Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models

Common carotid artery intima-media thickness (IMT) is regarded as one of the most significant indicators for the assessment of cardiovascular diseases. This paper proposes an automated method based on Markov random field models for IMT measurement. The label field is initialized from line segments generated using the Hough transform and the iterated conditional modes method is applied to detect the final boundaries of the lumen-intima interface as well as the media-adventitia interface. A total of 80 ultrasound images from 80 corresponding patients were tested with the proposed method. The ground truth (GT) of the IMT was manually measured a total of four times and then averaged, and the automatically segmented (AS) IMT was computed using the proposed method. The mean of the absolute error +/- A standard deviation between AS and GT IMT values was 0.0244 +/- A 0.0227 mm, and the correlation coefficient between the two was 0.9810. Furthermore, the computational time was 1.7 s per image for serial computation with MATLAB on a computer with an Intel Core i5-4200M CPU running 32-bit Windows 7. Experimental results show that the proposed method is both efficient and accurate. The proposed method can be applied for real-time IMT measurement by utilizing parallel computation, which is enable by the use of Markov random field models.