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

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 1 mm, 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.

Echogenicity based approach to detect, segment and track the common carotid artery in 2D ultrasound images.

Automatic detection and segmentation of the common carotid artery in transverse ultrasound (US) images of the thyroid gland play a vital role in the success of US guided intervention procedures. We propose in this paper a novel method to accurately detect, segment and track the carotid in 2D and 2D+t US images of the thyroid gland using concepts based on tissue echogenicity and ultrasound image formation. We first segment the hypoechoic anatomical regions of interest using local phase and energy in the input image. We then make use of a Hessian based blob like analysis to detect the carotid within the segmented hypoechoic regions. The carotid artery is segmented by making use of least squares ellipse fit for the edge points around the detected carotid candidate. Experiments performed on a multivendor dataset of 41 images show that the proposed algorithm can segment the carotid artery with high sensitivity (99.6 ±m 0.2%) and specificity (92.9 ±m 0.1%). Further experiments on a public database containing 971 images of the carotid artery showed that the proposed algorithm can achieve a detection accuracy of 95.2% with a 2% increase in performance when compared to the state-of-the-art method.

Automatic removal of manually induced artefacts in ultrasound images of thyroid gland.

Manually induced artefacts, like caliper marks and anatomical labels, render an ultrasound (US) image incapable of being subjected to further processes of Computer Aided Diagnosis (CAD). In this paper, we propose a technique to remove these artefacts and restore the image as accurately as possible. The technique finds application as a pre-processing step when developing unsupervised segmentation algorithms for US images that deal with automatic estimation of the number of segments and clustering. The novelty of the algorithm lies in the image processing pipeline chosen to automatically identify the artefacts and is developed based on the histogram properties of the artefacts. The algorithm was able to successfully restore the images to a high quality when it was executed on a dataset of 18 US images of the thyroid gland on which the artefacts were induced manually by a doctor. Further experiments on an additional dataset of 10 unmarked US images of the thyroid gland on which the artefacts were simulated using Matlab showed that the restored images were again of high quality with a PSNR > 38 dB and free of any manually induced artefacts.