Abstract
Early and accurate detection of lymph node metastases is crucial for improving breast cancer patient outcomes. However, current clinical practices, including CT, PET imaging, and microscopic examination, are time-consuming and prone to errors due to low tissue contrast, varying lymph node sizes, and complex workflows. To address the limitations of existing approaches in lymph node segmentation, feature embedding, and classification, this study proposes a novel framework Graph-Pruned Lymph Node Detection Framework (GPLN-DF) that integrates a Dynamic Graph Convolution (DGC) autoencoder with Node Attribute-wise Attention (NodeAttri-Attention) for accurate lymph node segmentation. This segmentation is further refined using Comprehensive Graph Gradual Pruning (CGP) to reduce unnecessary parameters and computational costs. After segmentation, Hessian-based Locally Linear Embedding (HLLE) is applied for effective feature extraction and dimensionality reduction, preserving the geometric structure of lymph node regions. Finally, a Graph Neural Network (GNN) classifier enhanced with CGP is used to classify the segmented lymph nodes as metastatic or non-metastatic based on the extracted features. This comprehensive framework addresses challenges such as small lymph node size, shape variability, low contrast in medical imaging, and high computational burden. The model was evaluated on the CAMELYON17 dataset, achieving a classification accuracy of 98.65%, surpassing existing models in segmentation precision and classification performance.
Data availability
The data used in this paper is collected from Kaggle. The dataset is available at https://www.kaggle.com/datasets/mahdihajialilue/camelyon17-clean.
References
Xu, Q. et al. Difficulty-aware bi-network with Spatial attention constrained graph for axillary lymph node segmentation. Sci. China Inf. Sci. 65 (9), 192102. https://doi.org/10.1007/s11432-020-3079-8 (2022).
Kos, K. et al. Tumor-educated Tregs drive organ-specific metastasis in breast cancer by impairing NK cells in the lymph node niche. Cell. Rep. 38 (9). https://doi.org/10.1016/j.celrep.2022.110447 (2022).
Jayapal, S. & Annamalai, R. Graph neural network with Hessian-Based locally linear embedding for cancer metastasis analysis in lymph nodes using deeplab segmentation. IEEE Access. 13, 46448–46458. https://doi.org/10.1109/ACCESS.2025.3546716 (2025).
Xuan, P. et al. Dynamic graph convolutional autoencoder with node-attribute-wise attention for kidney and tumor segmentation from CT volumes. Knowl. -Based Syst. 236, 107360. https://doi.org/10.1016/j.knosys.2021.107360 (2022).
Wu, W., Laville, A., Deutsch, E. & Sun, R. Deep learning for malignant lymph node segmentation and detection: a review. Front. Immunol. 16, 1526518. https://doi.org/10.3389/fimmu.2025.1526518 (2025).
Iuga, A. I. et al. Automated detection and segmentation of thoracic lymph nodes from CT using 3D foveal fully convolutional neural networks. BMC Med. Imaging. 21 (1), 69. https://doi.org/10.1186/s12880-021-00599-z (2021).
Wang, L. et al. Deep regional metastases segmentation for patient-level lymph node status classification. IEEE Access. 9, 129293–129302. https://doi.org/10.1109/ACCESS.2021.3113036 (2021).
Fan, J. et al. Weakly supervised state space model for multi-class segmentation of pathology images. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 500–509 (2024). https://doi.org/10.1007/978-3-031-72111-3_47
Fang, G., Ma, X., Song, M., Mi, M. B. & Wang, X. Depgraph: Towards any structural pruning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 16091–16101 (2023).
Yu, S., Mazaheri, A. & Jannesari, A. Auto graph encoder-decoder for neural network pruning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6362–6372, (2021).
Cheng, H., Zhang, M. & Shi, J. Q. A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations. IEEE Trans. Pattern Anal. Mach. Intell. 46 (12), 10558–10578. https://doi.org/10.1109/TPAMI.2024.3447085 (2024).
Liang, Y., Liu, W., Yi, S., Yang, H. & He, Z. Filter pruning-based two-step feature map reconstruction. Signal. Image Video Process. 15 (7), 1555–1563. https://doi.org/10.1007/s11760-021-01888-4 (2021).
Singh, A. & Plumbley, M. D. Efficient CNNs via passive filter pruning. IEEE Trans. Audio Speech Lang. Process. 33, 1763–1774. https://doi.org/10.1109/TASLPRO.2025.3561589 (2025).
Xu, Y. & Li, E. Robust locally nonlinear embedding (RLNE) for dimensionality reduction of high-dimensional data with noise. Neurocomputing 596, 127900. https://doi.org/10.1016/j.neucom.2024.127900 (2024).
Luo, F., Zou, Z., Liu, J. & Lin, Z. Dimensionality reduction and classification of hyperspectral image via multistructure unified discriminative embedding. IEEE Trans. Geosci. Remote Sens. 60, 1–16. https://doi.org/10.1109/TGRS.2021.3128764 (2021).
