Abstract:
Contrast 3D echocardiography (C3DE) is commonly used to enhance the visual quality of ultrasound images in comparison with non-contrast 3D echocardiography (3DE). Though the image quality in C3DE is perceived to be improved for visual analysis, but it actually deteriorates for the purpose of automatic or semi-automatic analysis due to high speckle noise and intensity inhomogeneity. Therefore, the left ventricle (LV) endocardial feature extraction and segmentation from C3DE images remains a challenging problem. To overcome this challenge, this research work proposes a simple adaptive preprocessing method to invert the appearance of C3DE image. In this inverted appearance, the LV cavity appears dark while the myocardium appears bright making it similar looking to a 3DE image. Moreover, the resulting inverted image has high contrast and low noise appearance, yielding strong LV endocardium boundary and facilitating feature extraction for segmentation.
Our proposed image inversion mapping is based on an image intensity level threshold value, therefore our major contribution in this work is presenting an automatic threshold estimation (ATE) method through histogram analysis. This technique is validated through rigorous qualitative and quantitative measuring methods and favorable results are achieved. The results demonstrate that the inverse appearance of contrast image enables and simplifies the subsequent LV segmentation process. We highlight that the proposed method is the first attempt of its kind towards preprocessing technique and automatic/semi-automatic LV segmentation from C3DE images.
