Ultrasound breast lesion segmentation using adaptive parameters

摘要

In computer aided diagnosis for ultrasound images, breast lesion segmentation is an important but intractable procedure. Although active contour models with level set energy function have been proposed for breast ultrasound lesion segmentation, those models usually select and fix the weight values for each component of the level set energy function empirically. The fixed weights might affect the segmentation performance since the characteristics and patterns of tissue and tumor differ between patients. Besides, there is observer variability in probe handling and ultrasound machine gain setting. Hence, we propose an active contour model with adaptive parameters in breast ultrasound lesion segmentation to overcome the variability of tissue and tumor patterns between patients. The main idea is to estimate the optimal parameter set automatically for different input images. We used regression models using 27 numerical features from the input image and an initial seed box. Our method showed better results in segmentation performance than the original model with fixed parameters. In addition, it could facilitate the higher classification performance with the segmentation results. In conclusion, the proposed active contour segmentation model with adaptive parameters has the potential to deal with various different patterns of tissue and tumor effectively.