摘要：

深度学习逐渐被广泛应用于医学图像分割领域，基于注意力机制的分割算法是目前研究的主要方法。现有大多数基于注意力机制的2D图像分割模型在多器官分割任务中往往关注切片的整体分割效果，而忽略了切片中小目标特征信息的丢失或欠分割问题，使模型分割性能受到限制。针对这一问题，提出一种基于多尺度特征融合和改进注意力机制的多器官语义分割模型DASC-Net。DASC-Net的整体框架基于编码器-解码器架构，编码器采用ResNet 50，与解码器之间设置跳跃连接。注意力机制由1个双重注意力模块(DAM)和1个小目标提取(SOC)模块的并联结构实现，从而进行多尺度区域特征融合。DASC-Net不仅可以感知到较大目标的特征信息，还可以通过注意力权重重建的方式保留小目标的特征信息，提高了模型的分割性能。在CHAOS数据集上的实验结果表明，DASC-Net在灵敏度、Jaccard相似系数、正类预测值(PPV)、Dice相似系数和平均交并比(mIoU)上分别可以达到83.72%、75.79%、87.75%、85.63%和77.60%，在Synapse数据集上的Dice相似系数和95%豪斯多夫距离(HD95)指标数值分别为82.44%和21.25 mm。DASC-Net在2个数据集上的表现均优于其他分割网络，具有可靠、准确的分割性能。

关键词: 深度学习, 医学图像分割, 注意力机制, 多器官, 小目标提取模块

Abstract:

Deep learning has been widely applied to medical imaging. A medical image segmentation model based on an attention mechanism is one of the main methods used in current research. For the multi-organ segmentation task, most existing 2D segmentation models mainly focus on the overall segmentation effect of slices, while ignoring the loss or under-segmentation of small object feature information in slices, which limits the model′s segmentation performance. To solve this problem, this study proposes a multi-organ semantic segmentation model, DASC-Net, based on multi-scale feature fusion and an improved attention mechanism. The overall framework of the DASC-Net is based on an encoder-decoder architecture. The encoder uses the ResNet 50 network and sets a skip connection with the decoder. The attention mechanism is realized using the parallel structure of a Dual Attention Module (DAM) and a Small Object Capture (SOC) module to perform multi-scale regional feature fusion. DASC-Net not only perceives the feature information of larger objects but also retains the feature information of small objects through attention weight reconstruction, which effectively addresses the limitations of the attention module and further improves the segmentation performance of the model. The experimental results on the CHAOS dataset show that DASC-Net can obtain 83.72%, 75.79%, 87.75%, 85.63% and 77.60% on the Sensitivity, Jaccard similarity coefficient, Positivity Predictive Value (PPV), Dice similarity coefficient, and mean Intersection over Union (mIoU) indicators, respectively; the Dice similarity coefficient and 95% Hausdorff Distance (HD95) values on the Synapse dataset are 82.44% and 21.25 mm, respectively. DASC-Net performs better than the other segmentation networks on both datasets, which demonstrates its reliable and accurate segmentation performance.

Key words: deep learning, medical image segmentation, attention mechanism, multi-organ, Small Object Capture(SOC) module