论文标题
CMU-NET：一个基于强的交换器的医疗超声图像分割网络
CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network
论文作者
论文摘要
U-NET及其扩展在医学图像分割方面取得了巨大成功。但是，由于普通卷积操作的固有本地特征，U-Net编码器无法有效提取全局上下文信息。此外，简单的跳过连接无法捕获显着功能。在这项工作中，我们提出了一个完全卷积分割网络（CMU-NET），该网络结合了混合卷积和多规模的注意门。 Convmixer模块通过在遥远的空间位置混合特征来提取全局上下文信息。此外，多尺度的注意门强调了宝贵的功能，并实现了有效的跳过连接。我们使用乳房超声数据集和甲状腺超声图像数据集评估了提出的方法； CMU-NET与联合（IOU）值（IOU）值达到73.27％和84.75％，F1分数达到84.81％和91.71％。该代码可在https://github.com/fenghetan9/cmu-net上找到。
U-Net and its extensions have achieved great success in medical image segmentation. However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information. In addition, simple skip connections cannot capture salient features. In this work, we propose a fully convolutional segmentation network (CMU-Net) which incorporates hybrid convolutions and multi-scale attention gate. The ConvMixer module extracts global context information by mixing features at distant spatial locations. Moreover, the multi-scale attention gate emphasizes valuable features and achieves efficient skip connections. We evaluate the proposed method using both breast ultrasound datasets and a thyroid ultrasound image dataset; and CMU-Net achieves average Intersection over Union (IoU) values of 73.27% and 84.75%, and F1 scores of 84.81% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net.
