Computerized Segmentation on CT Proves Reliable

April 21, 2010 - A computerized segmentation system can reliably estimate changes in tumor size on computed tomography (CT) scans relative to radiologists' manual segmentation, according to new research published in the May issue of the American Journal of Roentgenology. Researchers in the departments of Radiology at University of Michigan, Johns Hopkins Hospitals, and the department of Otolaryngology-Head and Neck Surgery, University of Michigan, conducted the study. They set out to determine the feasibility of computerized segmentation of lesions on head and neck CT scans and evaluate its potential for estimating changes in tumor volume in response to treatment of head and neck cancers. The computer-estimated change in tumor volume and percentage change in tumor volume between the pre- and post-treatment scans achieved a high correlation with the estimates from manual segmentation for the 13 primary tumors. The average error in estimating the percentage change in tumor volume by automatic segmentation relative to the radiologists' average error was –1.5 percent ± 5.4 percent. The researchers concluded the computerized segmentation system was reliable in estimating changes in tumor size on CT scans compared to manual segmentation performed by a radiologists. They added, "This data can be used to calculate changes in tumor size on pre- and post-treatment scans to assess response to treatment." Reference: Hadjiiski, L., Mukherji, S., Mohannad, I., et al. Head and Neck Cancers on CT: Preliminary Study of Treatment Response Assessment Based on Computerized Volume Analysis. American Journal of Roentgenology. May 2010. For more information: www.ajronline.org