Academic Journal
Προβολή σε EDS

Preoperative Decision-Oriented Decoupled Multi-Scale Feature Pyramid and Global Context Aggregation Network for Coronary Artery Segmentation in X-Ray Angiography.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Preoperative Decision-Oriented Decoupled Multi-Scale Feature Pyramid and Global Context Aggregation Network for Coronary Artery Segmentation in X-Ray Angiography.
Συγγραφείς: Lin J; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China., Lin L; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China., Li Z; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China., Zhou M; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China., Wang Y; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China., Sun F; Fuqing City Hospital Affiliated to Fujian Medical University, Fuqing, China.
Πηγή: The international journal of medical robotics + computer assisted surgery : MRCAS [Int J Med Robot] 2026 Aug; Vol. 22 (4), pp. e70210.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Wiley Country of Publication: England NLM ID: 101250764 Publication Model: Print Cited Medium: Internet ISSN: 1478-596X (Electronic) Linking ISSN: 14785951 NLM ISO Abbreviation: Int J Med Robot Subsets: MEDLINE
Imprint Name(s): Publication: 2006- : West Sussex, England : Wiley
Original Publication: Ilkley, UK : Robotic Publications, c2004-
Ιατρικοί όροι (MeSH): Coronary Angiography*/methods , Coronary Vessels*/diagnostic imaging , Coronary Vessels*/surgery, Humans ; Algorithms
Περίληψη: Background: Accurate preoperative coronary artery delineation in X-ray angiography is critical for stenosis quantification, cardiovascular diagnosis, and treatment planning, yet class imbalance, weak bifurcation contrast, and overlapping artefacts often cause broken or distorted vessel segmentation.
Methods: We propose a decoupled hybrid architecture that separates multi-scale detail recovery from global context aggregation, combining an FPN neck for distal-vessel edge preservation with a UPerHead head for multi-level contextual prior modelling.
Results: On the ARCADE benchmark, the model achieves Dice, IoU, and Centreline Dice scores of 0.7633, 0.6290, and 0.7827, outperforming competitive baseline methods in terms of Dice, IoU, and Centreline Dice, with consistent but moderate improvements over the strongest competing model. Grad-CAM++ and feature-distribution analyses suggest improved contextual attention and enhanced interpretability of learnt representations.
Conclusions: The framework enhances robust preoperative vessel segmentation, supporting assessment of distal continuity, bifurcation morphology, and lesion-adjacent boundaries for clinical decision-making.
(© 2026 John Wiley & Sons Ltd. All rights reserved, including rights for text and data mining and training of artificial intelligence technologies or similar technologies.)
References: F. Shariaty, M. Mohebi, E. Barzegar‐Golmoghani, et al., “Deep Vessel Segmentation With U‐Net and Texture Representation of Image (TRI) Features Provides a Foundation for Improved Objective and Automated Analysis of Coronary Artery Disease From Angiography,” Computer Methods and Programs in Biomedicine (2025): 109072, https://doi.org/10.1016/j.cmpb.2025.109072.
C. K. Revathi and H. Santhi, “A Dual‐Stage Deep Learning Framework for Detecting Borderline Coronary Artery Stenosis in X‐Ray Angiography,” Engineering Research Express 8, no. 9 (2026): 095230, https://doi.org/10.1088/2631‐8695/ae6419.
C. Li, M. Chu, X. Liu, et al., “Straightening the Path to Clarity: A Subpixel‐Level Vessel Segmentation Framework in X‐Ray Coronary Angiography,” Computerized Medical Imaging and Graphics (2025): 102634, https://doi.org/10.1016/j.compmedimag.2025.102634.
M. Yousefzadeh, S. Shirzadeh Barough, A. Fakharifar, et al., “Coronary Artery Segmentation and Vessel‐Type Classification in X‐Ray Angiography,” arXiv.org (2026).
T. Chen, Yu Ren, W. Liu, et al., “Computational Methods for Analysing X‐Ray‐Guided Coronary Angiography: From Key Frame Selection to Vessel Segmentation, Stenosis Detection and Classification,” Journal of Asian Pacific Society of Cardiology 4 (2025): e22, https://doi.org/10.15420/japsc.2024.46.
