[论文解读] Cobb Angle Measurement of Scoliosis with Reduced Variability

Raka Kundu, Amlan Chakrabarti+1 more|arXiv (Cornell University)|Nov 22, 2012

Scoliosis diagnosis and treatment参考文献 14被引用 9

一句话总结

本文提出了一种新颖的自动化方法，用于测量脊柱侧弯X光片中的Cobb角，显著降低了观察者间和观察者内的一致性差异。通过结合非局部欧几里得截尾均值去噪滤波器与Otsu阈值化Canny边缘检测，该方法提升了图像质量与边缘定位精度，相较于现有技术，实现了更一致且准确的Cobb角测量。

ABSTRACT

Cobb angle, which is a measure of spinal curvature is the standard method for quantifying the magnitude of Scoliosis related to spinal deformity in orthopedics. Determining the Cobb angle through manual process is subject to human errors. In this work, we propose a methodology to measure the magnitude of Cobb angle, which appreciably reduces the variability related to its measurement compared to the related works. The proposed methodology is facilitated by using a suitable new improved version of Non-Local Means for image denoisation and Otsus automatic threshold selection for Canny edge detection. We have selected NLM for preprocessing of the image as it is one of the fine states of art for image denoisation and helps in retaining the image quality. Trimmedmean, median are more robust to outliners than mean and following this concept we observed that NLM denoising quality performance can be enhanced by using Euclidean trimmed-mean replacing the mean. To prove the better performance of the Non-Local Euclidean Trimmed-mean denoising filter, we have provided some comparative study results of the proposed denoising technique with traditional NLM and NonLocal Euclidean Medians. The experimental results for Cobb angle measurement over intra observer and inter observer experimental data reveals the better performance and superiority of the proposed approach compared to the related works. MATLAB2009b image processing toolbox was used for the purpose of simulation and verification of the proposed methodology.

研究动机与目标

• 减少手动Cobb角测量中的观察者变异性，这是临床脊柱侧弯评估中的主要局限。
• 改进脊柱X光图像的预处理，以提高边缘检测的准确性。
• 开发一种鲁棒的自动化Cobb角测量方法，优于传统的手动和现有自动化方法。
• 通过观察者内和观察者间实验数据验证该方法，确保其临床相关性。

提出的方法

• 采用改进的非局部均值（NLM）去噪滤波器，使用欧几里得截尾均值替代均值，以在保留图像细节的同时更有效地抑制噪声。
• 将Otsu方法集成到Canny边缘检测中，实现自动阈值选择，以提高预处理后图像的边缘定位精度。
• 使用MATLAB R2009b图像处理工具箱进行流程模拟与验证。
• 在边缘检测前应用改进的NLM滤波器以提升图像质量，降低对异常值的敏感性。
• 将去噪与边缘检测整合为顺序工作流，确保椎体终板检测的准确性，从而支持角度计算。
• 利用截尾均值与中位数统计方法，增强去噪过程中对图像异常值的鲁棒性。

实验结果

研究问题

• RQ1 改进的非局部欧几里得截尾均值滤波器是否在脊柱X光图像中比标准NLM或非局部欧几里得中值滤波器更有效地抑制噪声？
• RQ2 将Otsu阈值化方法与Canny边缘检测结合，是否能提高脊柱侧弯X光片中边缘定位的准确性？
• RQ3 所提出的方法在多大程度上减少了Cobb角测量中的观察者间和观察者内变异性？
• RQ4 在测量一致性方面，该自动化方法与现有手动和自动化方法相比，其定量表现如何？

主要发现

• 所提出的非局部欧几里得截尾均值去噪滤波器在噪声抑制与图像质量保持方面，优于标准NLM和非局部欧几里得中值滤波器。
• 将Otsu阈值化与Canny边缘检测结合，显著提升了脊柱X光片中边缘定位的一致性与准确性。
• 实验结果表明，Cobb角测量的观察者内与观察者间变异性均显著降低。
• 在真实临床数据验证下，该方法在测量一致性和准确性方面优于相关研究工作。