Paediatric Liver Segmentation for Low-Contrast CT Images

Mariusz Bajger; Gobert Lee; Martin Caon

doi:10.1007/978-3-030-00807-9_17

Paediatric Liver Segmentation for Low-Contrast CT Images

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

Abstract

CT images from combined PET-CT scanners are of low contrast. Automatic organ segmentation on these images are challenging. This paper proposed an adaptive kernel-based Statistical Region Merging (SRM) algorithm for paediatric liver segmentation in low contrast PET-CT images. The results are compared to that from the original SRM. The average dice index is 0.79 for SRM and 0.85 for the adaptive kernel-based SRM. In addition, the proposed method was successful in segmenting all 37 CT images while SRM failed in 5 images.

Original language	English
Title of host publication	Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings
Subtitle of host publication	First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings
Editors	Andrew Melbourne, Roxane Licandro, Matthew DiFranco, Paolo Rota, Melanie Gau, Martin Kampel, Rosalind Aughwane, Pim Moeskops, Ernst Schwartz, Emma Robinson, Antonios Makropoulos
Publisher	Springer
Pages	169-178
Number of pages	10
ISBN (Electronic)	978-3-030-00807-9
ISBN (Print)	978-3-030-00806-2
DOIs	https://doi.org/10.1007/978-3-030-00807-9_17
Publication status	Published - 1 Jan 2018
Event	Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018. - Duration: 16 Oct 2018 → …

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Number	11076
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018.
Period	16/10/18 → …

Keywords

Adaptive-kernel
Low contrast CT
PET-CT

Access to Document

10.1007/978-3-030-00807-9_17Licence: In Copyright

https://rdcu.be/dA0SCLicence: In Copyright

Cite this

Bajger, M., Lee, G., & Caon, M. (2018). Paediatric Liver Segmentation for Low-Contrast CT Images. In A. Melbourne, R. Licandro, M. DiFranco, P. Rota, M. Gau, M. Kampel, R. Aughwane, P. Moeskops, E. Schwartz, E. Robinson, & A. Makropoulos (Eds.), Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings: First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings (pp. 169-178). (Lecture Notes in Computer Science; No. 11076). Springer . https://doi.org/10.1007/978-3-030-00807-9_17

Bajger, Mariusz ; Lee, Gobert ; Caon, Martin. / Paediatric Liver Segmentation for Low-Contrast CT Images. Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings: First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings. editor / Andrew Melbourne ; Roxane Licandro ; Matthew DiFranco ; Paolo Rota ; Melanie Gau ; Martin Kampel ; Rosalind Aughwane ; Pim Moeskops ; Ernst Schwartz ; Emma Robinson ; Antonios Makropoulos. Springer , 2018. pp. 169-178 (Lecture Notes in Computer Science; 11076).

@inproceedings{22a2f7d8f90c4daab9cbf76209a10bcf,

title = "Paediatric Liver Segmentation for Low-Contrast CT Images",

abstract = "CT images from combined PET-CT scanners are of low contrast. Automatic organ segmentation on these images are challenging. This paper proposed an adaptive kernel-based Statistical Region Merging (SRM) algorithm for paediatric liver segmentation in low contrast PET-CT images. The results are compared to that from the original SRM. The average dice index is 0.79 for SRM and 0.85 for the adaptive kernel-based SRM. In addition, the proposed method was successful in segmenting all 37 CT images while SRM failed in 5 images.",

keywords = "Adaptive-kernel, Low contrast CT, PET-CT",

author = "Mariusz Bajger and Gobert Lee and Martin Caon",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-3-030-00807-9_17",

language = "English",

isbn = "978-3-030-00806-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

number = "11076",

pages = "169--178",

editor = "Andrew Melbourne and Roxane Licandro and Matthew DiFranco and Paolo Rota and Melanie Gau and Kampel, {Martin } and Rosalind Aughwane and Pim Moeskops and Ernst Schwartz and Emma Robinson and Antonios Makropoulos",

booktitle = "Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings",

note = "Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018. ; Conference date: 16-10-2018",

}

Bajger, M , Lee, G & Caon, M 2018, Paediatric Liver Segmentation for Low-Contrast CT Images. in A Melbourne, R Licandro, M DiFranco, P Rota, M Gau, M Kampel, R Aughwane, P Moeskops, E Schwartz, E Robinson & A Makropoulos (eds), Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings: First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings. Lecture Notes in Computer Science, no. 11076, Springer , pp. 169-178, Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018., 16/10/18. https://doi.org/10.1007/978-3-030-00807-9_17

Paediatric Liver Segmentation for Low-Contrast CT Images. / Bajger, Mariusz ; Lee, Gobert; Caon, Martin.
Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings: First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings. ed. / Andrew Melbourne; Roxane Licandro; Matthew DiFranco; Paolo Rota; Melanie Gau; Martin Kampel; Rosalind Aughwane; Pim Moeskops; Ernst Schwartz; Emma Robinson; Antonios Makropoulos. Springer , 2018. p. 169-178 (Lecture Notes in Computer Science; No. 11076).

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

TY - GEN

T1 - Paediatric Liver Segmentation for Low-Contrast CT Images

AU - Bajger, Mariusz

AU - Lee, Gobert

AU - Caon, Martin

PY - 2018/1/1

Y1 - 2018/1/1

N2 - CT images from combined PET-CT scanners are of low contrast. Automatic organ segmentation on these images are challenging. This paper proposed an adaptive kernel-based Statistical Region Merging (SRM) algorithm for paediatric liver segmentation in low contrast PET-CT images. The results are compared to that from the original SRM. The average dice index is 0.79 for SRM and 0.85 for the adaptive kernel-based SRM. In addition, the proposed method was successful in segmenting all 37 CT images while SRM failed in 5 images.

AB - CT images from combined PET-CT scanners are of low contrast. Automatic organ segmentation on these images are challenging. This paper proposed an adaptive kernel-based Statistical Region Merging (SRM) algorithm for paediatric liver segmentation in low contrast PET-CT images. The results are compared to that from the original SRM. The average dice index is 0.79 for SRM and 0.85 for the adaptive kernel-based SRM. In addition, the proposed method was successful in segmenting all 37 CT images while SRM failed in 5 images.

KW - Adaptive-kernel

KW - Low contrast CT

KW - PET-CT

UR - http://www.scopus.com/inward/record.url?scp=85054827763&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-00807-9_17

DO - 10.1007/978-3-030-00807-9_17

M3 - Conference contribution

SN - 978-3-030-00806-2

T3 - Lecture Notes in Computer Science

SP - 169

EP - 178

BT - Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings

A2 - Melbourne, Andrew

A2 - Licandro, Roxane

A2 - DiFranco, Matthew

A2 - Rota, Paolo

A2 - Gau, Melanie

A2 - Kampel, Martin

A2 - Aughwane, Rosalind

A2 - Moeskops, Pim

A2 - Schwartz, Ernst

A2 - Robinson, Emma

A2 - Makropoulos, Antonios

PB - Springer

T2 - Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018.

Y2 - 16 October 2018

ER -

Bajger M , Lee G, Caon M. Paediatric Liver Segmentation for Low-Contrast CT Images. In Melbourne A, Licandro R, DiFranco M, Rota P, Gau M, Kampel M, Aughwane R, Moeskops P, Schwartz E, Robinson E, Makropoulos A, editors, Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018 Held in Conjunction with MICCAI 2018, Proceedings: First International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings. Springer . 2018. p. 169-178. (Lecture Notes in Computer Science; 11076). doi: 10.1007/978-3-030-00807-9_17

Paediatric Liver Segmentation for Low-Contrast CT Images

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this