Sharmin Sultana1, Praful Agrawal2, Shireen Elhabian2, Ross Whitaker2, Jason E Blatt3, Benjamin Gilles4, Justin Cetas5, Tanweer Rashid1, Michel A Audette6. 1. Department of Modeling, Simulation and Visualization Engineering, Old Dominion University, Norfolk, USA. 2. Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, USA. 3. Department of Neurosurgery, University of Florida, Gainesville, USA. 4. Montpellier Laboratory of Informatics, Robotics, and Microelectronics (LIRMM), Montpellier, France. 5. Department of Neurosurgery, Oregon Health and Science University, Portland, USA. 6. Department of Modeling, Simulation and Visualization Engineering, Old Dominion University, Norfolk, USA. maudette@odu.edu.
Abstract
PURPOSE: We propose a segmentation methodology for brainstem cranial nerves using statistical shape model (SSM)-based deformable 3D contours from T2 MR images. METHODS: We create shape models for ten pairs of cranial nerves. High-resolution T2 MR images are segmented for nerve centerline using a 1-Simplex discrete deformable 3D contour model. These segmented centerlines comprise training datasets for the shape model. Point correspondence for the training dataset is performed using an entropy-based energy minimization framework applied to particles located on the centerline curve. The shape information is incorporated into the 1-Simplex model by introducing a shape-based internal force, making the deformation stable against low resolution and image artifacts. RESULTS: The proposed method is validated through extensive experiments using both synthetic and patient MRI data. The robustness and stability of the proposed method are experimented using synthetic datasets. SSMs are constructed independently for ten pairs (CNIII-CNXII) of brainstem cranial nerves using ten non-pathological image datasets of the brainstem. The constructed ten SSMs are assessed in terms of compactness, specificity and generality. In order to quantify the error distances between segmented results and ground truths, two metrics are used: mean absolute shape distance (MASD) and Hausdorff distance (HD). MASD error using the proposed shape model is 0.19 ± 0.13 (mean ± std. deviation) mm and HD is 0.21 mm which are sub-voxel accuracy given the input image resolution. CONCLUSION: This paper described a probabilistic digital atlas of the ten brainstem-attached cranial nerve pairs by incorporating a statistical shape model with the 1-Simplex deformable contour. The integration of shape information as a priori knowledge results in robust and accurate centerline segmentations from even low-resolution MRI data, which is essential in neurosurgical planning and simulations for accurate and robust 3D patient-specific models of critical tissues including cranial nerves.
PURPOSE: We propose a segmentation methodology for brainstem cranial nerves using statistical shape model (SSM)-based deformable 3D contours from T2 MR images. METHODS: We create shape models for ten pairs of cranial nerves. High-resolution T2 MR images are segmented for nerve centerline using a 1-Simplex discrete deformable 3D contour model. These segmented centerlines comprise training datasets for the shape model. Point correspondence for the training dataset is performed using an entropy-based energy minimization framework applied to particles located on the centerline curve. The shape information is incorporated into the 1-Simplex model by introducing a shape-based internal force, making the deformation stable against low resolution and image artifacts. RESULTS: The proposed method is validated through extensive experiments using both synthetic and patient MRI data. The robustness and stability of the proposed method are experimented using synthetic datasets. SSMs are constructed independently for ten pairs (CNIII-CNXII) of brainstem cranial nerves using ten non-pathological image datasets of the brainstem. The constructed ten SSMs are assessed in terms of compactness, specificity and generality. In order to quantify the error distances between segmented results and ground truths, two metrics are used: mean absolute shape distance (MASD) and Hausdorff distance (HD). MASD error using the proposed shape model is 0.19 ± 0.13 (mean ± std. deviation) mm and HD is 0.21 mm which are sub-voxel accuracy given the input image resolution. CONCLUSION: This paper described a probabilistic digital atlas of the ten brainstem-attached cranial nerve pairs by incorporating a statistical shape model with the 1-Simplex deformable contour. The integration of shape information as a priori knowledge results in robust and accurate centerline segmentations from even low-resolution MRI data, which is essential in neurosurgical planning and simulations for accurate and robust 3D patient-specific models of critical tissues including cranial nerves.
Authors: Martin A Styner; Kumar T Rajamani; Lutz-Peter Nolte; Gabriel Zsemlye; Gábor Székely; Chris J Taylor; Rhodri H Davies Journal: Inf Process Med Imaging Date: 2003-07
Authors: Terry S Yoo; Michael J Ackerman; William E Lorensen; Will Schroeder; Vikram Chalana; Stephen Aylward; Dimitris Metaxas; Ross Whitaker Journal: Stud Health Technol Inform Date: 2002
Authors: Sharmin Sultana; Jason E Blatt; Benjamin Gilles; Tanweer Rashid; Michel A Audette Journal: IEEE Trans Med Imaging Date: 2017-04-12 Impact factor: 10.048
Authors: Gregor Antoniadis; Thomas Kretschmer; Maria Teresa Pedro; Ralph W König; Christian P G Heinen; Hans-Peter Richter Journal: Dtsch Arztebl Int Date: 2014-04-18 Impact factor: 5.594