Evaluation of a Template-Based Algorithm for Markerless Lung Tumor Localization on Single and Dual Energy Kilovoltage Images Journal Article

Local Library Link: Find It @ Loyola

Authors: Block, A. M.; Patel, R; Surucu, M; Harkenrider, M. M.; Roeske, J. C.
Article Title: Evaluation of a Template-Based Algorithm for Markerless Lung Tumor Localization on Single and Dual Energy Kilovoltage Images
Abstract: OBJECTIVES: To evaluate a template-based matching algorithm on single energy (SE) and dual energy (DE) radiographs for markerless localization of lung tumors. METHODS: A total of 74 images from 17 patients with Stage IA-IV lung cancer were considered. At the time of radiotherapy treatment, gated end-expiration SE radiographs were obtained at 60 and 120 kVp at different gantry angles (33 anterior, 41 oblique), from which, soft-tissue enhanced DE images were created. A template-based matching algorithm was used to localize individual tumors on both SE and DE radiographs. Tumor centroid coordinates obtained from the template matching software on both SE and DE images were compared with coordinates defined by physicians. RESULTS: The template-based matching algorithm was able to successfully localize the GTV within 5 mm on 70% (52/74) of the SE images vs. 91% (66/74) of the DE images (p0.01). Mean vector differences between the coordinates of the template matched by the algorithm and the coordinates of the physician defined ground truth were 3.2 mm +/- 2.8 mm for SE images, versus 2.3 mm +/- 1.7 mm for DE images (p=0.03). CONCLUSIONS: Template based matching on DE images was more accurate and precise than using SE images. Advances in knowledge: This represents, to the authors' knowledge, the largest study evaluating template matching on clinical SE and DE images, considering not only anterior gantry angles, but oblique angles as well, suggesting a novel lung tumor matching technique using DE subtraction that is reliable, accurate, and precise.
Journal Title: The British journal of radiology
ISSN: 1748-880X; 0007-1285
Publisher: Unknown  
Journal Place: England
Date Published: 2016
Start Page: 20160648
Language: ENG
DOI/URL:

10.1259/bjr.20160648
Notes: LR: 20161013; JID: 0373125; aheadofprint; SO: Br J Radiol. 2016 Oct 12:20160648.