基于KAN改进U型网络的染色体图像分割
Chromosome Image Segmentation Based on KAN Improved U-Net
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。
Abstract: 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, precise segmentation remains a significant challenge. This paper proposes a novel medical image segmentation 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 boundary segmentation accuracy by integrating the KAN-PSP module and cross-hierarchical SIMAM attention mechanism. KAN-PSP combines the adaptive B-spline basis functions of the Kolmogorov-Arnold 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 encoder 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 medical image analysis with significant clinical application value.
文章引用：马嘉美, 张荣福. 基于KAN改进U型网络的染色体图像分割[J]. 建模与仿真, 2025, 14(5): 1064-1078. https://doi.org/10.12677/mos.2025.145457

参考文献

[1] WHO (2020) Birth Defects Surveillance: A Manual for Programme Managers, 2nd Edition.
https://www.who.int/publications/i/item/9789240015395
[2] Mai, C.T., Isenburg, J.L., Canfield, M.A., Meyer, R.E., Correa, A., Alverson, C.J., et al. (2019) National Population‐Based Estimates for Major Birth Defects, 2010-2014. Birth Defects Research, 111, 1420-1435. [Google Scholar] [CrossRef] [PubMed]
[3] Gil, M.M., Accurti, V., Santacruz, B., Plana, M.N. and Nicolaides, K.H. (2017) Analysis of Cell‐Free DNA in Maternal Blood in Screening for Aneuploidies: Updated Meta‐Analysis. Ultrasound in Obstetrics & Gynecology, 50, 302-314. [Google Scholar] [CrossRef] [PubMed]
[4] Miller, D.T., Adam, M.P., Aradhya, S., Biesecker, L.G., Brothman, A.R., Carter, N.P., et al. (2010) Consensus Statement: Chromosomal Microarray Is a First-Tier Clinical Diagnostic Test for Individuals with Developmental Disabilities or Congenital Anomalies. The American Journal of Human Genetics, 86, 749-764. [Google Scholar] [CrossRef] [PubMed]
[5] American College of Obstetricians and Gynecologists, Society for Maternal-Fetal Medicine (2020) Screening for Fetal Chromosomal Abnormalities: ACOG Practice Bulletin, Number 226. Obstetrics & Gynecology, 136, e48-e69. [Google Scholar] [CrossRef] [PubMed]
[6] Van den Veyver, I.B., Chandler, N., Wilkins‐Haug, L.E., Wapner, R.J. and Chitty, L.S. (2022) International Society for Prenatal Diagnosis Updated Position Statement on the Use of Genome‐Wide Sequencing for Prenatal Diagnosis. Prenatal Diagnosis, 42, 796-803. [Google Scholar] [CrossRef] [PubMed]
[7] Madian, N., Jayanthi, K.B. and Suresh, S. (2015) Contour Based Segmentation of Chromosomes in G-Band Metaphase Images. 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 943-947 Orlando, 14-16 December 2015, 943-947. [Google Scholar] [CrossRef] 
[8] Andrade, M.F.S., Cordeiro, F.R., Macario, V., Lima, F.F., Hwang, S.F. and Mendonca, J.C.G. (2018) A Fuzzy-Adaptive Approach to Segment Metaphase Chromosome Images. 2018 7th Brazilian Conference on Intelligent Systems (BRACIS), Sao Paulo, 22-25 October 2018, 290-295. [Google Scholar] [CrossRef] 
[9] Zhang, Z., Kuang, J., Cui, X., Ji, X., Ma, J., Cai, J., et al. (2022) A Chromosome Segmentation Method Based on Corner Detection and Watershed Algorithm. In: Magnenat-Thalmann, N., et al., Eds., Advances in Computer Graphics, Springer, 477-488. [Google Scholar] [CrossRef] 
[10] Dougherty, A.W. and You, J. (2017). A Kernel-Based Adaptive Fuzzy C-Means Algorithm for M-FISH Image Segmentation. 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, 14-19 May 2017, 198-205.[CrossRef] 
[11] Pallavoor, A.S., Prajwal, A., Sundareshan, T.S. and Pallavoor, S.K. (2022) Chromosome Segmentation Analysis Using Image Processing Techniques and Autoencoders. arXiv: 2209.05414.
[12] Liu, X., Wang, S., Lin, J.C. and Liu, S. (2022) An Algorithm for Overlapping Chromosome Segmentation Based on Region Selection. Neural Computing and Applications, 36, 133-142. [Google Scholar] [CrossRef] 
[13] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W. and Frangi, A., Eds, Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer, 234-241. [Google Scholar] [CrossRef] 
[14] Song, S., Bai, T., Zhao, Y., Zhang, W., Yang, C., Meng, J., et al. (2021) A New Convolutional Neural Network Architecture for Automatic Segmentation of Overlapping Human Chromosomes. Neural Processing Letters, 54, 285-301. [Google Scholar] [CrossRef] 