C. Dong, D. Dai, X. Han, et al., “Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT‐CNN Encoding and Variational Fusion,” in International Conference on Medical Image Computing and Computer‐Assisted Intervention, (2025), 647–657.
T. Liu, H. Lin, A. Katsaggelos, and A. Kline, “YOLO‐Angio: An Algorithm for Coronary Anatomy Segmentation,” arXiv.org (2023).
Yi. Li, Y. Wu, J. He, et al., “Automatic Coronary Artery Segmentation and Diagnosis of Stenosis by Deep Learning Based on Computed Tomographic Coronary Angiography,” European Radiology 32, no. 9 (2022): 6037–6045, https://doi.org/10.1007/s00330‐022‐08761‐z.
H. Zhang, Z. Gao, D. Zhang, W. Hau, and H. Zhang, “Progressive Perception Learning for Main Coronary Segmentation in X‐Ray Angiography,” IEEE Transactions on Medical Imaging 42, no. 3 (2022): 864–879, https://doi.org/10.1109/TMI.2022.3219126.
X. Tang, H. Zhang, B. Xie, and X. Liu, “Temporally Consistent Segmentation of Main Coronary Artery in X‐Ray Coronary Angiography Sequences,” Expert Systems with Applications (2025): 126591, https://doi.org/10.1016/j.eswa.2025.126591.
G. Wei, X. Zeng, and Q. Zhang, “FlowVM‐Net: Enhanced Vessel Segmentation in X‐Ray Coronary Angiography Using Temporal Information Fusion,” Journal of imaging informatics in medicine (2025): 1–17, https://doi.org/10.1007/s10278‐025‐01732‐y.
H. Ren, D. Li, F. Jing, et al., “LASF: A Local Adaptive Segmentation Framework for Coronary Angiogram Segments,” Health Information Science and Systems 13 (2025): 19, https://doi.org/10.1007/s13755‐025‐00339‐5.
A. Qayyum, I. Ahmad, W. Mumtaz, M. Alassafi, R. Alghamdi, and M. Mazher, “Automatic Segmentation Using a Hybrid Dense Network Integrated With an 3D‐Atrous Spatial Pyramid Pooling Module for Computed Tomography (CT) Imaging,” IEEE Access 8 (2020): 169794–169803, https://doi.org/10.1109/ACCESS.2020.3024277.
M. Bilal, D. Martinho, R. Sim, et al., “Multivessel Coronary Artery Segmentation and Stenosis Localisation Using Ensemble Learning,” arXiv.org (2023).
O. Ronneberger, P. Fischer, and T. Brox, “U‐Net: Convolutional Networks for Biomedical Image Segmentation,” in International Conference on Medical Image Computing and Computer‐Assisted Intervention, (2015).
Y. Yang, S. Yue, and H. Quan, “Cs‐UNet: Cross‐Scale U‐Net With Semantic‐Position Dependencies for Retinal Vessel Segmentation,” Network: Computation in Neural Systems 35, no. 2 (April 2024): 134–153, https://doi.org/10.1080/0954898x.2023.2288858.
Z. Beevi Sulaiman, “Rp Squeeze U‐Segnet Model for Lesion Segmentation and Optimization Enabled Shufflenet Based Multi‐Level Severity Diabetic Retinopathy Classification,” Network: Computation in Neural Systems 36, no. 4 (October 2025): 1906–1939, https://doi.org/10.1080/0954898x.2024.2395375.
S. Li and Y. Fan, “Coronary Artery Segmentation in X‐Ray Angiography Based on Deep Learning Approach,” in 43rd Chinese Control Conference (CCC), (2024), 7345–7350.
O. Alirr, “Coronary Artery Segmentation in CTA Images: Evaluating Automated Segmentation of Coronary Arteries Using U‐Net Variants and Vesselness Enhancement,” European Journal of Pure and Applied Mathematics 18, no. 4 (2025): 6300, https://doi.org/10.29020/nybg.ejpam.v18i4.6300.
Y. Gao, Y. Wang, D. Ai, et al., “Iterative Joint Learning Integrating Temporal and Geometric Information for Vessel Segmentation in X‐Ray Coronary Angiography,” Medical Physics 53, no. 2 (2026): e70317, https://doi.org/10.1002/mp.70317.
