Machine learning and registration for automatic seed localization in 3D US images for prostate brachytherapy - Archive ouverte HAL
Arrêt de service programmé du vendredi 10 juin 16h jusqu’au lundi 13 juin 9h. Pour en savoir plus
Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Machine learning and registration for automatic seed localization in 3D US images for prostate brachytherapy

Hatem Younes 1 Jocelyne Troccaz 1 Sandrine Voros 1
1 TIMC-GMCAO - Gestes Medico-chirurgicaux Assistés par Ordinateur
TIMC - Translational Innovation in Medicine and Complexity / Recherche Translationnelle et Innovation en Médecine et Complexité - UMR 5525
Abstract : New radiation therapy protocols, in particular adaptive, focal or boost brachytherapy treatments, require determining precisely the position and orientation of the implanted radioactive seeds from real-time ultrasound (US) images. This is necessary to compare them to the planned one and to adjust automatically the dosimetric plan accordingly for next seeds implantations. The image modality, the small size of the seeds and the artifacts they produce make it a very challenging problem. The objective of the presented work is to setup and to evaluate a robust and automatic method for seed localization in 3D US images. Methods: The presented method is based on a pre-localization of the needles through which the seeds are injected in the prostate. This pre-localization allows focusing the search on a region of interest (ROI) around the needle tip. Seeds localization starts by binarizing the ROI and removing false positives using respectively a Bayesian classifier and a Support Vector Machine (SVM). This is followed by a registration stage using first an Iterative Closest Point (ICP) for localizing the connected set of seeds (named strand) inserted through a needle, and secondly refining each seed position using Sum of Squared Differences (SSD) as a similarity criterion. ICP registers a geometric model of the strand to the candidate voxels whilst SSD compares an appearance model of a single seed to a subset of the image. The method was evaluated both for 3D images of an Agar-agar phantom and a dataset of clinical 3D images. It was tested on stranded and on loose seeds. Results: Results on phantom and clinical images were compared with a manual localization giving mean errors of 1.09 ± 0.61 mm on phantom image and 1.44 ± 0.45 mm on clinical images. On clinical images, the mean errors of individual seeds orientation was 4.33 ± 8.51 •. Conclusions: The proposed algorithm for radioactive seed localization is robust, tested on different US images, accurate, giving small mean error values, and returns the 5 cylindrical seeds degrees of freedom.
Liste complète des métadonnées
Contributeur : Jocelyne Troccaz Connectez-vous pour contacter le contributeur
Soumis le : mercredi 25 novembre 2020 - 13:18:16
Dernière modification le : vendredi 1 avril 2022 - 03:44:00
Archivage à long terme le : : vendredi 26 février 2021 - 19:05:21


final submission.pdf
Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-03023560, version 1



Hatem Younes, Jocelyne Troccaz, Sandrine Voros. Machine learning and registration for automatic seed localization in 3D US images for prostate brachytherapy. Medical Physics, American Association of Physicists in Medicine, 2021, 48 (3), pp.1144-1156. ⟨hal-03023560⟩



Consultations de la notice


Téléchargements de fichiers