[15] Chen, X., Cai, Q., Ma, N. and Li, H. (2023) ChroSegNet: An Attention-Based Model for Chromosome Segmentation with Enhanced Processing. Applied Sciences, 13, Article 2308. [Google Scholar] [CrossRef] 
[16] Fan, X., Liu, H., Zheng, H., Zhai, J. and Zhang, L. (2024) DaCSeg: Divide and Conquer for Accurate Overlapping Chromosome Instance Segmentation in Metaphase Cell Images. Biomedical Signal Processing and Control, 89, Article ID: 105880. [Google Scholar] [CrossRef] 
[17] Huang, R., Lin, C., Yin, A., Chen, H., Guo, L., Zhao, G., et al. (2022) A Clinical Dataset and Various Baselines for Chromosome Instance Segmentation. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19, 31-39. [Google Scholar] [CrossRef] [PubMed]
[18] Mei, L., Yu, Y., Shen, H., Weng, Y., Liu, Y., Wang, D., et al. (2022) Adversarial Multiscale Feature Learning Framework for Overlapping Chromosome Segmentation. Entropy, 24, Article 522. [Google Scholar] [CrossRef] [PubMed]
[19] Luo, C., Wu, Y. and Zhao, Y. (2023) SupCAM: Chromosome Cluster Types Identification Using Supervised Contrastive Learning with Category-Variant Augmentation and Self-Margin Loss. Frontiers in Genetics, 14, Article 1109269. [Google Scholar] [CrossRef] [PubMed]
[20] Zhao, Y., Song, G. and Wang, P. (2024) Enhanced Label Constrained Contrastive Learning for Chromosome Optical Microscopic Image Classification. Biomedical Signal Processing and Control, 90, Article ID: 105825. [Google Scholar] [CrossRef] 
[21] Wang, J., Zhou, C., Ming, Z., et al. (2024) Skeleton-Guided Instance Separation for Fine-Grained Segmentation in Microscopy. arXiv: 2401.09895.
[22] Liu, Z., Wang, Y., Vaidya, S., et al. (2024) Kan: Kolmogorov-Arnold Networks. arXiv: 2404.19756.
[23] Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J. (2017) Pyramid Scene Parsing Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6230-6239. [Google Scholar] [CrossRef] 
[24] Yang, L., Zhang, R.Y., Li, L., et al. (2021) SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. Proceedings of the 38th International Conference on Machine Learning, 18-24 July 2021, 11863-11874.
[25] Rehman, M.U., Shafique, A., Ghadi, Y.Y., Boulila, W., Jan, S.U., Gadekallu, T.R., et al. (2022) A Novel Chaos-Based Privacy-Preserving Deep Learning Model for Cancer Diagnosis. IEEE Transactions on Network Science and Engineering, 9, 4322-4337. [Google Scholar] [CrossRef] 
[26] Zhao, Y., Lu, K., Xue, J., Wang, S. and Lu, J. (2023) Semi-Supervised Medical Image Segmentation with Voxel Stability and Reliability Constraints. IEEE Journal of Biomedical and Health Informatics, 27, 3912-3923. [Google Scholar] [CrossRef] [PubMed]
[27] Powers, D.M.W. (2020) Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. arXiv: 2010.16061.
[28] Taha, A.A. and Hanbury, A. (2017) Evaluation Metrics for Medical Organ Segmentation and Lesion Detection. In: Hanbury, A., Müller, H. and Langs, G., Eds., Cloud-Based Benchmarking of Medical Image Analysis, Springer, 87-105. [Google Scholar] [CrossRef] 
[29] Chicco, D. and Jurman, G. (2020) The Advantages of the Matthews Correlation Coefficient (MCC) over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genomics, 21, Article No. 6. [Google Scholar] [CrossRef] [PubMed]
[30] Myronenko, A. (2019) 3D MRI Brain Tumor Segmentation Using Autoencoder Regularization. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M. and van Walsum, T., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer, 311-320. [Google Scholar] [CrossRef] 
[31] Oktay, O., Schlemper, J., Folgoc, L.L., et al. (2018) Attention U-Net: Learning Where to Look for the Pancreas. arXiv: 1804.03999.
[32] Valanarasu, J.M.J. and Patel, V.M. (2022) UNeXt: MLP-Based Rapid Medical Image Segmentation Network. In: Wang, L., Dou, Q., Fletcher, P.T. and Speidel, S., Li, S., Eds., Medical Image Computing and Computer Assisted Intervention—MICCAI 2022, Springer, 23-33. [Google Scholar] [CrossRef] 
[33] Liu, Y., Zhu, H., Liu, M., Yu, H., Chen, Z. and Gao, J. (2024) Rolling-Unet: Revitalizing MLP’s Ability to Efficiently Extract Long-Distance Dependencies for Medical Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 3819-3827. [Google Scholar] [CrossRef] 
[34] Li, C., Liu, X., Li, W., et al. (2024) U-Kan Makes Strong Backbone for Medical Image Segmentation and Generation. arXiv: 2406.02918.

为你推荐