引入的误差。通过多组对比实验可知，SFDA-Net的参数量低于原UNet++，而分割精度提高了6.2个百分点，Dice得分提高了8.76个百分点，类别平均像素准确率（mPA）提升至84.09%，平均交并比（mIoU）提升至75.79%。SFDA-Net在降低参数量的同时稳步提高了网络性能，实现了更为准确的超声心动图分割。

关键词: 超声心动图, 深度学习, 图像分割, 空间分频, 注意力机制