Scholarlink

<p> 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 (<InlineEquation ID="IEq5"> <EquationSource Format="TEX">\({M}^{2}CA\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mrow> <mi>M</mi> </mrow> <mn>2</mn> </msup> <mi>C</mi> <mi>A</mi> </mrow> </math></EquationSource> </InlineEquation>-<InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(Net\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi mathvariant="italic">Net</mi> </mrow> </math></EquationSource> </InlineEquation>), 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 <InlineEquation ID="IEq7"> <EquationSource Format="TEX">\({M}^{2}CA\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mrow> <mi>M</mi> </mrow> <mn>2</mn> </msup> <mi>C</mi> <mi>A</mi> </mrow> </math></EquationSource> </InlineEquation>-<InlineEquation ID="IEq8"> <EquationSource Format="TEX">\(Net\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi mathvariant="italic">Net</mi> </mrow> </math></EquationSource> </InlineEquation> achieves superior segmentation performance and outperforms several state-of-the-art architectures.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

\({{{M}}}^{2}{{C}}{{A}}\)-\({{N}}{{e}}{{t}}\): Multi-scale and multi-frequency channel attentional neural network for invasive coronary angiography segmentation

  • 期刊论文

  • 发表日期：

    2025年10月26日

查看全文
  • Longhui Dai,
  • Tongtong Cao,
  • Lei Zhang,
  • Yuanquan Wang,
  • Feng Gan,
  • Di Zhao

摘要

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 ( \({M}^{2}CA\) M 2 C A - \(Net\) 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 \({M}^{2}CA\) M 2 C A - \(Net\) Net achieves superior segmentation performance and outperforms several state-of-the-art architectures.

Graphical Abstract