Anatomy-based algorithm for automatic segmentation of human diaphragm in noncontrast computed tomography images

Elham Karami; Yong Wang; Stewart Gaede; Ting-Yim Lee; Abbas Samani

doi:10.1117/1.JMI.3.4.046004

Anatomy-based algorithm for automatic segmentation of human diaphragm in noncontrast computed tomography images

J Med Imaging (Bellingham). 2016 Oct;3(4):046004. doi: 10.1117/1.JMI.3.4.046004. Epub 2016 Nov 22.

Authors

Elham Karami¹, Yong Wang², Stewart Gaede³, Ting-Yim Lee⁴, Abbas Samani⁵

Affiliations

¹ Western University, Department of Medical Biophysics, Medical Sciences Building, London, Ontario N6A 5C1, Canada; Robarts Research Institute, Imaging Research Laboratories, 1151 Richmond Street, London, Ontario N6A 5B7, Canada.
² Robarts Research Institute , Imaging Research Laboratories, 1151 Richmond Street, London, Ontario N6A 5B7, Canada.
³ Western University, Department of Medical Biophysics, Medical Sciences Building, London, Ontario N6A 5C1, Canada; London Regional Cancer Program, Department of Physics and Engineering, 800 Commissioners R E, London, Ontario N6A 5W9, Canada; Western University, Department of Oncology, 790 Commissioners Road East, London, Ontario N6A 4L6, Canada.
⁴ Western University, Department of Medical Biophysics, Medical Sciences Building, London, Ontario N6A 5C1, Canada; Robarts Research Institute, Imaging Research Laboratories, 1151 Richmond Street, London, Ontario N6A 5B7, Canada; Lawson Health Research Institute, Imaging Program, 268 Grosvenor Street, London, Ontario N6A 4V2, Canada; Western University, Department of Medical Imaging, London Health Sciences Centre, Victoria Hospital, London, Ontario N6A 5W9, Canada.
⁵ Western University, Department of Medical Biophysics, Medical Sciences Building, London, Ontario N6A 5C1, Canada; Robarts Research Institute, Imaging Research Laboratories, 1151 Richmond Street, London, Ontario N6A 5B7, Canada; Western University, Department of Electrical and Computer Engineering, Thompson Engineering Building, London, Ontario N6A 5B9, Canada; Western University, Graduate Program in Biomedical Engineering, Claudette MacKay Lassonde Pavilion, London, Ontario N6A 5B9, Canada.

Abstract

In-depth understanding of the diaphragm's anatomy and physiology has been of great interest to the medical community, as it is the most important muscle of the respiratory system. While noncontrast four-dimensional (4-D) computed tomography (CT) imaging provides an interesting opportunity for effective acquisition of anatomical and/or functional information from a single modality, segmenting the diaphragm in such images is very challenging not only because of the diaphragm's lack of image contrast with its surrounding organs but also because of respiration-induced motion artifacts in 4-D CT images. To account for such limitations, we present an automatic segmentation algorithm, which is based on a priori knowledge of diaphragm anatomy. The novelty of the algorithm lies in using the diaphragm's easy-to-segment contacting organs-including the lungs, heart, aorta, and ribcage-to guide the diaphragm's segmentation. Obtained results indicate that average mean distance to the closest point between diaphragms segmented using the proposed technique and corresponding manual segmentation is [Formula: see text], which is favorable. An important feature of the proposed technique is that it is the first algorithm to delineate the entire diaphragm. Such delineation facilitates applications, where the diaphragm boundary conditions are required such as biomechanical modeling for in-depth understanding of the diaphragm physiology.

Keywords: a priori knowledge; automatic segmentation; diaphragm; four-dimensional computed tomography; noncontrast computed tomography image.