School of Computer Science and Technology, University of Bedfordshire, Luton, LU1 3JU, UK.
Pattern Recognition and Image Processing Group (PRIP), TU Wien, Wien, Austria.
Sci Rep. 2021 Jan 27;11(1):2294. doi: 10.1038/s41598-021-81786-4.
Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients' cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren-Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients' cases will be available.
纹理特征旨在定量评估图像像素的空间分布模式，以进行图像分析和解释。纹理模式的无法解释的变化常常导致医学图像分析中的误解和不良后果。在本文中，我们探讨了机器学习 (ML) 方法在患者数量较少的早期阶段设计关节炎 (OA) 放射学测试的能力。在我们的实验中，我们使用了从 1 级进展的患者的膝关节高分辨率 X 射线图像。现有的 ML 方法提供了有限的诊断准确性，而提出的基于深度学习的群组数据处理策略则显著扩展了诊断测试。比较实验表明，使用基于 Zernike 的纹理特征的建议框架平均显著提高了 11%的诊断准确性。这使我们得出结论，设计用于早期诊断 OA 的模型将提供更准确的放射学测试，尽管在有大量患者病例时需要进行新的研究。
