A Deep-Learning and Bio-inspired Vision Model-Based Approach for Automatic Coronary Arteries Segmentation
Journal
2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM)
Publisher
IEEE
Date Issued
2025
Author(s)
López-Figueroa, Alberto
Gomez-Coronel, Sandra L.
Renza, Diego
Aguilera-Hernandez, Edgar I.
Cruz-Aceves, Ivan
Type
text::conference output::conference proceedings
Abstract
The accurate segmentation of coronary arteries from X-ray angiograms is critical for the diagnosis and treatment of cardiovascular diseases. Yet, it remains a challenging task due to low image contrast and complex vessel structures. This paper introduces a novel hybrid methodology that combines a bio-inspired vision model, the Steered Hermite Transform (SHT), with a deep learning architecture for robust vessel segmentation. We leverage the SHT to decompose each angiogram into a rich, multi-resolution set of 15 feature maps that capture local image structures at different scales and orientations. These Hermite coefficients, along with the original image, form a 16-channel input tensor used to train a U-Net. This approach enables the network to learn from an enhanced feature space that explicitly represents vessel-like patterns. Evaluated on a public dataset of 134 coronary angiograms, our model demonstrates outstanding performance, achieving an Area Under the Curve (AUC) of 0.9872. The results confirm that enriching the input of a deep neural network with SHT coefficients significantly improves its ability to identify and segment complex vascular networks accurately. ©The authors ©IEEE.
License
Acceso Restringido
How to cite
Lopez-Figueroa, A., Brieva, J., Moya-Albor, E., Gomez-Coronel, S. L., Renza, D., Aguilera-Hernandez, E. I., & Cruz-Aceves, I. (2025). A Deep-Learning and Bio-inspired Vision Model-Based Approach for Automatic Coronary Arteries Segmentation. In 2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM) (pp. 1–2). IEEE. 2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM). https://doi.org/10.1109/sipaim67325.2025.11283215