Literature DB >> 35636391

Reference-free learning-based similarity metric for motion compensation in cone-beam CT.

H Huang1, J H Siewerdsen1,2,3, W Zbijewski1, C R Weiss2, M Unberath3, T Ehtiati4, A Sisniega1.   

Abstract

Purpose. Patient motion artifacts present a prevalent challenge to image quality in interventional cone-beam CT (CBCT). We propose a novel reference-free similarity metric (DL-VIF) that leverages the capability of deep convolutional neural networks (CNN) to learn features associated with motion artifacts within realistic anatomical features. DL-VIF aims to address shortcomings of conventional metrics of motion-induced image quality degradation that favor characteristics associated with motion-free images, such as sharpness or piecewise constancy, but lack any awareness of the underlying anatomy, potentially promoting images depicting unrealistic image content. DL-VIF was integrated in an autofocus motion compensation framework to test its performance for motion estimation in interventional CBCT.Methods. DL-VIF is a reference-free surrogate for the previously reported visual image fidelity (VIF) metric, computed against a motion-free reference, generated using a CNN trained using simulated motion-corrupted and motion-free CBCT data. Relatively shallow (2-ResBlock) and deep (3-Resblock) CNN architectures were trained and tested to assess sensitivity to motion artifacts and generalizability to unseen anatomy and motion patterns. DL-VIF was integrated into an autofocus framework for rigid motion compensation in head/brain CBCT and assessed in simulation and cadaver studies in comparison to a conventional gradient entropy metric.Results. The 2-ResBlock architecture better reflected motion severity and extrapolated to unseen data, whereas 3-ResBlock was found more susceptible to overfitting, limiting its generalizability to unseen scenarios. DL-VIF outperformed gradient entropy in simulation studies yielding average multi-resolution structural similarity index (SSIM) improvement over uncompensated image of 0.068 and 0.034, respectively, referenced to motion-free images. DL-VIF was also more robust in motion compensation, evidenced by reduced variance in SSIM for various motion patterns (σDL-VIF = 0.008 versusσgradient entropy = 0.019). Similarly, in cadaver studies, DL-VIF demonstrated superior motion compensation compared to gradient entropy (an average SSIM improvement of 0.043 (5%) versus little improvement and even degradation in SSIM, respectively) and visually improved image quality even in severely motion-corrupted images.
Conclusion: The studies demonstrated the feasibility of building reference-free similarity metrics for quantification of motion-induced image quality degradation and distortion of anatomical structures in CBCT. DL-VIF provides a reliable surrogate for motion severity, penalizes unrealistic distortions, and presents a valuable new objective function for autofocus motion compensation in CBCT.
© 2022 Institute of Physics and Engineering in Medicine.

Entities:  

Keywords:  cone-beam CT; deep learning; interventional CBCT; motion compensation

Mesh:

Year:  2022        PMID: 35636391      PMCID: PMC9254028          DOI: 10.1088/1361-6560/ac749a

Source DB:  PubMed          Journal:  Phys Med Biol        ISSN: 0031-9155            Impact factor:   4.174


  52 in total

1.  An investigation of 4D cone-beam CT algorithms for slowly rotating scanners.

Authors:  Frank Bergner; Timo Berkus; Markus Oelhafen; Patrik Kunz; Tinsu Pa; Rainer Grimmer; Ludwig Ritschl; Marc Kachelriess
Journal:  Med Phys       Date:  2010-09       Impact factor: 4.071

2.  Interventional 4D motion estimation and reconstruction of cardiac vasculature without motion periodicity assumption.

Authors:  C Rohkohl; G Lauritsch; L Biller; M Prümmer; J Boese; J Hornegger
Journal:  Med Image Anal       Date:  2010-06-02       Impact factor: 8.545

Review 3.  Nonvascular and portal vein applications of cone-beam computed tomography: current status.

Authors:  Baljendra S Kapoor; Anthony Esparaz; Abraham Levitin; Gordon McLennan; Eunice Moon; Mark Sands
Journal:  Tech Vasc Interv Radiol       Date:  2013-09

4.  Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images.

Authors:  Babak Ehteshami Bejnordi; Guido Zuidhof; Maschenka Balkenhol; Meyke Hermsen; Peter Bult; Bram van Ginneken; Nico Karssemeijer; Geert Litjens; Jeroen van der Laak
Journal:  J Med Imaging (Bellingham)       Date:  2017-12-14

5.  C-Arm Conebeam CT Perfusion Imaging in the Angiographic Suite: A Comparison with Multidetector CT Perfusion Imaging.

Authors:  K Niu; P Yang; Y Wu; T Struffert; A Doerfler; S Schafer; K Royalty; C Strother; G-H Chen
Journal:  AJNR Am J Neuroradiol       Date:  2016-02-18       Impact factor: 3.825

6.  Motion compensation in extremity cone-beam CT using a penalized image sharpness criterion.

Authors:  A Sisniega; J W Stayman; J Yorkston; J H Siewerdsen; W Zbijewski
Journal:  Phys Med Biol       Date:  2017-03-22       Impact factor: 3.609

7.  Optimized Flat-Detector CT in Stroke Imaging: Ready for First-Line Use?

Authors:  Matthias Eckert; Philipp Gölitz; Hannes Lücking; Tobias Struffert; Frauke Knossalla; Arnd Doerfler
Journal:  Cerebrovasc Dis       Date:  2016-10-18       Impact factor: 2.762

8.  Appearance Learning for Image-Based Motion Estimation in Tomography.

Authors:  Alexander Preuhs; Michael Manhart; Philipp Roser; Elisabeth Hoppe; Yixing Huang; Marios Psychogios; Markus Kowarschik; Andreas Maier
Journal:  IEEE Trans Med Imaging       Date:  2020-10-28       Impact factor: 10.048

9.  Correction of patient motion in cone-beam CT using 3D-2D registration.

Authors:  S Ouadah; M Jacobson; J W Stayman; T Ehtiati; C Weiss; J H Siewerdsen
Journal:  Phys Med Biol       Date:  2017-11-09       Impact factor: 3.609

10.  Cardiac Motion Correction for Helical CT Scan With an Ordinary Pitch.

Authors:  Seungeon Kim; Yongjin Chang; Jong Beom Ra
Journal:  IEEE Trans Med Imaging       Date:  2018-07       Impact factor: 10.048

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.