A reweighted graph matching-based algorithm for automatic extraction of corresponding landmarks in medical images_Journal of Biomedical Engineering

Authors：

XU Yi , JIANG Zhengang , SHI Weili , MIAO Yu ,  YANG Huamin

School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, P. R. China;

Corresponding?author：

YANG Huamin, Email: yhm@cust.edu.cn

Keywords：

Medical image registration; Registration error evaluation; Graph matching; Landmark matching; Local similarity

DOI：

10.7507/1001-5515.202510040

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In the field of medical image registration, corresponding landmarks can serve as an crucial reference for the quantitative evaluation of registration algorithm errors. However, the corresponding landmarks extracted by existing methods generally lack anatomical correspondence. While some approaches have begun to take bifurcation points of tubular structures as landmarks, the establishment of accurate one-to-one correspondences between these points is hindered by highly similar local features and missing correspondences, thereby impeding effective quantification of registration errors. To address these limitations, this paper proposes a reweighted graph matching-based algorithm for automatic extraction of corresponding landmarks in medical images. First, the bifurcation points of tubular structures with anatomical correspondence are extracted as landmarks. Secondly, to address the issues of highly similar local features and missing correspondences, a reweighted graph matching model is constructed base on a local similarity strategy and a modality independent neighborhood descriptor, which iteratively identifies correct matches and rectifies mismatches to progressively refine the correspondence between landmarks. Finally, the K-nearest neighbor graph of landmarks is dynamically updated, and outlier matches are filtered based on a local similarity strategy, thereby achieving accurate landmark matching under partial correspondence conditions. Experimental results on two public datasets demonstrate that the proposed method can accurately extract corresponding landmarks and effectively evaluate registration error, thereby providing technical support for enhancing the reliability of medical image registration algorithms in clinical applications.

Citation： XU Yi, JIANG Zhengang, SHI Weili, MIAO Yu, YANG Huamin. A reweighted graph matching-based algorithm for automatic extraction of corresponding landmarks in medical images. Journal of Biomedical Engineering, 2026, 43(3): 461-470. doi: 10.7507/1001-5515.202510040 Copy

