MTR-PET: Multi-temporal resolution PET images for lymphoma segmentation

Wenbo Pang, Siqi Li, Huiyan Jiang, Yu dong Yao

Research output: Contribution to journalArticlepeer-review

Abstract

Lymphoma segmentation on positron emission tomography/computed tomography (PET/CT) is a challenge in clinical diagnosis. Existing methods commonly locate lymphoma candidates on PET images and removes false positive candidates using CT images. However, the combined use of PET with CT in segmentation is not trivial, either requiring CT-based multi-organ segmentation or PET/CT registration. The registration of PET/CT will introduce information change in images. Therefore, accurate lymphoma segmentation on PET images is of great importance for medical diagnoses. In this paper, we propose a novel idea of lymphoma segmentation on multi-temporal resolution PET (MTR-PET) images. Instead of using CT information, this method investigates differences of lymphoma and other tissues on different temporal resolution PET images. Two related features, metabolic variation and metabolic heterogeneity, are proposed and combined with traditional features to construct a statistical analysis model for removing false lymphoma candidates. To obtain accurate boundary results, CNN networks are used for lymphoma segmentation on the region of interesting (ROI) images. Our proposed method is evaluated on 53 MTR-PET images with a detection sensibility of 0.9953 and a segmentation Dice coefficient of 0.8667. Experiments and results demonstrate that information of MTR-PET images can significantly improve the performance of lymphoma segmentation.

Original languageEnglish
Article number105529
JournalBiomedical Signal Processing and Control
Volume87
DOIs
StatePublished - Jan 2024

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Keywords

  • Deep learning
  • Features analysis
  • Lymphoma segmentation
  • Multi-temporal resolution PET
  • Tumor detection

Cite this