Paediatric Liver Segmentation for Low-Contrast CT Images

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-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 languageEnglish
Title of host publicationData Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis
Subtitle of host publicationFirst International Workshop, DATRA 2018 and Third International Workshop, PIPPI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings
EditorsAndrew Melbourne, Roxane Licandro, Matthew DiFranco, Paolo Rota, Melanie Gau, Martin Kampel, Rosalind Aughwane, Pim Moeskops, Ernst Schwartz, Emma Robinson, Antonios Makropoulos
PublisherSpringer
Pages169-178
Number of pages10
ISBN (Electronic)978-3-030-00807-9
ISBN (Print)978-3-030-00806-2
DOIs
Publication statusPublished - 1 Jan 2018
EventData Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018. -
Duration: 16 Oct 2018 → …

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Number11076
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceData Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis. PIPPI 2018, DATRA 2018.
Period16/10/18 → …

Keywords

  • Adaptive-kernel
  • Low contrast CT
  • PET-CT

Fingerprint Dive into the research topics of 'Paediatric Liver Segmentation for Low-Contrast CT Images'. Together they form a unique fingerprint.

Cite this