Abstract
Ultrasound (US) is the most commonly used liver imaging modality worldwide. Due to its low cost, it is increasingly used in the follow-up of cancer patients with metastases localized in the liver. In this contribution, we present the results of an interactive segmentation approach for liver metastases in US acquisitions. A (semi-) automatic segmentation is still very challenging because of the low image quality and the low contrast between the metastasis and the surrounding liver tissue. Thus, the state of the art in clinical practice is still manual measurement and outlining of the metastases in the US images. We tackle the problem by providing an interactive segmentation approach providing real-time feedback of the segmentation results. The approach has been evaluated with typical US acquisitions from the clinical routine, and the datasets consisted of pancreatic cancer metastases. Even for difficult cases, satisfying segmentations results could be achieved because of the interactive real-time behavior of the approach. In total, 40 clinical images have been evaluated with our method by comparing the results against manual ground truth segmentations. This evaluation yielded to an average Dice Score of 85% and an average Hausdorff Distance of 13 pixels.
Highlights
The user was satisfied with the borders of the lesion and stopped the interactive segmentation process by releasing the mouse button
We presented the results of a fast interactive segmentation algorithm for liver metastases in ultrasound acquisitions, which is a challenging problem because of the low quality of the image data and the low contrast between metastases and surrounding tissue
Liver metastases are still measured in a purely manual way in the clinical routine. This leads to a poor inter-observer agreement regarding the size of the metastasis, which is the critical factor for treatment response evaluation and treatment planning
Summary
Yoshida et al.[7] introduce an approach for the segmentation of low-contrast objects embedded in noisy images They used it to segment liver tumors in B-scan ultrasound images with hypoechoic rims. The B-scan image is processed by a median filter to remove speckle noise, followed by obtaining several one-dimensional profiles along multiple radial directions, which pass through the manually identified center of the region of a tumor. The threshold to control the region growing process is automatically selected, and a gradient magnitude based region growing algorithm is adopted This segmentation approach was tested on different abdominal masses such as cyst and liver tumors. Note: figure adapted from[26]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
