A framework based on hidden Markov trees for multimodal PET/CT image co-segmentation

Autor: Dimitris Visvikis, Wojciech Pieczynski, Mathieu Hatt, Philippe Lambin, Didier Benoit, Houda Hanzouli-Ben Salah, Jerome Lapuyade-Lahorgue, Emmanuel Monfrini, Julien Bert, Angela van Baardwijk
Přispěvatelé: Laboratoire de Traitement de l'Information Medicale (LaTIM), Institut National de la Santé et de la Recherche Médicale (INSERM)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Maastricht Radiation Oncology Clinic (MAASTRO), Maastricht University [Maastricht], Traitement de l'Information Pour Images et Communications (TIPIC-SAMOVAR), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Centre National de la Recherche Scientifique (CNRS), RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, Radiotherapie, Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM)
Jazyk: angličtina
Rok vydání: 2017
Předmět:
QUANTITATION
Computer science
CELL LUNG-CANCER
Bayesian inference
Wavelet Analysis
Image processing
[SDV.IB.MN]Life Sciences [q-bio]/Bioengineering/Nuclear medicine
computed tomography (CT)
computer.software_genre
TRACER UPTAKE
CLASSIFICATION
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Wavelet
Voxel
Positron Emission Tomography Computed Tomography
Image Processing
Computer-Assisted

[INFO.INFO-IM]Computer Science [cs]/Medical Imaging
medicine
Humans
Segmentation
F-18-FDG PET
RECONSTRUCTION
positron emission tomography (PET)
BRAIN
Hidden Markov model
PET-CT
medicine.diagnostic_test
business.industry
segmentation
Pattern recognition
General Medicine
Image segmentation
CT IMAGES
Markov Chains
Contourlet
wavelet and contourlet analysis
TUMOR DELINEATION
MODEL
Positron emission tomography
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
030220 oncology & carcinogenesis
Artificial intelligence
business
Nuclear medicine
computer
hidden Markov trees (HMT)
Zdroj: HAL
Medical Physics
Medical Physics, American Association of Physicists in Medicine, 2017
Medical Physics, 44(11), 5835-5848. Wiley
ISSN: 0094-2405
DOI: 10.1002/mp.12531
Popis: PurposeThe purpose of this study was to investigate the use of a probabilistic quad-tree graph (hidden Markov tree, HMT) to provide fast computation, robustness and an interpretational framework for multimodality image processing and to evaluate this framework for single gross tumor target (GTV) delineation from both positron emission tomography (PET) and computed tomography (CT) images.MethodsWe exploited joint statistical dependencies between hidden states to handle the data stack using multi-observation, multi-resolution of HMT and Bayesian inference. This framework was applied to segmentation of lung tumors in PET/CT datasets taking into consideration simultaneously the CT and the PET image information. PET and CT images were considered using either the original voxels intensities, or after wavelet/contourlet enhancement. The Dice similarity coefficient (DSC), sensitivity (SE), positive predictive value (PPV) were used to assess the performance of the proposed approach on one simulated and 15 clinical PET/CT datasets of non-small cell lung cancer (NSCLC) cases. The surrogate of truth was a statistical consensus (obtained with the Simultaneous Truth and Performance Level Estimation algorithm) of three manual delineations performed by experts on fused PET/CT images. The proposed framework was applied to PET-only, CT-only and PET/CT datasets, and were compared to standard and improved fuzzy c-means (FCM) multimodal implementations.ResultsA high agreement with the consensus of manual delineations was observed when using both PET and CT images. Contourlet-based HMT led to the best results with a DSC of 0.92 0.11 compared to 0.89 +/- 0.13 and 0.90 +/- 0.12 for Intensity-based HMT and Wavelet-based HMT, respectively. Considering PET or CT only in the HMT led to much lower accuracy. Standard and improved FCM led to comparatively lower accuracy than HMT, even when considering multimodal implementations.ConclusionsWe evaluated the accuracy of the proposed HMT-based framework for PET/CT image segmentation. The proposed method reached good accuracy, especially with pre-processing in the contourlet domain.
Databáze: OpenAIRE