X. Zhang, P. Lu, Z. Zheng, and W. Li, “HR‐UMamba++: A High‐Resolution Multi‐Directional Mamba Framework for Coronary Artery Segmentation in X‐Ray Coronary Angiography,” Fractal and Fractional 10, no. 1 (2026): 43, https://doi.org/10.3390/fractalfract10010043.
A. Sadanand and A. Roy, “Optic Disc Approximation Using an Ensemble of Processing Methods,” International Journal of Engineering Research and Technology (2016), https://doi.org/10.17577/IJERTV5IS090310.
T.‐Yi Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature Pyramid Networks for Object Detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition (2017), 936–944.
K. Zhang, Z. Li, H. Hu, et al., “Dynamic Feature Pyramid Networks for Detection,” in IEEE International Conference on Multimedia and Expo (2022), 1–6.
A. Kirillov, R. Girshick, K. He, and P. Dollár, “Panoptic Feature Pyramid Networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition (2019), 6392–6401.
Y. Quan, D. Zhang, L. Zhang, and J. Tang, “Centralized Feature Pyramid for Object Detection,” IEEE Transactions on Image Processing: A publication of the IEEE Signal Processing Society 32 (2023): 4341–4354, https://doi.org/10.1109/TIP.2023.3297408.
W. Wang, J. Zhong, H. Wu, Z. Wen, and J. Qin, “RVSeg‐Net: An Efficient Feature Pyramid Cascade Network for Retinal Vessel Segmentation,” in International Conference on Medical Image Computing and Computer‐Assisted Intervention (2020), 796–805.
Y. Ye, C. Pan, Y. Wu, S. Wang, and Y. Xia, “MFI‐Net: Multiscale Feature Interaction Network for Retinal Vessel Segmentation,” IEEE Journal of Biomedical and Health Informatics 26, no. 9 (2022): 4551–4562, https://doi.org/10.1109/JBHI.2022.3182471.
F. Li, Y. Liu, J.Bo Qi, et al., “PS5‐Net: A Medical Image Segmentation Network With Multiscale Resolution,” Journal of Medical Imaging 11, no. 1 (2024), https://doi.org/10.1117/1.jmi.11.1.014008.
S. Wazir and D. Kim, “Rethinking the Nested U‐Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion,” arXiv.org (2025).
B. Liang, C. Tang, M. Xu, T. Wu, and Z. Lei, “Fusion Network Based on the Dual Attention Mechanism and Atrous Spatial Pyramid Pooling for Automatic Segmentation in Retinal Vessel Images,” Journal of The Optical Society of America A‐Optics Image Science and Vision (2022), https://doi.org/10.1364/JOSAA.459912.
Q. Yang, M. Liu, X. Chen, and Y. Feng, “Stenosis‐YOLO: Semisupervised YOLOv8 With Edge Enhancement and Hierarchical Feature Fusion for Coronary Stenosis Segmentation,” Journal of imaging informatics in medicine (2026), https://doi.org/10.1007/s10278‐026‐01883‐6.
T. Xiao, Y. Liu, B. Zhou, Y. Jiang, and J. Sun, “Unified Perceptual Parsing for Scene Understanding,” in European Conference on Computer Vision (2018), 432–448.
H. Kim, Ye Ju Kim, J. Hong, H. Yang, S. Euna, and K. Lee, “Local Context Aggregation for Semantic Segmentation: A Novel Pspnet Approach,” in 2024 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC‐CSCC) (2024), 1–5.
L. Mou, Y. Zhao, Li Chen, et al., “CS‐Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation,” in International Conference on Medical Image Computing and Computer‐Assisted Intervention (2019).
E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Álvarez, and P. Luo, “SegFormer: Simple and Efficient Design for Semantic Segmentation With Transformers,” in Proceedings of the 35th International Conference on Neural Information Processing Systems (Curran Associates Inc., 2021).
