一种用于在斜侧位（MLO）乳房 X 光片中分割胸肌的稳健方法。

A robust method for segmenting pectoral muscle in mediolateral oblique (MLO) mammograms.

机构信息

School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.

School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA.

出版信息

Int J Comput Assist Radiol Surg. 2019 Feb;14(2):237-248. doi: 10.1007/s11548-018-1867-7. Epub 2018 Oct 4.

DOI:10.1007/s11548-018-1867-7

PMID:30288698

Abstract

PURPOSE

Accurately detecting and removing pectoral muscle areas depicting on mediolateral oblique (MLO) view mammograms are an important step to develop a computer-aided detection scheme to assess global mammographic density or tissue patterns. This study aims to develop and test a new fully automated, accurate and robust method for segmenting pectoral muscle in MLO mammograms.

METHODS

The new method includes the following steps. First, a small rectangular region in the top-left corner of the MLO mammogram which may contain pectoral muscle is captured and enhanced by the fractional differential method. Next, an improved iterative threshold method is applied to segment a rough binary boundary of the pectoral muscle in the small region. Then, a rough contour is fitted with the least squares method on the basis of points of the rough boundary. Last, the fitting contour is subjected to local active contour evolution to obtain the final pectoral muscle segmentation line. The method has been tested on 720 MLO mammograms.

RESULTS

The segmentation results generated using the new scheme were evaluated by two expert mammographic radiologists using a 5-scale rating system. More than 65% were rated above scale 3. When assessing the segmentation results generated using Hough transform, morphologic thresholding methods and Unet-based model, less than 20%, 35% and 47% of segmentation results were rated above scale 3 by two radiologists, respectively. Quantitative data analysis results show that the Dice coefficient of 0.986 ± 0.005 is obtained. In addition, the mean rate of errors and Hausdorff distance between the contours detected by automated and manual segmentation are FP = 1.71 ± 3.82%, FN = 5.20 ± 3.94% and 2.75 ± 1.39 mm separately.

CONCLUSION

The proposed method can be used to segment the pectoral muscle in MLO mammograms with higher accuracy and robustness.

摘要

目的

准确检测和去除在侧斜位（MLO）乳腺钼靶图像上显示的胸肌区域，是开发计算机辅助检测方案以评估全局乳腺密度或组织模式的重要步骤。本研究旨在开发和测试一种新的全自动、准确且稳健的方法，用于分割 MLO 乳腺钼靶图像中的胸肌。

方法

新方法包括以下步骤。首先，通过分数阶微分方法捕获并增强 MLO 乳腺钼靶图像左上角的一个小矩形区域，该区域可能包含胸肌。接下来，应用改进的迭代阈值方法对小区域中的胸肌进行粗略二值边界分割。然后，基于粗糙边界上的点，用最小二乘法拟合粗糙轮廓。最后，通过局部主动轮廓演化对拟合轮廓进行处理，得到最终的胸肌分割线。该方法已在 720 张 MLO 乳腺钼靶图像上进行了测试。

结果

使用新方案生成的分割结果由两位专家乳腺放射科医生使用 5 级评分系统进行评估。超过 65%的结果被评为 3 级以上。当评估使用霍夫变换、形态学阈值方法和基于 Unet 的模型生成的分割结果时，两位放射科医生分别对少于 20%、35%和 47%的分割结果评为 3 级以上。定量数据分析结果表明，Dice 系数为 0.986±0.005。此外，自动和手动分割检测到的轮廓之间的错误率和 Hausdorff 距离的平均值分别为 FP=1.71±3.82%、FN=5.20±3.94%和 2.75±1.39mm。