-
Tytuł:
-
Hybrid PET/MRI co-segmentation based on joint fuzzy connectedness and graph cut.
-
Autorzy:
-
Sbei A; Université de Tunis El Manar, Institut Supérieur d'Informatique, Research Team on Intelligent Systems in Imaging and Articial Vision (SIIVA), LR16ES06 Laboratoire de recherche en Informatique, Modélisation et Traitement de l'Information et de la Connaissance (LIMTIC), Tunisia; Nuclear Medicine Department, Pasteur Institute of Tunis, Tunis, Tunisia.
ElBedoui K; Université de Tunis El Manar, Institut Supérieur d'Informatique, Research Team on Intelligent Systems in Imaging and Articial Vision (SIIVA), LR16ES06 Laboratoire de recherche en Informatique, Modélisation et Traitement de l'Information et de la Connaissance (LIMTIC), Tunisia; Université de Carthage, Ecole Nationale d'Ingénieurs de Carthage, Tunisia.
Barhoumi W; Université de Tunis El Manar, Institut Supérieur d'Informatique, Research Team on Intelligent Systems in Imaging and Articial Vision (SIIVA), LR16ES06 Laboratoire de recherche en Informatique, Modélisation et Traitement de l'Information et de la Connaissance (LIMTIC), Tunisia; Université de Carthage, Ecole Nationale d'Ingénieurs de Carthage, Tunisia. Electronic address: walid_.
Maksud P; Nuclear Medicine Department, Pitié-Salpêtrière Hospital, AP-HP, Paris, France.
Maktouf C; Nuclear Medicine Department, Pasteur Institute of Tunis, Tunis, Tunisia.
-
Źródło:
-
Computer methods and programs in biomedicine [Comput Methods Programs Biomed] 2017 Oct; Vol. 149, pp. 29-41. Date of Electronic Publication: 2017 Jul 19.
-
Typ publikacji:
-
Journal Article
-
Język:
-
English
-
Imprint Name(s):
-
Publication: Limerick : Elsevier Scientific Publishers
Original Publication: Amsterdam : Elsevier Science Publishers, c1984-
-
MeSH Terms:
-
Image Processing, Computer-Assisted*
Magnetic Resonance Imaging*
Positron-Emission Tomography*
Neoplasms/*diagnostic imaging
Algorithms ; Humans
-
Contributed Indexing:
-
Keywords: Co-segmentation; GC; Graph cut; Iterative relative fuzzy connectedness; PET/MRI
-
Entry Date(s):
-
Date Created: 20170814 Date Completed: 20171218 Latest Revision: 20181202
-
Update Code:
-
20240105
-
DOI:
-
10.1016/j.cmpb.2017.07.006
-
PMID:
-
28802328
-
Background and Objective: Tumor segmentation from hybrid PET/MRI scans may be highly beneficial in radiotherapy treatment planning. Indeed, it gives for both modalities the suitable information that could make the delineation of tumors more accurate than using each one apart. We aim in this work to propose a co-segmentation method that deals with several challenges, notably the lack of one-to-one correspondence between tumors of the two modalities and the boundaries' smoothing.
Methods: The proposed method is designed to surpass these limits, we propose a segmentation method based on the GC sum max technique. The method takes the advantage of Iterative Relative Fuzzy Connectedness (IRFC) on seeds initialization, and the standard min-cut/max-flow technique for the boundary smoothing. Seed initialization was accurately performed thanks to high uptake regions on PET. Besides, a visibility weighting scheme was adapted to achieve the task of co-segmentation using the IRFC algorithm. Then, given the co-segmented regions, we introduce a morphological-based technique that provides object seeds to standard Graph Cut (GC) allowing it to avoid the shrinking problem. Finally, for each modality, the segmentation task is formulated as an energy minimization problem which is resolved by a min-cut/max-flow technique.
Results: The overlap ratio (denoted DSC) between our segmentation results and the ground-truth for PET images is 92.63 ± 1.03, while the DSC for MRI images is 90.61 ± 3.70.
Conclusions: The proposed method was tested on different types of diseases and it outperformed the state-of-the-art methods. We show its superiority in terms of assymetric relation between PET and MRI and tumors heterogeneity.
(Copyright © 2017 Elsevier B.V. All rights reserved.)
