Segmentation of individual ribs from low-dose chest CT

Jaesung Lee; Anthony P. Reeves

doi:10.1117/12.844565

9 March 2010 Segmentation of individual ribs from low-dose chest CT

Jaesung Lee, Anthony P. Reeves

Proceedings Volume 7624, Medical Imaging 2010: Computer-Aided Diagnosis; 76243J (2010) https://doi.org/10.1117/12.844565
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

Segmentation of individual ribs and other bone structures in chest CT images is important for anatomical analysis, as the segmented ribs may be used as a baseline reference for locating organs within a chest as well as for identification and measurement of any geometric abnormalities in the bone. In this paper we present a fully automated algorithm to segment the individual ribs from low-dose chest CT scans. The proposed algorithm consists of four main stages. First, all the high-intensity bone structure present in the scan is segmented. Second, the centerline of the spinal canal is identified using a distance transform of the bone segmentation. Then, the seed region for every rib is detected based on the identified centerline, and each rib is grown from the seed region and separated from the corresponding vertebra. This algorithm was evaluated using 115 low-dose chest CT scans from public databases with various slice thicknesses. The algorithm parameters were determined using 5 scans, and remaining 110 scans were used to evaluate the performance of the segmentation algorithm. The outcome of the algorithm was inspected by an author for the correctness of the segmentation. The results indicate that over 98% of the individual ribs were correctly segmented with the proposed algorithm.

Citation Download Citation

Jaesung Lee and Anthony P. Reeves "Segmentation of individual ribs from low-dose chest CT", Proc. SPIE 7624, Medical Imaging 2010: Computer-Aided Diagnosis, 76243J (9 March 2010); https://doi.org/10.1117/12.844565

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available