Lin Muqing, Chen Jeon-Hor, Nie Ke, Chang Daniel, Nalcioglu Orhan, Su Min-Ying
Tu & Yuen Center for Functional Onco-Imaging, University of California, Irvine, CA 92697-5020, USA.
J Magn Reson Imaging. 2009 Oct;30(4):817-24. doi: 10.1002/jmri.21915.
To develop a computer-based algorithm for detecting blood vessels that appear in breast dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), and to evaluate the improvement in reducing the number of vascular pixels that are labeled by computer-aided diagnosis (CAD) systems as being suspicious of malignancy.
The analysis was performed in 34 cases. The algorithm applied a filter bank based on wavelet transform and the Hessian matrix to detect linear structures as blood vessels on a two-dimensional maximum intensity projection (MIP). The vessels running perpendicular to the MIP plane were then detected based on the connectivity of enhanced pixels above a threshold. The nonvessel enhancements were determined and excluded based on their morphological properties, including those showing scattered small segment enhancements or nodular or planar clusters. The detected vessels were first converted to a vasculature skeleton by thinning and subsequently compared to the vascular track manually drawn by a radiologist.
When evaluating the performance of the algorithm in identifying vascular tissue, the correct-detection rate refers to pixels identified by both the algorithm and radiologist, while the incorrect-detection rate refers to pixels identified by only the algorithm, and the missed-detection rate refers to pixels identified only by the radiologist. From 34 analyzed cases the median correct-detection rate was 85.6% (mean 84.9% +/- 7.8%), the incorrect-detection rate was 13.1% (mean 15.1% +/- 7.8%), and the missed-detection rate was 19.2% (mean 21.3% +/- 12.8%). When detected vessels were excluded in the hot-spot color-coding of the CAD system, they could reduce the labeling of vascular vessels in 2.6%-68.6% of hot-spot pixels (mean 16.6% +/- 15.9%).
The computer algorithm-based method can detect most large vessels and provide an effective means in reducing the labeling of vascular pixels as suspicious on a DCE-MRI CAD system. This algorithm may improve the workflow of radiologists using CAD for image display, but will be particularly useful for development of automated CAD that gives diagnostic impression.
开发一种基于计算机的算法，用于检测乳腺动态对比增强（DCE）磁共振成像（MRI）中出现的血管，并评估在减少计算机辅助诊断（CAD）系统标记为可疑恶性的血管像素数量方面的改进。
对34例病例进行分析。该算法应用基于小波变换和黑塞矩阵的滤波器组，在二维最大强度投影（MIP）上检测作为血管的线性结构。然后根据高于阈值的增强像素的连通性检测垂直于MIP平面的血管。根据非血管增强的形态学特性确定并排除非血管增强，包括那些显示散在小片段增强或结节状或平面簇状增强的情况。首先通过细化将检测到的血管转换为血管骨架，随后与放射科医生手动绘制的血管轨迹进行比较。
在评估该算法识别血管组织的性能时，正确检测率是指算法和放射科医生都识别出的像素，错误检测率是指仅由算法识别出的像素，漏检率是指仅由放射科医生识别出的像素。在34例分析病例中，正确检测率的中位数为85.6%（平均84.9%±7.8%），错误检测率为13.1%（平均15.1%±7.8%），漏检率为19.2%（平均21.3%±12.8%）。当在CAD系统的热点颜色编码中排除检测到的血管时，它们可以减少2.6% - 68.6%的热点像素中血管的标记（平均16.6%±15.9%）。
基于计算机算法的方法可以检测到大多数大血管，并为减少DCE - MRI CAD系统上标记为可疑的血管像素提供一种有效手段。该算法可能会改善放射科医生使用CAD进行图像显示的工作流程，但对于给出诊断印象的自动化CAD的开发将特别有用。
