Convolutional neural networks for PET functional volume fully automatic segmentation : development and validation in a multi-center setting
Iantsen, A. (LaTIM. INSERM. UMR 1101. University Brest)
Ferreira, M. (GIGA-CRC in vivo Imaging. University of Liège)
Lucia, F. (LaTIM. INSERM. UMR 1101. University Brest)
Jaouen, V. (LaTIM. INSERM. UMR 1101. University Brest)
Reinhold, C. (Department of Radiology. McGill University Health Centre (MUHC))
Bonaffini, P. (Department of Radiology. McGill University Health Centre (MUHC))
Alfieri, J. (Department of Radiation Oncology. McGill University Health Centre (MUHC))
Rovira Negre, Ramon (Institut d'Investigació Biomèdica Sant Pau)
Masson, I. (Department of Radiation Oncology. Institut de Cancérologie de l'Ouest (ICO))
Robin, P. (Nuclear Medicine Department. University Hospital)
Mervoyer, A. (Department of Radiation Oncology. Institut de Cancérologie de l'Ouest (ICO))
Rousseau, C. (Nuclear Medicine Department. Institut de Cancérologie de l'Ouest (ICO))
Kridelka, F. (Division of Oncological Gynecology. University Hospital of Liège)
Decuypere, M. (Division of Oncological Gynecology. University Hospital of Liège)
Lovinfosse, P. (Division of Nuclear Medicine and Oncological Imaging. University Hospital of Liège)
Pradier, O. (LaTIM. INSERM. UMR 1101. University Brest)
Hustinx, R. (GIGA-CRC in vivo Imaging. University of Liège)
Schick, U. (LaTIM. INSERM. UMR 1101. University Brest)
Visvikis, D. (LaTIM. INSERM. UMR 1101. University Brest)
Hatt, M. (LaTIM. INSERM. UMR 1101. University Brest)

Date:	2021
Abstract:	Purpose: In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics. Methods: In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing). Results: The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0. 80 ± 0. 03), with higher recall (0. 90 ± 0. 05) than precision (0. 75 ± 0. 05) and improved results over the standard U-Net (DSC 0. 77 ± 0. 05, recall 0. 87 ± 0. 02, precision 0. 74 ± 0. 08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0. 33 ± 0. 15, recall 0. 52 ± 0. 17, precision 0. 30 ± 0. 16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training. Conclusion: The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context.
Grants:	European Commission. Horizon 2020 766276
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Convolutional neural network ; PET ; Segmentation ; Cervical cancer ; U-Net
Published in:	European Journal of Nuclear Medicine and Molecular Imaging, Vol. 48 Núm. 11 (october 2021) , p. 3444-3456, ISSN 1619-7089

DOI: 10.1007/s00259-021-05244-z
PMID: 33772335

13 p, 1.3 MB

The record appears in these collections:
Research literature > UAB research groups literature > Research Centres and Groups (research output) > Health sciences and biosciences > Institut de Recerca Sant Pau
Articles > Research articles
Articles > Published articles