Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors. / Ladefoged, Claes N.; Andersen, Flemming L.; Keller, Sune H.; Beyer, Thomas; Højgaard, Liselotte; Lauze, Francois Bernard.

Proceedings of SPIE Medical Imaging 2014: Image processing. ed. / Sebastien Ourselin; Martin A. Styner. SPIE - International Society for Optical Engineering, 2014. 90341M (Proceedings of S P I E - International Society for Optical Engineering, Vol. 9034). (Progress in Biomedical Optics and Imaging; No. 35, Vol. 15).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Ladefoged, CN, Andersen, FL, Keller, SH, Beyer, T, Højgaard, L & Lauze, FB 2014, Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors. in S Ourselin & MA Styner (eds), Proceedings of SPIE Medical Imaging 2014: Image processing., 90341M, SPIE - International Society for Optical Engineering, Proceedings of S P I E - International Society for Optical Engineering, vol. 9034, Progress in Biomedical Optics and Imaging, no. 35, vol. 15, Medical Imaging 2014, San Diego, United States, 15/02/2014. https://doi.org/10.1117/12.2043779

APA

Ladefoged, C. N., Andersen, F. L., Keller, S. H., Beyer, T., Højgaard, L., & Lauze, F. B. (2014). Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors. In S. Ourselin, & M. A. Styner (Eds.), Proceedings of SPIE Medical Imaging 2014: Image processing [90341M] SPIE - International Society for Optical Engineering. Proceedings of S P I E - International Society for Optical Engineering Vol. 9034 Progress in Biomedical Optics and Imaging Vol. 15 No. 35 https://doi.org/10.1117/12.2043779

Vancouver

Ladefoged CN, Andersen FL, Keller SH, Beyer T, Højgaard L, Lauze FB. Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors. In Ourselin S, Styner MA, editors, Proceedings of SPIE Medical Imaging 2014: Image processing. SPIE - International Society for Optical Engineering. 2014. 90341M. (Proceedings of S P I E - International Society for Optical Engineering, Vol. 9034). (Progress in Biomedical Optics and Imaging; No. 35, Vol. 15). https://doi.org/10.1117/12.2043779

Author

Ladefoged, Claes N. ; Andersen, Flemming L. ; Keller, Sune H. ; Beyer, Thomas ; Højgaard, Liselotte ; Lauze, Francois Bernard. / Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors. Proceedings of SPIE Medical Imaging 2014: Image processing. editor / Sebastien Ourselin ; Martin A. Styner. SPIE - International Society for Optical Engineering, 2014. (Proceedings of S P I E - International Society for Optical Engineering, Vol. 9034). (Progress in Biomedical Optics and Imaging; No. 35, Vol. 15).

Bibtex

@inproceedings{19414e3133ab4372b5856ba7514a1173,
title = "Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors",
abstract = "n combined PET/MR, attenuation correction (AC) is performed indirectly based on the available MR image information. Metal implant-induced susceptibility artifacts and subsequent signal voids challenge MR-based AC. Several papers acknowledge the problem in PET attenuation correction when dental artifacts are ignored, but none of them attempts to solve the problem. We propose a clinically feasible correction method which combines Active Shape Models (ASM) and k- Nearest-Neighbors (kNN) into a simple approach which finds and corrects the dental artifacts within the surface boundaries of the patient anatomy. ASM is used to locate a number of landmarks in the T1-weighted MR-image of a new patient. We calculate a vector of offsets from each voxel within a signal void to each of the landmarks. We then use kNN to classify each voxel as belonging to an artifact or an actual signal void using this offset vector, and fill the artifact voxels with a value representing soft tissue. We tested the method using fourteen patients without artifacts, and eighteen patients with dental artifacts of varying sizes within the anatomical surface of the head/neck region. Though the method wrongly filled a small volume in the bottom part of a maxillary sinus in two patients without any artifacts, due to their abnormal location, it succeeded in filling all dental artifact regions in all patients. In conclusion, we propose a method, which combines ASM and kNN into a simple approach which, as the results show, succeeds to find and correct the dental artifacts within the anatomical surface. ",
author = "Ladefoged, {Claes N.} and Andersen, {Flemming L.} and Keller, {Sune H.} and Thomas Beyer and Liselotte H{\o}jgaard and Lauze, {Francois Bernard}",
year = "2014",
doi = "10.1117/12.2043779",
language = "English",
isbn = "9780819498274 ",
series = "Proceedings of S P I E - International Society for Optical Engineering",
publisher = "SPIE - International Society for Optical Engineering",
editor = "Sebastien Ourselin and Styner, {Martin A.}",
booktitle = "Proceedings of SPIE Medical Imaging 2014",
note = "Medical Imaging 2014 : Image Processing ; Conference date: 15-02-2014",

