基于非对称多解码器和注意力模块的三维肾脏影像结构分割模型

Structure segmentation model for 3D kidney images based on asymmetric multi-decoder and attention module

针对肾脏结构中,因不同结构间差异大,动静脉体积小、结构薄及计算机断层扫描血管造影(CTA)图像灰度分布不均和伪影带来的精确分割困难的问题,提出基于非对称多解码器和注意力模块的三维肾脏影像结构分割模型MDAUnet(MultiDecoder-Attention-Unet)。首先,针对不同结构间差异大导致网络无法共享权重的问题,采用多解码器结构,为语义结构不同的特征结构匹配不同的解码器分支;其次,针对血管体积小、结构薄难分割的问题,引入非对称的空间通道联合注意力模块使模型更关注管状结构,并对学习到的特征信息同时进行空间维度和通道维度的校准;最后,为了保证模型在反向传播中对血管结构有足够的关注,提出改进的加权硬区域适应损失(WHRA)作为损失函数来动态保持训练过程中血管结构的类间平衡以及保留背景信息的特征;此外,为了提高特征图灰度值的对比度,将传统图像处理边缘检测算子嵌入模型的预处理阶段,对待分割的感兴趣区域边界进行特征增强使模型更关注边界信息并抑制伪影信息。实验结果表明:所提出的MDAUnet模型在肾脏结构分割任务上的Dice相似系数(DSC),豪斯多夫距离95(HD95)和平均表面距离(AVD)分别为89.1%,1.76 mm和1.04 mm;在DSC指标上,与次优的MGANet(Meta Greyscale Adaptive Network)相比,MDAUnet提升了1.2个百分点;在HD95和ASD指标上,与次优的UNETR(UNEt TRansformers)相比,MDAUnet分别降低了0.87 mm和0.45 mm。可见MDAUnet能有效提高肾脏三维结构分割精度,有助于医生在临床手术中客观有效地评估病情。

To address the problems of accurate segmentation difficulties for kidney structures caused by large differences between different structures,small sizes and thin structures of arteries and veins,and uneven grayscale distribution and artifacts in Computed Tomography Angiography(CTA)images,a kidney 3D structure segmentation model MDAUnet(MultiDecoder-Attention-Unet)based on multi-decoder and attention mechanism with CTA was proposed.Firstly,to address the problem that the network cannot share weights due to large differences between different structures,a multidecoder structure was used to match different decoder branches for feature structures with different semantic structures.Secondly,to address the problem that it is difficult to segment blood vessels with small size and thin structure,an asymmetric spatial channel joint attention module was introduced to make the model more focused on tubular structures,and the learned feature information was simultaneously calibrated in spatial dimension and channel dimension.Finally,in order to ensure that the model paid enough attention to the vessel structure in back propagation,an improved WHRA(Weighted Hard Region Adaptation)loss was proposed as a loss function to dynamically maintain the inter-class balance of the vessel structure during training as well as to preserve the characteristics of the background information.In addition,in order to improve the contrast of the grayscale values of the feature map,the edge detection operator in traditional image processing was embedded into the pre-processing stage of the model,and the feature enhancement of the boundary of the region of interest to be segmented made the model more focused on the boundary information and suppressed the artifact information.The experimental results show that the Dice Similarity Coefficient(DSC),Hausdorff Distance 95(HD95)and Average Surface Distance(AVD)of the proposed MDAUnet model on the kidney structure segmentation task are 89.1%,1.76 mm and 1.04 mm,respectively.Compared with suboptimal MGANet(Meta Greyscale Adaptive Network),MDAUnet improves the DSC index by 1.2 percentage points;compared with suboptimal UNETR(UNEt TRansformers),MDAUnet reduces HD95 and ASD indexes by 0.87 mm and 0.45 mm,respectively.It can be seen that MDAUnet can effectively improve the segmentation accuracy of the three-dimensional structure of the kidney,and help doctors to evaluate the condition objectively and effectively in clinical operations.