Saruhan Eda Nur, Ozturk Hakancan, Kul Demet, Sevgin Bortecine, Coban Merve Nur, Pekkan Kerem
Computer Science and Engineering, Koç University, Rumelifeneri, Istanbul, 34450, Turkey.
Computational Science and Engineering, Imperial College, London, SW7 2AZ, UK.
Biomed Opt Express. 2025 Jul 22;16(8):3315-3336. doi: 10.1364/BOE.563643. eCollection 2025 Aug 1.
Fibrous proteins, such as elastin and collagen, are crucial for the structural integrity of the cardiovascular system. For thin tissue-engineered heart valves and surgical patches, the two-dimensional mapping of fiber orientation is well-established. However, for three-dimensional (3D) thick tissue samples, e.g., the embryonic whole heart, robust 3D fiber analysis tools are not available. This information is essential for computational vascular modeling and tissue microstructure characterization. Therefore, this study employs machine learning (ML) and deep learning (DL) techniques to analyze the 3D cardiovascular fiber structures in thick samples of porcine pericardium and embryonic whole hearts. It is hypothesized that ML/DL-based fiber orientation analysis will outperform traditional Fourier transform and directional filter methods by offering higher spatial accuracy and reduced dependency on manual preprocessing. We trained our ML/DL models on both synthetic and real-world cardiovascular datasets obtained from confocal imaging. The evaluation used a mixed dataset of 1200 samples and a porcine/bovine dataset of 400 samples. Support vector regression (SVR) demonstrated the highest accuracy, achieving a normalized mean absolute error (nMAE) of 5.0% on the mixed dataset and 13.0% on the biological dataset. Among DL models, convolutional neural network (CNN) and residual network-50 (ResNet50) had an nMAE of 12.0% and 11.0% on the mixed dataset and 23.0% and 22.0% on the biological dataset, respectively. Attention mechanisms improved performance further, with the channel attention ResNet50 achieving an nMAE of 5.8% on the mixed dataset and 21.0% on the biological dataset. These findings highlight the potential of ML and DL techniques in improving 3D fiber orientation detection, enabling detailed cardiovascular microstructural assessment.
纤维蛋白,如弹性蛋白和胶原蛋白,对心血管系统的结构完整性至关重要。对于薄的组织工程心脏瓣膜和手术补片,纤维取向的二维映射已经很成熟。然而,对于三维(3D)厚组织样本,例如胚胎全心脏,强大的3D纤维分析工具尚不可用。这些信息对于计算血管建模和组织微观结构表征至关重要。因此,本研究采用机器学习(ML)和深度学习(DL)技术来分析猪心包和胚胎全心脏厚样本中的3D心血管纤维结构。据推测,基于ML/DL的纤维取向分析将通过提供更高的空间精度和减少对手动预处理的依赖,优于传统的傅里叶变换和方向滤波方法。我们在从共聚焦成像获得的合成和真实世界心血管数据集上训练我们的ML/DL模型。评估使用了一个包含1200个样本的混合数据集和一个包含400个样本的猪/牛数据集。支持向量回归(SVR)表现出最高的准确率,在混合数据集上实现了5.0%的归一化平均绝对误差(nMAE),在生物数据集上实现了13.0%的归一化平均绝对误差。在DL模型中,卷积神经网络(CNN)和残差网络50(ResNet50)在混合数据集上的nMAE分别为12.0%和11.0%,在生物数据集上分别为23.0%和22.0%。注意力机制进一步提高了性能,通道注意力ResNet50在混合数据集上的nMAE为5.8%,在生物数据集上为21.0%。这些发现突出了ML和DL技术在改善3D纤维取向检测方面的潜力,能够实现详细的心血管微观结构评估。