J. Chen, Y. Lu, Q. Yu, et al., “TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation,” arXiv.org (2021).
R. Yang, K. Liu, S. Xu, J. Yin, and Z. Zhang, “ViT‐UperNet: A Hybrid Vision Transformer With Unified‐Perceptual‐Parsing Network for Medical Image Segmentation,” Complex & Intelligent Systems 10 (2024): 3819–3831, https://doi.org/10.1007/s40747‐024‐01359‐6.
X. Tan, X. Chen, Q. Meng, et al., “OCT2Former: A Retinal OCT‐Angiography Vessel Segmentation Transformer,” Computer Methods and Programs in Biomedicine 233 (2023): 107454, https://doi.org/10.1016/j.cmpb.2023.107454.
W. Zhao, X. Wang, Y. Zhang, L. Zhang, Z. Xu, and C. Ling, “KDAU‐Net: KAN‐Based Dynamic Attention U‐Net With Global‐Local Fusion for Robust Skin‐Lesion Segmentation,” in Asia Conference on Computer Vision, Image Processing and Pattern Recognition (2025).
I. Bakkouri and S. Bakkouri, “UGS‐M3F: Unified Gated Swin Transformer With Multi‐Feature Fully Fusion for Retinal Blood Vessel Segmentation,” BMC Medical Imaging 25, no. 1 (2025): 77, https://doi.org/10.1186/s12880‐025‐01616‐1.
H. Tang, N. Que, Y. Tian, M. Li, A. Perelli, and Y. Teng, “MLAR‐UNet: LDCT Image Denoising Based on U‐Net With Multiple Lightweight Attention‐Based Modules and Residual Reinforcement,” Physics in Medicine and Biology 70, no. 4 (2025): 045021, https://doi.org/10.1088/1361‐6560/adb19a.
J. Zhuang, “LadderNet: Multi‐Path Networks Based on U‐Net for Medical Image Segmentation,” arXiv.org (2018).
M. Alom, M. Hasan, C. Yakopcic, T. Taha, and V. Asari, “Recurrent Residual Convolutional Neural Network Based on U‐Net (R2U‐Net) for Medical Image Segmentation,” arXiv.org (2018).
M. Alom, C. Yakopcic, M. Hasan, T. Taha, and V. Asari, “Recurrent Residual U‐Net for Medical Image Segmentation,” Journal of Medical Imaging 6, no. 1 (2019): 014006, https://doi.org/10.1117/1.jmi.6.1.014006.
D. Jha, P. Smedsrud, M. Riegler, et al., “ResUNet++: An Advanced Architecture for Medical Image Segmentation,” in IEEE International Symposium on Multimedia (2019), 225–230.
D. Jha, P. H. Smedsrud, D. Johansen, et al., “A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test‐Time Augmentation,” IEEE Journal of Biomedical and Health Informatics 25, no. 6 (2021): 2029–2040, https://doi.org/10.1109/jbhi.2021.3049304.
W. Song, N. Zheng, X. Liu, L. Qiu, and R. Zheng, “An Improved U‐Net Convolutional Networks for Seabed Mineral Image Segmentation,” IEEE Access (2019): 82744–82752, https://doi.org/10.1109/ACCESS.2019.2923753.
A. Jansson, E. Humphrey, N. Montecchio, R. Bittner, A. Kumar, and T. Weyde, “Singing Voice Separation With Deep U‐Net Convolutional Networks,” in International Society for Music Information Retrieval Conference, (2017).
J. Yang, Y. Zhang, Y. Yu, and N. Zhong, “Nested U‐Net Architecture Based Image Segmentation for 3D Neuron Reconstruction,” Journal of Medical Imaging and Health Informatics 11, no. 5 (2021): 1348–1356, https://doi.org/10.1166/jmihi.2021.3379.
G.‐X. Xu and C.‐X. Ren, “SPNet: A Novel Deep Neural Network for Retinal Vessel Segmentation Based on Shared Decoder and Pyramid‐Like Loss,” Neurocomputing 523 (2023): 199–212, https://doi.org/10.1016/j.neucom.2022.12.039.
T. Luo, J. Zhang, T. Chen, et al., “Artifact‐Suppressed 3D Retinal Microvascular Segmentation via Multi‐Scale Topology Regulation,” Medical Image Analysis 110 (2026): 103988, https://doi.org/10.1016/j.media.2026.103988.