1.	Xiao H, Xue X, Zhu M, et al. Deep learning-based lung image registration: a review. Comput Biol Med, 2023, 165: 107434.
2.	Liang X, Lin S, Liu F, et al. ORRN: an ODE-based recursive registration network for deformable respiratory motion estimation with lung 4DCT images. IEEE Trans Biomed Eng, 2023, 70(12): 3265-3276.
3.	Kolenbrander I D, Maspero M, Hendriksen A A, et al. Deep-learning-based joint rigid and deformable contour propagation for magnetic resonance imaging-guided prostate radiotherapy. Med Phys, 2024, 51(4): 2367-2377.
4.	Bosma L S, Zachiu C, Denis de Senneville B, et al. Intensity-based quality assurance criteria for deformable image registration in image-guided radiotherapy. Med Phys, 2023, 50(9): 5715-5722.
5.	Zhou Z, Yin P, Liu Y, et al. Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning. Med Biol Eng Comput, 2024, 62(9): 2669-2686.
6.	Bierbrier J, Gueziri H E, Collins D L. Estimating medical image registration error and confidence: a taxonomy and scoping review. Med Image Anal, 2022, 81: 102531.
7.	Nenoff L, Amstutz F, Murr M, et al. Review and recommendations on deformable image registration uncertainties for radiotherapy applications. Phys Med Biol, 2023, 68(24): 24TR01.
8.	劉鈺煜, 王麗, 高燕萍, 等. 肺癌放療中基于四維計算機斷層掃描通氣成像的放射性肺炎預測研究進展. 生物醫學工程學雜志, 2025, 42(4): 863-870.
9.	李雪, 許青, 俞雅. 肺部腫瘤放療中影像配準算法應用研究. 中國醫學計算機成像雜志, 2026, 32(2): 271-275.
10.	Muenzing S E A, Ginneken B, Viergever M, et al. DIRBoost-an algorithm for boosting deformable image registration: application to lung CT intra-subject registration. Med Image Anal, 2014, 18(3): 449-459.
11.	Chen J, Liu Y, Wei S, et al. A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond. Med Image Anal, 2025, 100: 103385.
12.	Yang D, Zhang M, Chang X, et al. A method to detect landmark pairs accurately between intra-patient volumetric medical images. Med Phys, 2017, 44(11): 5859-5872.
13.	Bhat I, Kuijf H J, Viergever M A, et al. Influence of learned landmark correspondences on lung CT registration. Med Phys, 2024, 51(8): 5321-5336.
14.	Ma J, Jiang X, Fan A, et al. Image matching from handcrafted to deep features: a survey. Int J Comput Vis, 2021, 129(1): 23-79.
15.	Yu J, Chang J, He J, et al. Adaptive spot-guided transformer for consistent local feature matching//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver: IEEE, 2023: 21898-21908.
16.	Wei X, Ge L, Huang L, et al. Unsupervised non-rigid histological image registration guided by keypoint correspondences based on learnable deep features with iterative training. IEEE Trans Med Imaging, 2024, 44(1): 447-461.
17.	Cai N, Chen H, Li Y, et al. Reducing non-realistic deformations in registration using precise and reliable landmark correspondences. Comput Biol Med, 2019, 115: 103515.
18.	Rühaak J, Polzin T, Heldmann S, et al. Estimation of large motion in lung CT by integrating regularized keypoint correspondences into dense deformable registration. IEEE Trans Med Imaging, 2017, 36(8): 1746-1757.
19.	譚振霖, 郭圣文. 基于關鍵點的超聲圖像與磁共振圖像多分辨率離散優化配準方法. 生物醫學工程學雜志, 2023, 40(2): 202-207.
20.	Grewal M, Deist T M, Wiersma J, et al. An end-to-end deep learning approach for landmark detection and matching in medical images//Medical Imaging 2020: Image Processing, Houston: SPIE, 2020, 11313: 548-557.
21.	Grewal M, Wiersma J, Westerveld H, et al. Automatic landmark correspondence detection in medical images with an application to deformable image registration. J Med Imaging, 2023, 10(1): 014007.
22.	Wang A Q, Evan M Y, Dalca A V, et al. A robust and interpretable deep learning framework for multi-modal registration via keypoints. Med Image Anal, 2023, 90: 102962.
23.	Billot B, Muthukrishnan R, Abaci T E, et al. Spatial regularisation for improved accuracy and interpretability in keypoint-based registration//28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Daejeon: Springer Nature Switzerland, 2025: 583-593.
24.	Matkovic L, Lei Y, Fu Y, et al. Deformable lung 4DCT image registration via landmark-driven cycle network. Med Phys, 2024, 51(3): 1974-1984.
25.	Hansen L, Heinrich M P. GraphRegNet: deep graph regularisation networks on sparse keypoints for dense registration of 3D lung CTs. IEEE Trans Med Imaging, 2021, 40(9): 2246-2257.
26.	Sindel A, Hohberger B, Maier A, et al. Multi-modal retinal image registration using a keypoint-based vessel structure aligning network//25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Singapore: Springer Nature Switzerland, 2022: 108-118.
27.	Liu L, Fan X, Liu H, et al. QUIZ: an arbitrary volumetric point matching method for medical image registration. Comput Med Imaging Graph, 2024, 112: 102336.
28.	Jin H, Shen Y, Lou J, et al. KeypointDETR: an end-to-end 3D keypoint detector//18th European Conference on Computer Vision (ECCV), Milan: Springer Nature Switzerland, 2024: 374-390.
29.	Salari S, Rasoulian A, Rivaz H, et al. Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning//26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vancouver: Springer Nature Switzerland, 2023: 668-678.
30.	Rivas-Villar D, Hervella á S, Rouco J, et al. ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration. Med Biol Eng Comput, 2024, 62(12): 3721-3736.
31.	Wang Y, Wang X, Gu Z, et al. Superjunction: learning-based junction detection for retinal image registration//Proceedings of the 38th AAAI Conference on Artificial Intelligence, Vancouver: AAAI, 2024, 38(1): 292-300.
32.	Cazoulat G, Anderson B M, McCulloch M M, et al. Detection of vessel bifurcations in CT scans for automatic objective assessment of deformable image registration accuracy. Med Phys, 2021, 48(10): 5935-5946.
33.	Liu J, Li X, Wei Q, et al. Semi-supervised keypoint detector and descriptor for retinal image matching//17th European Conference on Computer Vision (ECCV), Tel Aviv: Springer Nature Switzerland, 2022: 593-609.
34.	Wang G, Huang Y, Ma K, et al. Automatic vessel crossing and bifurcation detection based on multi-attention network vessel segmentation and directed graph search. Comput Biol Med, 2023, 155: 106647.
35.	Zhu J, Li H, Ai D, et al. Iterative closest graph matching for non-rigid 3D/2D coronary arteries registration. Comput Methods Programs Biomed, 2021, 199: 105901.
36.	Xu Y, Yang H, Jiang Z, et al. MGASM-Net: morphology-guided multi-task learning network with anatomic spatial mamba for 3D airway segmentation. Complex Intell Syst, 2025, 11(8): 360.
37.	Lee T C, Kashyap R L, Chu C N. Building skeleton models via 3-D medial surface axis thinning algorithms. CVGIP Graph Models Image Process, 1994, 56(6): 462-478.
38.	Crouse D F. On implementing 2D rectangular assignment algorithms. IEEE Trans Aerosp Electron Syst, 2016, 52(4): 1679-1696.
39.	Heinrich M P, Jenkinson M, Bhushan M, et al. MIND: modality independent neighbourhood descriptor for multi-modal deformable registration. Med Image Anal, 2012, 16(7): 1423-1435.
40.	Criscuolo E R, Fu Y, Hao Y, et al. A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms. Med Phys, 2024, 51(5): 3806-3817.
41.	Zhang Z, Criscuolo E R, Hao Y, et al. A comprehensive liver CT landmark pair dataset for evaluating deformable image registration algorithms. arXiv, 2024: 2404.04427.

