Automatic 3D modelling for prostate cancer brachytherapy

Mohammad Ali Jan Ghasab, Andrew P. Paplinski, John M. Betts, Hayley M. Reynolds, Annette Haworth

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

3D visualisation is being used increasingly to improve the accuracy of biopsies and seed placement for prostate cancer brachytherapy (the implantation of small radioactive 'seeds' for radiotherapy). The construction of a 3D model requires the segmentation of 2D Magnetic Resonance (MR) images, which remains a challenging problem. The current practice of manual segmentation requires a very high level of expertise and is time-consuming. In this paper, we propose a new method for creating a 3D model of the prostate from MR images obtained pre-operatively. To do this, an Active Appearance Model (AAM) is created from the image data by grouping the MR images based on the region of the prostate each is taken from. A fast optimisation algorithm is then used to segment a new prostate using the AAM. Our results show that this method is fast and accurate compared with manual segmentation enabling this method to be used intra-operatively.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing - Proceedings
Subtitle of host publication17–20 September 2017 China National Convention Center Beijing, China
EditorsJiebo Luo, Wenjun Zeng, Yu-Jin Zhang
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4452-4456
Number of pages5
ISBN (Electronic)9781509021758
ISBN (Print)9781509021765, 9781509021741
DOIs
Publication statusPublished - 2017
EventIEEE International Conference on Image Processing 2017 - China National Convention Center (CNCC), Beijing, China
Duration: 17 Sep 201720 Sep 2017
Conference number: 24th
http://www.2017.ieeeicip.org/
http://2017.ieeeicip.org/

Conference

ConferenceIEEE International Conference on Image Processing 2017
Abbreviated titleICIP 2017
CountryChina
CityBeijing
Period17/09/1720/09/17
Internet address

Keywords

  • Medical Image Analysis
  • Prostate Modelling
  • Segmentation
  • Visualisation

Cite this

Ghasab, M. A. J., Paplinski, A. P., Betts, J. M., Reynolds, H. M., & Haworth, A. (2017). Automatic 3D modelling for prostate cancer brachytherapy. In J. Luo, W. Zeng, & Y-J. Zhang (Eds.), 2017 IEEE International Conference on Image Processing - Proceedings: 17–20 September 2017 China National Convention Center Beijing, China (pp. 4452-4456). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2017.8297124
Ghasab, Mohammad Ali Jan ; Paplinski, Andrew P. ; Betts, John M. ; Reynolds, Hayley M. ; Haworth, Annette. / Automatic 3D modelling for prostate cancer brachytherapy. 2017 IEEE International Conference on Image Processing - Proceedings: 17–20 September 2017 China National Convention Center Beijing, China. editor / Jiebo Luo ; Wenjun Zeng ; Yu-Jin Zhang. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 4452-4456
@inproceedings{7ae9ff71c30e49b694861142782f8c59,
title = "Automatic 3D modelling for prostate cancer brachytherapy",
abstract = "3D visualisation is being used increasingly to improve the accuracy of biopsies and seed placement for prostate cancer brachytherapy (the implantation of small radioactive 'seeds' for radiotherapy). The construction of a 3D model requires the segmentation of 2D Magnetic Resonance (MR) images, which remains a challenging problem. The current practice of manual segmentation requires a very high level of expertise and is time-consuming. In this paper, we propose a new method for creating a 3D model of the prostate from MR images obtained pre-operatively. To do this, an Active Appearance Model (AAM) is created from the image data by grouping the MR images based on the region of the prostate each is taken from. A fast optimisation algorithm is then used to segment a new prostate using the AAM. Our results show that this method is fast and accurate compared with manual segmentation enabling this method to be used intra-operatively.",
keywords = "Medical Image Analysis, Prostate Modelling, Segmentation, Visualisation",
author = "Ghasab, {Mohammad Ali Jan} and Paplinski, {Andrew P.} and Betts, {John M.} and Reynolds, {Hayley M.} and Annette Haworth",
year = "2017",
doi = "10.1109/ICIP.2017.8297124",
language = "English",
isbn = "9781509021765",
pages = "4452--4456",
editor = "Jiebo Luo and Zeng, {Wenjun } and Zhang, {Yu-Jin }",
booktitle = "2017 IEEE International Conference on Image Processing - Proceedings",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Ghasab, MAJ, Paplinski, AP, Betts, JM, Reynolds, HM & Haworth, A 2017, Automatic 3D modelling for prostate cancer brachytherapy. in J Luo, W Zeng & Y-J Zhang (eds), 2017 IEEE International Conference on Image Processing - Proceedings: 17–20 September 2017 China National Convention Center Beijing, China. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 4452-4456, IEEE International Conference on Image Processing 2017, Beijing, China, 17/09/17. https://doi.org/10.1109/ICIP.2017.8297124

