Title: Performance analysis of different segmentation methods applied to positron emission tomography image fusion

Authors: Abdallah Mehidi; Malika Mimi; Jerome Lapuyade-Lahorgue

Addresses: Laboratory of Signals and Systems, Faculty of Science and Technology, Abdelhamid Ibn Badis University of Mostaganem, Algeria ' Laboratory of Signals and Systems, Faculty of Science and Technology, Abdelhamid Ibn Badis University of Mostaganem, Algeria ' LITIS EA 4108, Equipe Quantif, University of Rouen, France

Abstract: The objective of this paper is to present and analyse the main techniques of PET image segmentation and to provide a comparative study of all methods in terms of precision, accuracy assessment and reproducibility. We report the most recent results of tumour image segmentation that are used in literature. Six state-of-the-art tumour segmentation algorithms are applied to sets of PET tumours which are characterised by the following properties: noise levels, wide range of contrast, uptake heterogeneity and complexity of the form by considering clinical tumour cases. The obtained results show that the fuzzy locally adaptive Bayesian (FLAB) provides superior accuracy and higher precision compared to the recently used methods namely hidden fuzzy Markov fields (HFMF) and fuzzy hidden Markov chains (FHMC). The FLAB outperforms as well other clustering-based approaches like fuzzy C-means (FCM), fuzzy local information C-means (FLICM) and automated generalised fuzzy C-means (GFCM) with estimated norm less than 3. Furthermore, we show that the GFCM achieves the best results surpassing all other techniques when the estimated norm values are greater than 3.

Keywords: image segmentation; clustering methods-Bayesian segmentation; fuzzy C-means Hilbertian-norm; positron emission tomography; PET; image fusion.

DOI: 10.1504/IJBET.2022.125572

International Journal of Biomedical Engineering and Technology, 2022 Vol.40 No.2, pp.108 - 129

Received: 04 Nov 2019
Accepted: 30 Jan 2020
Published online: 16 Sep 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article