1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25181
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHerzig, Ivo-
dc.contributor.authorPaysan, Pascal-
dc.contributor.authorScheib, Stefan-
dc.contributor.authorZüst, Alexander-
dc.contributor.authorSchilling, Frank-Peter-
dc.contributor.authorMontoya, Javier-
dc.contributor.authorAmirian, Mohammadreza-
dc.contributor.authorStadelmann, Thilo-
dc.contributor.authorEggenberger Hotz, Peter-
dc.contributor.authorFüchslin, Rudolf Marcel-
dc.contributor.authorLichtensteiger, Lukas-
dc.date.accessioned2022-06-24T14:09:18Z-
dc.date.available2022-06-24T14:09:18Z-
dc.date.issued2022-06-09-
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/25181-
dc.description.abstractPurpose: Respiratory gated 4D-CBCT suffers from sparseness artefacts caused by the limited number of projections available for each respiratory phase/amplitude. These artefacts severely impact deformable image registration methods used to extract motion information. We use deep learning-based methods to predict displacement vector-fields (DVF) from sparse 4D-CBCT images to alleviate the impacts of sparseness artefacts. Methods: We trained U-Net-type convolutional neural network models to predict multiple (10) DVFs in a single forward pass given multiple sparse, gated CBCT and an optional artefact-free reference image as inputs. The predicted DVFs are used to warp the reference image to the different motion states, resulting in an artefact-free image for each state. The supervised training uses data generated by a motion simulation framework. The training dataset consists of 560 simulated 4D-CBCT images of 56 different patients; the generated data include fully sampled ground-truth images that are used to train the network. We compare the results of our method to pairwise image registration (reference image to single sparse image) using a) the deeds algorithm and b) VoxelMorph with image pair inputs. Results: We show that our method clearly outperforms pairwise registration using the deeds algorithm alone. PSNR improved from 25.8 to 46.4, SSIM from 0.9296 to 0.9999. In addition, the runtime of our learning-based method is orders of magnitude shorter (2 seconds instead of 10 minutes). Our results also indicate slightly improved performance compared to pairwise registration (delta-PSNR=1.2). We also trained a model that does not require the artefact-free reference image (which is usually not available) during inference demonstrating only marginally compromised results (delta-PSNR=-0.8). Conclusion: To the best of our knowledge, this is the first time CNNs are used to predict multi-phase DVFs in a single forward pass. This enables novel applications such as 4D-auto-segmentation, motion compensated image reconstruction, motion analyses, and patient motion modeling.de_CH
dc.language.isoende_CH
dc.publisherAmerican Association of Physicists in Medicinede_CH
dc.relation.ispartofMedical Physicsde_CH
dc.rightsLicence according to publishing contractde_CH
dc.subjectDeep learningde_CH
dc.subjectDeformable image registrationde_CH
dc.subjectCBCTde_CH
dc.subjectMedical imagingde_CH
dc.subjectArtificial intelligencede_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.subject.ddc616: Innere Medizin und Krankheitende_CH
dc.titleDeep learning-based simultaneous multi-phase deformable image registration of sparse 4D-CBCTde_CH
dc.typeKonferenz: Posterde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitCentre for Artificial Intelligence (CAI)de_CH
zhaw.organisationalunitInstitut für Angewandte Mathematik und Physik (IAMP)de_CH
dc.identifier.doi10.1002/mp.15769de_CH
dc.identifier.doi10.21256/zhaw-25181-
zhaw.conference.detailsAAPM Annual Meeting, Washington, DC, USA, 10-14 July 2022de_CH
zhaw.funding.euNode_CH
zhaw.issue6de_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.ende326de_CH
zhaw.pages.starte325de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume49de_CH
zhaw.publication.reviewPeer review (Abstract)de_CH
zhaw.webfeedMachine Perception and Cognitionde_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedDigital Health Labde_CH
zhaw.webfeedZHAW digitalde_CH
zhaw.webfeedIntelligent Vision Systemsde_CH
zhaw.funding.zhawDIR3CT: Deep Image Reconstruction through X-Ray Projection-based 3D Learning of Computed Tomography Volumesde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Herzig-etal_Sparse4DCBCT-multiphase-DIR_AAPM-eposter.pdf713.76 kBAdobe PDFThumbnail
View/Open
Show simple item record
Herzig, I., Paysan, P., Scheib, S., Züst, A., Schilling, F.-P., Montoya, J., Amirian, M., Stadelmann, T., Eggenberger Hotz, P., Füchslin, R. M., & Lichtensteiger, L. (2022). Deep learning-based simultaneous multi-phase deformable image registration of sparse 4D-CBCT [Conference poster]. Medical Physics, 49(6), e325–e326. https://doi.org/10.1002/mp.15769
Herzig, I. et al. (2022) ‘Deep learning-based simultaneous multi-phase deformable image registration of sparse 4D-CBCT’, in Medical Physics. American Association of Physicists in Medicine, pp. e325–e326. Available at: https://doi.org/10.1002/mp.15769.
I. Herzig et al., “Deep learning-based simultaneous multi-phase deformable image registration of sparse 4D-CBCT,” in Medical Physics, Jun. 2022, vol. 49, no. 6, pp. e325–e326. doi: 10.1002/mp.15769.
HERZIG, Ivo, Pascal PAYSAN, Stefan SCHEIB, Alexander ZÜST, Frank-Peter SCHILLING, Javier MONTOYA, Mohammadreza AMIRIAN, Thilo STADELMANN, Peter EGGENBERGER HOTZ, Rudolf Marcel FÜCHSLIN und Lukas LICHTENSTEIGER, 2022. Deep learning-based simultaneous multi-phase deformable image registration of sparse 4D-CBCT. In: Medical Physics. Conference poster. American Association of Physicists in Medicine. 9 Juni 2022. S. e325–e326
Herzig, Ivo, Pascal Paysan, Stefan Scheib, Alexander Züst, Frank-Peter Schilling, Javier Montoya, Mohammadreza Amirian, et al. 2022. “Deep Learning-Based Simultaneous Multi-Phase Deformable Image Registration of Sparse 4D-CBCT.” Conference poster. In Medical Physics, 49:e325–e26. American Association of Physicists in Medicine. https://doi.org/10.1002/mp.15769.
Herzig, Ivo, et al. “Deep Learning-Based Simultaneous Multi-Phase Deformable Image Registration of Sparse 4D-CBCT.” Medical Physics, vol. 49, no. 6, American Association of Physicists in Medicine, 2022, pp. e325–26, https://doi.org/10.1002/mp.15769.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.