Speckle Patch Similarity for Echogenicity-Based Multiorgan Segmentation in Ultrasound Images of the Thyroid Gland.

Abstract

Ultrasound (US) imaging deals with forming a brightness image from the amplified backscatter echo when an ultrasound wave is triggered at the region of interest. Imaging artifacts and speckles occur in the image as a consequence of backscattering and subsequent amplification. We demonstrate the usefulness of speckle-related pixels and imaging artifacts as sources of information to perform multiorgan segmentation in US images of the thyroid gland. The speckle-related pixels are clustered based on a similarity constraint to quantize the image. The quantization results are used to locate useful anatomical landmarks that aid the detection of multiple organs in the image, which are the thyroid gland, the carotid artery, the muscles, and the trachea. The spatial locations of the carotid artery and the trachea are used to estimate the boundaries of the thyroid gland in transverse US scans. Experiments performed on a multivendor dataset yield good quality segmentation results with probabilistic Rand index > 0.83 and boundary error 1mm, and an average accuracy greater than 94%. Analysis of the results using the Dice coefficient as the metric shows that the proposed method performs better than the state-of-the-art methods. Further, experiments conducted on 971 images of a publicly available dataset prove the effectiveness of the algorithm to track the carotid artery for guided interventions. In addition to US-guided interventions, the algorithm can be used as a general framework in applications pertaining to volumetric analysis and computer-aided diagnosis.