PURPOSE: The major hurdle for three-dimensional display of lung lobes is the automatic recognition of lobar fissures, boundaries of lung lobes. Lobar fissures are difficult to recognize due to their variable shape and appearance, along with the low contrast and high noise inherent in computed tomographic (CT) images. An algorithm for recognizing the major fissures in human lungs was developed and tested. METHODS: The algorithm employs texture analysis and fissure appearance to mimic the way that surgeons/radiologists read CT images in clinical settings. The algorithm uses 3 stages to automatically find the major fissures in human lungs: (a) texture analysis, (b) fissure region analysis, and (c) fissure identification. RESULTS: The algorithm's feasibility was evaluated using isotropic CT images from 16 anonymous patients with varying pathologies. Compared with manual segmentation, the algorithm yielded mean distances of 1.92 ± 2.07 and 2.07 ± 2.37 mm, for recognizing the left and right major fissures, respectively. CONCLUSIONS: An automatic recognition algorithm for major fissures in human lungs is feasible, providing a foundation for the future development of a complete segmentation algorithm for lung lobes.
PURPOSE: The major hurdle for three-dimensional display of lung lobes is the automatic recognition of lobar fissures, boundaries of lung lobes. Lobar fissures are difficult to recognize due to their variable shape and appearance, along with the low contrast and high noise inherent in computed tomographic (CT) images. An algorithm for recognizing the major fissures in human lungs was developed and tested. METHODS: The algorithm employs texture analysis and fissure appearance to mimic the way that surgeons/radiologists read CT images in clinical settings. The algorithm uses 3 stages to automatically find the major fissures in human lungs: (a) texture analysis, (b) fissure region analysis, and (c) fissure identification. RESULTS: The algorithm's feasibility was evaluated using isotropic CT images from 16 anonymous patients with varying pathologies. Compared with manual segmentation, the algorithm yielded mean distances of 1.92 ± 2.07 and 2.07 ± 2.37 mm, for recognizing the left and right major fissures, respectively. CONCLUSIONS: An automatic recognition algorithm for major fissures in human lungs is feasible, providing a foundation for the future development of a complete segmentation algorithm for lung lobes.
Authors: Jiantao Pu; Joseph K Leader; Bin Zheng; Friedrich Knollmann; Carl Fuhrman; Frank C Sciurba; David Gur Journal: IEEE Trans Med Imaging Date: 2008-12-09 Impact factor: 10.048
Authors: Sarah E Gerard; Taylor J Patton; Gary E Christensen; John E Bayouth; Joseph M Reinhardt Journal: IEEE Trans Med Imaging Date: 2018-08-10 Impact factor: 10.048