Interactive Segmentation with Curve-based Template Deformation for Spatiotemporal Computed Tomography of Swallowing Motion

Overview

Journal PLoS One

Specialties General Medicine
Science

Date 2024 Oct 21

PMID 39432481

Authors

Yuki Kimura

Takashi Ijiri

Yoko Inamoto

Takuya Hashimoto

Yukihiro Michiwaki

Affiliations

Soon will be listed here.

Abstract

Repeating X-ray computed tomography (CT) measurements over a short period of time allows for obtaining a spatiotemporal four-dimensional (4D) volume image. This study presents an interactive method for segmenting a 4DCT image by fitting a template model to a target organ. The template consists of a three-dimensional (3D) mesh model and free-form-deformation (FFD) cage enclosing the mesh. The user deforms the template by placing multiple curve constraints that specify the boundary shape of the template in 3D space. We also present curve constraints shared over all time frames and interpolated along the time axis to facilitate efficient curve specification. Our method formulates the template deformation using the FFD cage modification, allowing the user to switch between our curve-based method and traditional FFD at any time. To illustrate the feasibility of our method, we show segmentation results in which we could accurately segment three organs from a 4DCT image capturing a swallowing motion. To evaluate the usability of our method, we conducted a user study comparing our curve-based method with the cage-based FFD. We found that the participants finished segmentation in approximately 20% interaction time periods on average with our method.

References

Jahani N, Choi S, Choi J, Iyer K, Hoffman E, Lin C . Assessment of regional ventilation and deformation using 4D-CT imaging for healthy human lungs during tidal breathing. J Appl Physiol (1985). 2015; 119(10):1064-74. PMC: 4816408. DOI: 10.1152/japplphysiol.00339.2015. View

Ecabert O, Peters J, Schramm H, Lorenz C, von Berg J, Walker M . Automatic model-based segmentation of the heart in CT images. IEEE Trans Med Imaging. 2008; 27(9):1189-201. DOI: 10.1109/TMI.2008.918330. View

Kim H, Kim Y, Kim B, Shin D, Lee S, Choi S . Hyoid Bone Tracking in a Videofluoroscopic Swallowing Study Using a Deep-Learning-Based Segmentation Network. Diagnostics (Basel). 2021; 11(7). PMC: 8303435. DOI: 10.3390/diagnostics11071147. View

Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell. 2016; 39(4):640-651. DOI: 10.1109/TPAMI.2016.2572683. View

Inamoto Y, Gonzalez-Fernandez M, Saitoh E . 3D-CT Evaluation of Swallowing: Metrics of the Swallowing Response Using Swallowing CT. Dysphagia. 2021; 37(2):237-249. PMC: 8948108. DOI: 10.1007/s00455-021-10288-2. View

Zhang Z, Coyle J, Sejdic E . Automatic hyoid bone detection in fluoroscopic images using deep learning. Sci Rep. 2018; 8(1):12310. PMC: 6097989. DOI: 10.1038/s41598-018-30182-6. View

. Surface Reconstruction From Non-parallel Curve Networks. Comput Graph Forum. 2011; 27(2):155-163. PMC: 2733791. DOI: 10.1111/j.1467-8659.2008.01112.x. View

Brinkhorst M, Foumani M, van Rosmalen J, Selles R, Hovius S, Strackee S . Four-dimensional CT analysis of carpal kinematics: An explorative study on the effect of sex and hand-dominance. J Biomech. 2021; 139:110870. DOI: 10.1016/j.jbiomech.2021.110870. View

He W, Zhang C, Dai J, Liu L, Wang T, Liu X . A statistical deformation model-based data augmentation method for volumetric medical image segmentation. Med Image Anal. 2023; 91:102984. DOI: 10.1016/j.media.2023.102984. View

10.

Pizer S, Fletcher P, Joshi S, Thall A, Chen J, Fridman Y . Deformable M-Reps for 3D Medical Image Segmentation. Int J Comput Vis. 2013; 55(2-3):85-106. PMC: 3697155. DOI: 10.1023/a:1026313132218. View

11.

Duan J, Bello G, Schlemper J, Bai W, Dawes T, Biffi C . Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach. IEEE Trans Med Imaging. 2019; 38(9):2151-2164. PMC: 6728160. DOI: 10.1109/TMI.2019.2894322. View

12.

Liang X, Li N, Zhang Z, Xiong J, Zhou S, Xie Y . Incorporating the hybrid deformable model for improving the performance of abdominal CT segmentation via multi-scale feature fusion network. Med Image Anal. 2021; 73:102156. DOI: 10.1016/j.media.2021.102156. View

13.

Fujii N, Inamoto Y, Saitoh E, Baba M, Okada S, Yoshioka S . Evaluation of swallowing using 320-detector-row multislice CT. Part I: single- and multiphase volume scanning for three-dimensional morphological and kinematic analysis. Dysphagia. 2010; 26(2):99-107. DOI: 10.1007/s00455-009-9268-2. View