Brandt Danja, Nikishina Anastasiia A, Bias Anne, Günther Robert, Hauser Anja E, Duda Georg N, Beckers Ingeborg E, Niesner Raluca A
German Rheumatology Research Center, a Leibniz-Institute (DRFZ), Biophysical Analytics, Berlin, Germany.
Freie Universität Berlin, Dynamic and Functional in vivo Imaging, Department of Veterinary Medicine, Berlin, Germany.
J Biomed Opt. 2025 Aug;30(8):086001. doi: 10.1117/1.JBO.30.8.086001. Epub 2025 Aug 4.
Understanding the structural organization of biological tissues is critical for studying their function and response to physiological and pathological conditions. imaging techniques, such as multiphoton microscopy, enable high-resolution visualization of tissue architecture. However, automated orientation analysis remains challenging due to imaging noise, complexity, and reliance on manual annotations, which are time-consuming and subjective.
We present a Radon transform-based algorithm for robust, annotation-free structural orientation analysis across multimodal imaging datasets, aiming to improve objectivity and efficiency without introducing preprocessing artifacts.
The algorithm employs a patch-based Radon transform approach to detect oriented structures in noisy images. By analyzing projection peaks in Radon space, it enhances small structures' visibility while minimizing noise and artifact influence. The method was evaluated using synthetic and datasets, comparing its performance with human annotations.
The algorithm achieved strong agreement with human annotations, with detection accuracy exceeding 88% across different imaging modalities. Variability among trained raters emphasized the benefits of an objective, mathematically driven approach.
The proposed method provides a robust and adaptable solution for structural orientation analysis in biological images. Its ability to quantify tissue component orientation without preprocessing artifacts makes it valuable for high-resolution, dynamic studies in tissue architecture and biomechanics.
了解生物组织的结构组织对于研究其功能以及对生理和病理状况的反应至关重要。诸如多光子显微镜等成像技术能够实现组织结构的高分辨率可视化。然而，由于成像噪声、复杂性以及对人工标注的依赖，自动方向分析仍然具有挑战性，人工标注既耗时又主观。
我们提出一种基于拉东变换的算法，用于跨多模态成像数据集进行稳健的、无需标注的结构方向分析，旨在提高客观性和效率，同时不引入预处理伪影。
该算法采用基于补丁的拉东变换方法来检测噪声图像中的定向结构。通过分析拉东空间中的投影峰值，它增强了小结构的可见性，同时将噪声和伪影的影响降至最低。使用合成数据集和真实数据集对该方法进行了评估，并将其性能与人工标注进行了比较。
该算法与人工标注高度一致，在不同成像模态下检测准确率超过88%。训练评分者之间的差异凸显了客观的、数学驱动方法的优势。
所提出的方法为生物图像中的结构方向分析提供了一种稳健且适应性强的解决方案。它能够在不产生预处理伪影的情况下量化组织成分的方向，这使其在组织结构和生物力学的高分辨率动态研究中具有重要价值。