Yang, L. et al. Semantic sketch segmentation with graph neural networks. ACM Trans. Graph. 40 (3), 1–13. https://doi.org/10.1145/3450284 (2021).
Agarwal, R., Ghosal, P., Sadhu, A. K., Murmu, N. & Nandi, D. Multi-scale dual-channel feature embedding decoder for biomedical image segmentation. Comput. Methods Programs Biomed. 257, 108464. https://doi.org/10.1016/j.cmpb.2024.108464 (2024).
Su, L., Du, Y. & GCUNet: A GNN-Based Contextual Learning Network for Tertiary Lymphoid Structure Semantic Segmentation in Whole Slide Image. arXiv preprint arXiv:2412.06129 (2024).
Liu, Z. et al. Axillary lymph node metastasis prediction by contrast-enhanced computed tomography images for breast cancer patients based on deep learning. Comput. Biol. Med. 136, 104715. https://doi.org/10.1016/j.compbiomed.2021.104715 (2021).
Sharma, A. L., Sharma, K., Srivastava, U. P. & Ghosal, P. U. S. T. Automated Skin Lesion Segmentation Using Swin Transformer. In 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), pp. 25–30 (2025)., pp. 25–30 (2025). (2025). https://doi.org/10.1109/ISACC65211.2025.10969397
Chen, C., Li, K., Zou, X., Li, Y. & Dygnn Algorithm and architecture support of dynamic pruning for graph neural networks. In 2021 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, pp. 1201–1206 (2021). https://doi.org/10.1109/DAC18074.2021.9586298
He, W., Wu, M., Liang, M., Lam, S. K. & Cap Context-aware pruning for semantic segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp. 960–969 (2021).
Chen, Z. et al. Neural network pruning through regular graph with edges swapping. Trans. Neural Netw. Learn. Syst. 35 (10), 14671–14683. https://doi.org/10.1109/TNNLS.2023.3280899 (2023).
Gurevin, D. et al. Algorithm-architecture pruning framework for graph neural network acceleration. In 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA), Edinburgh, United Kingdom, pp. 108–123 (2024). https://doi.org/10.1109/HPCA57654.2024.00019
Lalit, M., Tomancak, P., Jug, F. & Embedseg Embedding-based instance segmentation for biomedical microscopy data. Med. Image Anal. 81, 102523. https://doi.org/10.1016/j.media.2022.102523 (2022).
Sun, Y., Pang, S., Zhang, Y. & Zhang, J. Fluid classification with dynamic graph Convolution network by local linear embedding well logging data. Phys. Fluids. 36 (2). https://doi.org/10.1063/5.0187612 (2024).
Liu, R., Liu, Y. & Liu, J. L. L. C. E. Locally Linear Contrastive Embedding. In Companion Proceedings of the ACM Web Conference 2024, pp. 517–520, (2024). (2024). https://doi.org/10.1145/3589335.3651534
Liu, C. et al. Comprehensive graph gradual pruning for sparse training in graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 35 (10), 14903–14917. https://doi.org/10.1109/TNNLS.2023.3282049 (2023).
The CAMELYON17 dataset is available. at https://www.kaggle.com/datasets/mahdihajialilue/camelyon17-clean accessed on July 2025.
Jena, P. P. et al. EPO-SEB: a novel attention-enhanced hybrid model for accurate histopathological image segmentation. Connect. Sci. 37 (1), 2508357. https://doi.org/10.1080/09540091.2025.2508357 (2025).
Huang, N. Y. & Liu, C. X. Efficient tumor detection and classification model based on ViT in an End-to-End architecture. IEEE Access. 12, 106096–106106. https://doi.org/10.1109/ACCESS.2024.3424294 (2024).
Fourkioti, O., De Vries, M., Jin, C., Alexander, D. C. & Bakal, C. C. A. M. I. L. Context-aware multiple instance learning for cancer detection and subtyping in whole slide images. arXiv preprint arXiv:2305.05314 (2023).
Wang, J., Mao, Y., Cui, Y., Guan, N. & Xue, C. J. BAHOP: Similarity-based Basin Hopping for A fast hyper-parameter search in WSI classification. arXiv preprint arXiv:2404.11161 (2024).
Funding
Open access funding provided by Manipal Academy of Higher Education, Manipal. The Authors received NO FUNDING for this work.
Author information
Authors and Affiliations
Contributions
C.H.N. and S.N. developed the core methodology and implemented the Dynamic Graph Convolution and Comprehensive Graph Pruning framework. A.R.S. supervised the project, guided the study design, and contributed to the integration of the GNN classifier. C.S. conducted dataset preparation, preprocessing, and experimental validation. R.Y. contributed to the analysis of results and interpretation of clinical significance. All authors contributed to writing and reviewing the manuscript, approved the final version, and agree to be accountable for all aspects of the work.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
H. N., C., N., S., S., A.R. et al. Dynamic graph convolution with comprehensive pruning and GNN classification for precise lymph node metastasis detection. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37193-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37193-8