1. Xiao H, Xue X, Zhu M, et al. Deep learning-based lung image registration: a review. Comput Biol Med, 2023, 165: 107434.
2. Liang X, Lin S, Liu F, et al. ORRN: an ODE-based recursive registration network for deformable respiratory motion estimation with lung 4DCT images. IEEE Trans Biomed Eng, 2023, 70(12): 3265-3276.
3. Kolenbrander I D, Maspero M, Hendriksen A A, et al. Deep-learning-based joint rigid and deformable contour propagation for magnetic resonance imaging-guided prostate radiotherapy. Med Phys, 2024, 51(4): 2367-2377.
4. Bosma L S, Zachiu C, Denis de Senneville B, et al. Intensity-based quality assurance criteria for deformable image registration in image-guided radiotherapy. Med Phys, 2023, 50(9): 5715-5722.
5. Zhou Z, Yin P, Liu Y, et al. Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning. Med Biol Eng Comput, 2024, 62(9): 2669-2686.
6. Bierbrier J, Gueziri H E, Collins D L. Estimating medical image registration error and confidence: a taxonomy and scoping review. Med Image Anal, 2022, 81: 102531.
7. Nenoff L, Amstutz F, Murr M, et al. Review and recommendations on deformable image registration uncertainties for radiotherapy applications. Phys Med Biol, 2023, 68(24): 24TR01.
8. 劉鈺煜, 王麗, 高燕萍, 等. 肺癌放療中基于四維計算機斷層掃描通氣成像的放射性肺炎預測研究進展. 生物醫學工程學雜志, 2025, 42(4): 863-870.
9. 李雪, 許青, 俞雅. 肺部腫瘤放療中影像配準算法應用研究. 中國醫學計算機成像雜志, 2026, 32(2): 271-275.
10. Muenzing S E A, Ginneken B, Viergever M, et al. DIRBoost-an algorithm for boosting deformable image registration: application to lung CT intra-subject registration. Med Image Anal, 2014, 18(3): 449-459.
11. Chen J, Liu Y, Wei S, et al. A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond. Med Image Anal, 2025, 100: 103385.
12. Yang D, Zhang M, Chang X, et al. A method to detect landmark pairs accurately between intra-patient volumetric medical images. Med Phys, 2017, 44(11): 5859-5872.
13. Bhat I, Kuijf H J, Viergever M A, et al. Influence of learned landmark correspondences on lung CT registration. Med Phys, 2024, 51(8): 5321-5336.
14. Ma J, Jiang X, Fan A, et al. Image matching from handcrafted to deep features: a survey. Int J Comput Vis, 2021, 129(1): 23-79.
15. Yu J, Chang J, He J, et al. Adaptive spot-guided transformer for consistent local feature matching//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver: IEEE, 2023: 21898-21908.
16. Wei X, Ge L, Huang L, et al. Unsupervised non-rigid histological image registration guided by keypoint correspondences based on learnable deep features with iterative training. IEEE Trans Med Imaging, 2024, 44(1): 447-461.
17. Cai N, Chen H, Li Y, et al. Reducing non-realistic deformations in registration using precise and reliable landmark correspondences. Comput Biol Med, 2019, 115: 103515.
18. Rühaak J, Polzin T, Heldmann S, et al. Estimation of large motion in lung CT by integrating regularized keypoint correspondences into dense deformable registration. IEEE Trans Med Imaging, 2017, 36(8): 1746-1757.
19. 譚振霖, 郭圣文. 基于關鍵點的超聲圖像與磁共振圖像多分辨率離散優化配準方法. 生物醫學工程學雜志, 2023, 40(2): 202-207.
20. Grewal M, Deist T M, Wiersma J, et al. An end-to-end deep learning approach for landmark detection and matching in medical images//Medical Imaging 2020: Image Processing, Houston: SPIE, 2020, 11313: 548-557.
21. Grewal M, Wiersma J, Westerveld H, et al. Automatic landmark correspondence detection in medical images with an application to deformable image registration. J Med Imaging, 2023, 10(1): 014007.
22. Wang A Q, Evan M Y, Dalca A V, et al. A robust and interpretable deep learning framework for multi-modal registration via keypoints. Med Image Anal, 2023, 90: 102962.