Automatic 3D modelling for prostate cancer brachytherapy. / Ghasab, Mohammad Ali Jan; Paplinski, Andrew P.; Betts, John M.; Reynolds, Hayley M.; Haworth, Annette.

2017 IEEE International Conference on Image Processing - Proceedings: 17–20 September 2017 China National Convention Center Beijing, China. ed. / Jiebo Luo; Wenjun Zeng; Yu-Jin Zhang. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 4452-4456.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Automatic 3D modelling for prostate cancer brachytherapy

AU - Ghasab, Mohammad Ali Jan

AU - Paplinski, Andrew P.

AU - Betts, John M.

AU - Reynolds, Hayley M.

AU - Haworth, Annette

PY - 2017

Y1 - 2017

N2 - 3D visualisation is being used increasingly to improve the accuracy of biopsies and seed placement for prostate cancer brachytherapy (the implantation of small radioactive 'seeds' for radiotherapy). The construction of a 3D model requires the segmentation of 2D Magnetic Resonance (MR) images, which remains a challenging problem. The current practice of manual segmentation requires a very high level of expertise and is time-consuming. In this paper, we propose a new method for creating a 3D model of the prostate from MR images obtained pre-operatively. To do this, an Active Appearance Model (AAM) is created from the image data by grouping the MR images based on the region of the prostate each is taken from. A fast optimisation algorithm is then used to segment a new prostate using the AAM. Our results show that this method is fast and accurate compared with manual segmentation enabling this method to be used intra-operatively.

AB - 3D visualisation is being used increasingly to improve the accuracy of biopsies and seed placement for prostate cancer brachytherapy (the implantation of small radioactive 'seeds' for radiotherapy). The construction of a 3D model requires the segmentation of 2D Magnetic Resonance (MR) images, which remains a challenging problem. The current practice of manual segmentation requires a very high level of expertise and is time-consuming. In this paper, we propose a new method for creating a 3D model of the prostate from MR images obtained pre-operatively. To do this, an Active Appearance Model (AAM) is created from the image data by grouping the MR images based on the region of the prostate each is taken from. A fast optimisation algorithm is then used to segment a new prostate using the AAM. Our results show that this method is fast and accurate compared with manual segmentation enabling this method to be used intra-operatively.

KW - Medical Image Analysis

KW - Prostate Modelling

KW - Segmentation

KW - Visualisation

UR - http://www.scopus.com/inward/record.url?scp=85045310816&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8297124

DO - 10.1109/ICIP.2017.8297124

M3 - Conference Paper

SN - 9781509021765

SN - 9781509021741

SP - 4452

EP - 4456

BT - 2017 IEEE International Conference on Image Processing - Proceedings

A2 - Luo, Jiebo

A2 - Zeng, Wenjun

A2 - Zhang, Yu-Jin

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Ghasab MAJ, Paplinski AP, Betts JM, Reynolds HM, Haworth A. Automatic 3D modelling for prostate cancer brachytherapy. In Luo J, Zeng W, Zhang Y-J, editors, 2017 IEEE International Conference on Image Processing - Proceedings: 17–20 September 2017 China National Convention Center Beijing, China. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 4452-4456 https://doi.org/10.1109/ICIP.2017.8297124