M2CA-Net: Multi-scale and multi-frequency channel attentional neural network for invasive coronary angiography segmentation

TY - JOUR

T1 - M2CA-Net

T2 - Multi-scale and multi-frequency channel attentional neural network for invasive coronary angiography segmentation

AU - Dai, Longhui

AU - Cao, Tongtong

AU - Zhang, Lei

AU - Wang, Yuanquan

AU - Gan, Feng

AU - Zhao, Di

N1 - Publisher Copyright: © International Federation for Medical and Biological Engineering 2025.

PY - 2026/2

Y1 - 2026/2

N2 - Accurate segmentation of invasive coronary angiography (ICA) images is crucial for diagnosing of coronary artery disease (CAD). While existing deep learning-based segmentation models have shown promising results, most operate solely in the spatial domain and overlook informative cues available in the frequency domain. To address this limitation, we design a multi-scale and multi-frequency channel attention neural network (M2CA-Net), which fuses spatial and frequency information to enhance ICA image segmentation. Specifically, we introduce a multi-frequency channel attention (MCA) block based on 2D discrete cosine transform (2D DCT) to extract global frequency representations, enhancing channel discrimination. Combined with multi-scale convolutions, this design facilitates effective fusion of spatial and frequency-domain features. We validate our model on both public and clinical datasets, where M2CA-Net achieves superior segmentation performance and outperforms several state-of-the-art architectures.

AB - Accurate segmentation of invasive coronary angiography (ICA) images is crucial for diagnosing of coronary artery disease (CAD). While existing deep learning-based segmentation models have shown promising results, most operate solely in the spatial domain and overlook informative cues available in the frequency domain. To address this limitation, we design a multi-scale and multi-frequency channel attention neural network (M2CA-Net), which fuses spatial and frequency information to enhance ICA image segmentation. Specifically, we introduce a multi-frequency channel attention (MCA) block based on 2D discrete cosine transform (2D DCT) to extract global frequency representations, enhancing channel discrimination. Combined with multi-scale convolutions, this design facilitates effective fusion of spatial and frequency-domain features. We validate our model on both public and clinical datasets, where M2CA-Net achieves superior segmentation performance and outperforms several state-of-the-art architectures.

KW - Invasive coronary angiography

KW - Multi-frequency

KW - Multi-scale

KW - Segmentation

UR - https://www.scopus.com/pages/publications/105019700635

U2 - 10.1007/s11517-025-03454-3

DO - 10.1007/s11517-025-03454-3

M3 - Article

AN - SCOPUS:105019700635

SN - 0140-0118

VL - 64

SP - 513

EP - 530

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

IS - 2

ER -