Thyroid nodule segmentation using active contour bilateral filtering on ultrasound images

摘要

Utilization of ultrasound imaging with various resolutions as modalities for thyroid nodules examination is growing rapidly. This is consistent with an increase in incidence of thyroid malignancy. Thyroid ultrasound examination is considered superior to other medical imaging modalities for its non-invasive, practical, inexpensive and painless. In the examination process, a radiologist expects areas of thyroid nodules that can be localized precisely from the surrounding normal tissue. Thus boundary of the nodules can be seen as to be regular or irregular. Boundary is one of the important features of malignancy that doctors use to make a diagnosis. Most malignant nodules have unclear and irregular boundaries. Imprecise segmentation result will lead to misdiagnosis based on boundary characteristics. Active contour segmentation technique is applied for detecting boundary of thyroid nodules and separating them with normal tissue iteratively. However, the characteristics of the ultrasound image that brings speckle noises make the segmentation process more complicated. It also resulted in interpretation errors and inaccuracies diagnosis made by a doctor. The intricacy of irregular nodule area can not easily be solved by changing the value of iteration on active contour. Therefore, speckle noise reduction method is needed to overcome this problem so that nodule area segmented properly. In this paper speckle noise reduction is done with bilateral filter. Comparison of image segmentation results of thyroid nodules with and without bilateral filter is attached at the end of this article. The combination of bilateral filter and active contour showed better results with the edge of the nodules firmly and clear.