M. Shafiei Neyestanak, H. Jahani, M. Khodarahmi, et al., “A Quantitative Comparison Between Focal Loss and Binary Cross‐Entropy Loss in Brain Tumor Auto‐Segmentation Using U‐Net,” Journal of biostatistics and epidemiology (2025), https://doi.org/10.18502/jbe.v11i1.19315.
I.‐K. Lee, J. Shin, Y.‐H. Lee, J. Ku, and H.‐W. Kim, eds, SSASS: Semi‐Supervised Approach for Stenosis Segmentation (2023) arXiv.org.
M. Atwany, M. Lashgari, R. P. Choudhury, and A. Banerjee, “Domain‐Specific Progressive Channel Dropout: Single‐Source Domain Generalization for Vessel Segmentation in X‐Ray Coronary Angiography,” in Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2025), 1–5.
A. Norouziazad, F. Esmaeildoost, B. Homam, and R. Salahandish, “Grey Wolf Optimizer Enhances Adaptive Atrous Spatial Pyramid Pooling for Efficient Multi‐Scale Feature Selection in Medical Image Segmentation,” in Annual Computers, Software, and Applications Conference (COMPSAC) (2025), 1571–1576.
C. Chen, Z. Zou, C. Zhao, Z. Gao, and J. Tian, “U2Net R+: A Method for MRI Image Segmentation of the Patellar Ligament Based on the Pyramid Pooling Module and Reverse Attention Mechanism,” in 2025 IEEE 3rd International Conference on Control, Electronics and Computer Technology (ICCECT) (2025), 1337–1342.
Z. Wang, S. Fu, H. Zhang, et al., “Dual‐Branch Dynamic Hierarchical U‐Net With Multi‐Layer Space Fusion Attention for Medical Image Segmentation,” Scientific Reports 15 (2025): 8194, https://doi.org/10.1038/s41598‐025‐92715‐0.
G. Zheng, P. Bo, L. Liu, Z. Cong, K. Tang, and C. Zhang, “CoroSAM: Enhancing SAM With Frequency and Orientation Awareness for Coronary Artery Segmentation in X‐Ray Angiography,” in IEEE International Conference on Bioinformatics and Biomedicine (2025), 3349–3356.
M. Farouk Shabrawi, D. Elmenshawy, ElS. Farag, and W. Ali, “Correlation Between B‐Type Natriuretic Peptide and Syntax Score in Patients of Multivessel Coronary Artery Disease Presented With Acute Coronary Syndrome,” Egyptian Journal of Hospital Medicine 101 (2025): 5308–5317, https://doi.org/10.21608/ejhm.2025.461632.
H. Li, B. Chen, G.‐C. Wang, Y.‐X. Wang, and Y. Yang, “Predicting Coronary Artery Lesion Severity Using Pulse Wave Harmonics: A SYNTAX Score‐Based Study,” Current Cardiology Reviews 22, no. 1 (2025): e1573403X400522, https://doi.org/10.2174/011573403x400522250519073551.
L. Lin, Y. Zheng, Y. Li, et al., “Automatic Vessel Segmentation and Reformation of Non‐Contrast Coronary Magnetic Resonance Angiography Using Transfer Learning‐Based Three‐Dimensional U‐Net With Attention Mechanism,” Journal of Cardiovascular Magnetic Resonance 27, no. 1 (2025): 101126, https://doi.org/10.1016/j.jocmr.2024.101126.
J. Chooi, K. Cong, R. Li, and L. Sun, “DP‐AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning,” arXiv.org (2025).
Z. Zhou, Md M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U‐Net Architecture for Medical Image Segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (2018), 3–11.
L.‐C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder‐Decoder With Atrous Separable Convolution for Semantic Image Segmentation,” in Computer Vision—ECCV 2018 (2018), 833–851.
Entry Date(s): Date Created: 20260728 Date Completed: 20260729 Latest Revision: 20260730
Update Code: 20260730
PubMed Central ID: PMC13411197
DOI: 10.1002/rcs.70210
PMID: 42517604
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1478-596X
DOI:10.1002/rcs.70210