}

RIS

TY - GEN

T1 - Correction of dental artifacts within the anatomical surface in PET/MRI using active shape models and k-nearest-neighbors

AU - Ladefoged, Claes N.

AU - Andersen, Flemming L.

AU - Keller, Sune H.

AU - Beyer, Thomas

AU - Højgaard, Liselotte

AU - Lauze, Francois Bernard

PY - 2014

Y1 - 2014

N2 - n combined PET/MR, attenuation correction (AC) is performed indirectly based on the available MR image information. Metal implant-induced susceptibility artifacts and subsequent signal voids challenge MR-based AC. Several papers acknowledge the problem in PET attenuation correction when dental artifacts are ignored, but none of them attempts to solve the problem. We propose a clinically feasible correction method which combines Active Shape Models (ASM) and k- Nearest-Neighbors (kNN) into a simple approach which finds and corrects the dental artifacts within the surface boundaries of the patient anatomy. ASM is used to locate a number of landmarks in the T1-weighted MR-image of a new patient. We calculate a vector of offsets from each voxel within a signal void to each of the landmarks. We then use kNN to classify each voxel as belonging to an artifact or an actual signal void using this offset vector, and fill the artifact voxels with a value representing soft tissue. We tested the method using fourteen patients without artifacts, and eighteen patients with dental artifacts of varying sizes within the anatomical surface of the head/neck region. Though the method wrongly filled a small volume in the bottom part of a maxillary sinus in two patients without any artifacts, due to their abnormal location, it succeeded in filling all dental artifact regions in all patients. In conclusion, we propose a method, which combines ASM and kNN into a simple approach which, as the results show, succeeds to find and correct the dental artifacts within the anatomical surface.

AB - n combined PET/MR, attenuation correction (AC) is performed indirectly based on the available MR image information. Metal implant-induced susceptibility artifacts and subsequent signal voids challenge MR-based AC. Several papers acknowledge the problem in PET attenuation correction when dental artifacts are ignored, but none of them attempts to solve the problem. We propose a clinically feasible correction method which combines Active Shape Models (ASM) and k- Nearest-Neighbors (kNN) into a simple approach which finds and corrects the dental artifacts within the surface boundaries of the patient anatomy. ASM is used to locate a number of landmarks in the T1-weighted MR-image of a new patient. We calculate a vector of offsets from each voxel within a signal void to each of the landmarks. We then use kNN to classify each voxel as belonging to an artifact or an actual signal void using this offset vector, and fill the artifact voxels with a value representing soft tissue. We tested the method using fourteen patients without artifacts, and eighteen patients with dental artifacts of varying sizes within the anatomical surface of the head/neck region. Though the method wrongly filled a small volume in the bottom part of a maxillary sinus in two patients without any artifacts, due to their abnormal location, it succeeded in filling all dental artifact regions in all patients. In conclusion, we propose a method, which combines ASM and kNN into a simple approach which, as the results show, succeeds to find and correct the dental artifacts within the anatomical surface.

U2 - 10.1117/12.2043779

DO - 10.1117/12.2043779

M3 - Article in proceedings

SN - 9780819498274

T3 - Proceedings of S P I E - International Society for Optical Engineering

BT - Proceedings of SPIE Medical Imaging 2014

A2 - Ourselin, Sebastien

A2 - Styner, Martin A.

PB - SPIE - International Society for Optical Engineering

T2 - Medical Imaging 2014

Y2 - 15 February 2014

ER -

ID: 128599792