Skip to main content

Automated Characterization of Pyelocalyceal Anatomy Using CT Urograms to Aid in Management of Kidney Stones

Posted by on Monday, December 18, 2017 in News.

Yuankai Huo, Vaughn Braxton, S. Duke Herrell, Bennett Landman, and Smita De. “Automated Characterization of Pyelocalyceal Anatomy Using CT Urograms to Aid in Management of Kidney Stones.” In Computer Assisted and Robotic Endoscopy and Clinical Image-Based Procedures, pp. 99-107. Springer, Cham, 2017.

Full text: https://link.springer.com/chapter/10.1007/978-3-319-67543-5_9

Abstract

Nephrolithiasis is a costly and prevalent disease that is associated with significant morbidity including pain, infection, and kidney injury.  While surgical treatment of kidney stones is generally based on size and quality of the stones, studies have suggested that specific characteristics of pyelocalyceal anatomy, such as the lower pole infundibulopelvic angle, can also influence the success rate of various treatment modalities.  However, the traditional methods of deriving such quantitative measurements have relied on 2-dimensional images of a 3-dimensional system as well as manual delineations, which are both cumbersome and potentially inaccurate during treatment planning. In this paper, we propose a novel non-invasive framework that automatically achieves a tree structure of the urinary collecting system using computerized tomography (CT) urograms, allowing for 3-dimensional characterization of the pyelocalyceal anatomy.  First, the urinary collecting system was segmented using an automated segmentation framework and results were validated by a radiologist.  A centerline tree structure was then extracted from volume segmentation.  Finally, the infundibulopelvic angle was derived from the tree structure. Results demonstrated that our algorithm is able to automatically segment the pyelocalyceal anatomy from CT urograms and determine the tree structure of the pyelocalyceal system to allow for 3-dimensional measurement of the infundibulopelvic angle. To the best of our knowledge, this is the first method that allows for an automated characterization of the 3-dimensional pyelocalyceal structure.

aaaa