23. Billot B, Muthukrishnan R, Abaci T E, et al. Spatial regularisation for improved accuracy and interpretability in keypoint-based registration//28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Daejeon: Springer Nature Switzerland, 2025: 583-593.
24. Matkovic L, Lei Y, Fu Y, et al. Deformable lung 4DCT image registration via landmark-driven cycle network. Med Phys, 2024, 51(3): 1974-1984.
25. Hansen L, Heinrich M P. GraphRegNet: deep graph regularisation networks on sparse keypoints for dense registration of 3D lung CTs. IEEE Trans Med Imaging, 2021, 40(9): 2246-2257.
26. Sindel A, Hohberger B, Maier A, et al. Multi-modal retinal image registration using a keypoint-based vessel structure aligning network//25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Singapore: Springer Nature Switzerland, 2022: 108-118.
27. Liu L, Fan X, Liu H, et al. QUIZ: an arbitrary volumetric point matching method for medical image registration. Comput Med Imaging Graph, 2024, 112: 102336.
28. Jin H, Shen Y, Lou J, et al. KeypointDETR: an end-to-end 3D keypoint detector//18th European Conference on Computer Vision (ECCV), Milan: Springer Nature Switzerland, 2024: 374-390.
29. Salari S, Rasoulian A, Rivaz H, et al. Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning//26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vancouver: Springer Nature Switzerland, 2023: 668-678.
30. Rivas-Villar D, Hervella á S, Rouco J, et al. ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration. Med Biol Eng Comput, 2024, 62(12): 3721-3736.
31. Wang Y, Wang X, Gu Z, et al. Superjunction: learning-based junction detection for retinal image registration//Proceedings of the 38th AAAI Conference on Artificial Intelligence, Vancouver: AAAI, 2024, 38(1): 292-300.
32. Cazoulat G, Anderson B M, McCulloch M M, et al. Detection of vessel bifurcations in CT scans for automatic objective assessment of deformable image registration accuracy. Med Phys, 2021, 48(10): 5935-5946.
33. Liu J, Li X, Wei Q, et al. Semi-supervised keypoint detector and descriptor for retinal image matching//17th European Conference on Computer Vision (ECCV), Tel Aviv: Springer Nature Switzerland, 2022: 593-609.
34. Wang G, Huang Y, Ma K, et al. Automatic vessel crossing and bifurcation detection based on multi-attention network vessel segmentation and directed graph search. Comput Biol Med, 2023, 155: 106647.
35. Zhu J, Li H, Ai D, et al. Iterative closest graph matching for non-rigid 3D/2D coronary arteries registration. Comput Methods Programs Biomed, 2021, 199: 105901.
36. Xu Y, Yang H, Jiang Z, et al. MGASM-Net: morphology-guided multi-task learning network with anatomic spatial mamba for 3D airway segmentation. Complex Intell Syst, 2025, 11(8): 360.
37. Lee T C, Kashyap R L, Chu C N. Building skeleton models via 3-D medial surface axis thinning algorithms. CVGIP Graph Models Image Process, 1994, 56(6): 462-478.
38. Crouse D F. On implementing 2D rectangular assignment algorithms. IEEE Trans Aerosp Electron Syst, 2016, 52(4): 1679-1696.
39. Heinrich M P, Jenkinson M, Bhushan M, et al. MIND: modality independent neighbourhood descriptor for multi-modal deformable registration. Med Image Anal, 2012, 16(7): 1423-1435.
40. Criscuolo E R, Fu Y, Hao Y, et al. A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms. Med Phys, 2024, 51(5): 3806-3817.
41. Zhang Z, Criscuolo E R, Hao Y, et al. A comprehensive liver CT landmark pair dataset for evaluating deformable image registration algorithms. arXiv, 2024: 2404.04427.

Journal of Biomedical Engineering

A reweighted graph matching-based algorithm for automatic extraction of corresponding landmarks in medical images

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content