Feature reconstruction-based self-supervised learning model for vessel segmentation_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

ZHOU Bowen ¹ , SUN Hui ² , DIAO Kaiyue ¹ , XIA Qing ² ,  LI Kang ¹

1. West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
2. West China Hospital - Sensetime Joint Laboratory, Chengdu, 610213, P. R. China;

Corresponding author：

LI Kang, Email: likang@wchscu.cn

Keywords：

Vessel segmentation; self-supervised learning; histogram of oriented gradients

DOI：

10.7507/1007-4848.202504059

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To propose an innovative self-supervised learning method for vascular segmentation in computed tomography angiography (CTA) images by integrating feature reconstruction with masked autoencoding. Methods A 3D masked autoencoder-based framework is developed, where in 3D histogram of oriented gradients (HOG) is utilized for multi-scale vascular feature extraction. During pre-training, random masking is applied to local patches of CTA images, and the model is trained to jointly reconstruct original voxels and HOG features of masked regions. The pre-trained model is further fine-tuned on two annotated datasets for clinical-level vessel segmentation. Results Evaluated on two independent datasets (30 labeled CTA images each), our method achieves superior segmentation accuracy to the supervised neural network U-Net (nnU-Net) baseline, with dice similarity coefficients (DSC) of 91.2% vs. 89.7% (aorta) and 84.8% vs. 83.2% (coronary arteries). Conclusion The proposed self-supervised model significantly reduces manual annotation costs without compromising segmentation precision, showing substantial potential for enhancing clinical workflows in vascular disease management.

1.	Moccia S, De Momi E, El Hadji S, et al. Blood vessel segmentation algorithms – Review of methods, datasets and evaluation metrics. Comput Methods Programs Biomed, 2018, 158: 71-91.
2.	Chen D, Zhang X, Mei Y, et al. Multi-stage learning for segmentation of aortic dissections using a prior aortic anatomy simplification. Med Image Anal, 2021, 69: 101931.
3.	Pepe A, Li J, Rolf-Pissarczyk M, et al. Detection, segmentation, simulation and visualization of aortic dissections: A review. Med Image Anal, 2020, 65: 101773.
4.	Jie G, Tuo C, Jing Z, et al. A survey on self-supervised learning: Algorithms, applications, and future trends. IEEE Trans Pattern Anal Mach Intell, 2024, 46(12): 9052-9071.
5.	Kaiming H, Xinlei C, Saining X, et al. Masked autoencoders are scalable vision learners. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022: 15979-15988.
6.	Chen W, Haoqi F, Saining X, et al. Masked feature prediction for self-supervised visual pre-training. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022: 14648-14658.
7.	Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI, 2016: 424-432.
8.	Devvi S, Alhadi B. 3D-HOG features-based classification using MRI images to early diagnosis of Alzheimer’s disease. In: IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), Singapore, 2018: 457-462.
9.	How to evenly distribute points on a sphere more effectively than the canonical Fibonacci Lattice [Online]. Accessed on 2025-02-04.
10.	Ali H, Yucheng T, Vishwesh N, et al. UNETR: Transformers for 3D medical image segmentation. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2022: 1748-1758.
11.	Jia D, Wei D, Richard S, et al. ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 248-255.
12.	Alexey D, Lucas B, Alexander K, et al. An image is worth 16×16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations, 2021.
13.	Xiaoya L, Xiaofei S, Yuxian M, et al. Dice loss for data-imbalanced NLP tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 465-476.
14.	Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods, 2021, 18(2): 203-211.

1. Moccia S, De Momi E, El Hadji S, et al. Blood vessel segmentation algorithms – Review of methods, datasets and evaluation metrics. Comput Methods Programs Biomed, 2018, 158: 71-91.
2. Chen D, Zhang X, Mei Y, et al. Multi-stage learning for segmentation of aortic dissections using a prior aortic anatomy simplification. Med Image Anal, 2021, 69: 101931.
3. Pepe A, Li J, Rolf-Pissarczyk M, et al. Detection, segmentation, simulation and visualization of aortic dissections: A review. Med Image Anal, 2020, 65: 101773.
4. Jie G, Tuo C, Jing Z, et al. A survey on self-supervised learning: Algorithms, applications, and future trends. IEEE Trans Pattern Anal Mach Intell, 2024, 46(12): 9052-9071.
5. Kaiming H, Xinlei C, Saining X, et al. Masked autoencoders are scalable vision learners. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022: 15979-15988.
6. Chen W, Haoqi F, Saining X, et al. Masked feature prediction for self-supervised visual pre-training. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022: 14648-14658.
7. Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI, 2016: 424-432.
8. Devvi S, Alhadi B. 3D-HOG features-based classification using MRI images to early diagnosis of Alzheimer’s disease. In: IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), Singapore, 2018: 457-462.
9. How to evenly distribute points on a sphere more effectively than the canonical Fibonacci Lattice [Online]. Accessed on 2025-02-04.
10. Ali H, Yucheng T, Vishwesh N, et al. UNETR: Transformers for 3D medical image segmentation. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2022: 1748-1758.
11. Jia D, Wei D, Richard S, et al. ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 248-255.
12. Alexey D, Lucas B, Alexander K, et al. An image is worth 16×16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations, 2021.
13. Xiaoya L, Xiaofei S, Yuxian M, et al. Dice loss for data-imbalanced NLP tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 465-476.
14. Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods, 2021, 18(2): 203-211.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Latest ArticlesFeature reconstruction-based self-supervised learning model for vessel segmentation

Abstract Full text Figures/Tables Video References Cited by

Format

Content