SC-Net:用于重叠染色体分割的上下文信息跳跃连接网络  

SC-Net:a contextual information skip connection network for overlapping chromosome segmentation

作　　者：焦润海[1] 褚佳杰 刘嘉骥 余济民 Jiao Runhai;Chu Jiajie;Liu Jiaji;Yu Jimin(School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China)

机构地区：[1]华北电力大学控制与计算机工程学院,北京102206

出　　处：《中国图象图形学报》2024年第9期2806-2824,共19页Journal of Image and Graphics

基　　金：中央高校基本科研业务费专项资金资助(2022JG004)。

摘　　要：目的染色体核型分析从细胞分裂中期图像中分离和分类染色体,是遗传疾病诊断广泛采用的方法,其中形态多样的重叠染色体簇的分割,依赖于准确的边界等细节特征。为此,本文融合目标的上下文信息,构建了一种两阶段的重叠染色体分割模型SC-Net(skip connection network)。方法首先,在语义分割基线模型U-Net++中增加混合池化模块捕获重叠染色体的局部上下文信息,在解码器网络中并联上下文融合模块和上下文先验辅助分支,增强通道和空间上的全局上下文信息。其次,利用已标注样本的类别先验信息生成真实亲和矩阵,加入训练过程以有效区分重叠染色体图像中易混淆的空间信息。最后,通过染色体实例重建算法对重叠与非重叠区域的元素迭代进行配对,拼接形成单条染色体。结果在公开的ChromSeg(chromosome segmentation)数据集上进行实验,结果表明SC-Net分割出的重叠染色体区域交并比值为83.5%,与对比算法中的较优算法相比性能提升2.7%。结论本文构建的重叠染色体分割模型通过融合上下文信息,能更有效地解决形态多样的重叠染色体簇的分割问题,相比对比方法可以得到更精细和准确的结果。Objective Chromosome karyotype analysis separates and categorizes chromosomes in midcell division images,and it is widely used for the diagnosis of genetic diseases,in which overlapping chromosome segmentation is one of the key steps.Based on image analysis of overlapping chromosomes,the morphologically diverse chromosome clusters depend on detailed features,such as accurate boundaries during segmentation,in addition to obtaining the basic contour,texture,and semantic information.For this reason,in this paper,a two-stage overlapping chromosome segmentation model SC-Net was constructed through fusion of the contextual information of the target to improve the segmentation performance of the network.Method First,the model SC-UNet++added the hybrid pooling module(HPM)to the baseline model U-Net++for semantic segmentation to capture the local context information of overlapping chromosomes and complemented the detailed features of chromosomes,such as color,thickness,and stripes,based on the superposition operation of empty space pyra⁃mid pooling and stripe pooling.The context fusion module(CFM)was connected in parallel to a decoder network,i.e.,the channel correlation of input features was extracted using the efficient channel attention module,and the features obtained via the multiplication of the output with the input were subsequently fed to the HPM and the spatial attention mod⁃ule(SAM),which explored the correlation of the region around the pixel to obtain the local context and extract the global context through global pooling operation,respectively.In addition,context prior auxiliary branch(CPAB)was introduced after CFM to improve the global context information on channel and space.Second,the category a priori information of labeled training samples,which serves as an additional source of supervisory information during training and effectively dis⁃tinguishes confusing spatial features in overlapping chromosome images,was used to generate the true affinity matrix.Finally,the elements of overlapping and non-o

关 键 词：重叠染色体分割 混合池化模块(HPM) 上下文融合模块(CFM) 上下文先验辅助分支(CPAB) 真实亲和矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]