摘要
在产前诊断中,染色体核型分析是检测遗传疾病的金标准,但染色体形态复杂且易交叉粘连,精准分割仍面临挑战。文章提出了新型医学图像分割模型KEU-Net,旨在解决染色体等高复杂度、多尺度目标的精准分割问题。KEU-Net通过融合KAN-PSP模块和跨层级SIMAM注意力机制,显著提升特征建模与边界分割精度。KAN-PSP结合Kolmogorov-Arnold网络的自适应B样条基函数与金字塔池化,实现多尺度特征建模,提升Jaccard指数3.361%;SIMAM注意力机制在编码器深层抑制背景噪声、在解码器浅层增强边缘响应,将边界贴合误差ASD降低19.6%。此外,KAN-PSP与SIMAM通过动态特征协同优化,维持高召回率。实验结果表明,KEU-Net在染色体数据集上的Dice系数为87.074%,较UNet和Attention UNet提升2.57%~3.94%,为医学影像分析提供了高精度、强鲁棒性的解决方案,具有重要的临床应用价值。
In prenatal diagnosis,chromosomal karyotype analysis is the gold standard for detecting genetic disorders.However,due to the complex morphology and frequent overlaps of chromosomes,pre-cise segmentation remains a significant challenge.This paper proposes a novel medical image seg-mentation model,KEU-Net,aimed at addressing the precise segmentation of high-complexity,multi-scale structures such as chromosomes.KEU-Net significantly enhances feature modeling and bound-ary segmentation accuracy by integrating the KAN-PSP module and cross-hierarchical SIMAM atten-tion mechanism.KAN-PSP combines the adaptive B-spline basis functions of the Kolmogorov-Ar-nold network with pyramid pooling to achieve multi-scale feature modeling,improving the Jaccard index by 3.361%.The SIMAM attention mechanism suppresses background noise in the deeper en-coder layers and enhances edge responses in the shallower decoder layers,reducing the boundary fitting error(ASD)by 19.6%.Furthermore,KAN-PSP and SIMAM work together through a dynamic feature collaborative optimization,maintaining a high recall rate.Experimental results show that KEU-Net achieves a Dice coefficient of 87.074%on the chromosome dataset,outperforming U-Net and Attention U-Net by 2.57%~3.94%.This provides a high-precision and robust solution for med-ical image analysis with significant clinical application value.
作者
马嘉美
张荣福
Jiamei Ma;Rongfu Zhang(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai)
出处
《建模与仿真》
2025年第5期1064-1078,共15页
Modeling and Simulation
关键词
医学图像分割
染色体图像分割
KAN网络
多尺度感知
注意力机制
Medical Image Segmentation
Chromosomal Image Segmentation
KAN Network
Multi-Scale Perception
Attention Mechanism
