Ensemble of neural networks for 3D position estimation in monolithic PET detectors

[EN] We propose an ensemble of multilayer feedforward neural networks to estimate the 3D position of photoelectric interactions in monolithic detectors. The ensemble is trained with data generated from optical Monte Carlo simulations only. The originality of our approach is to exploit simulations to...

Descripción completa

Detalles Bibliográficos
Autores: Iborra Carreres, Amadeo, González, A., Bousse, A., Visvikis, Dimitris, González Martínez, Antonio Javier
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/144674
Acceso en línea:https://riunet.upv.es/handle/10251/144674
Access Level:acceso abierto
Palabra clave:Positron-emission tomography
Monolithic PET detectors
Ensemble of neural networks
Monte Carlo generated training
Interaction position determination
Depth of interaction determination
Descripción
Sumario:[EN] We propose an ensemble of multilayer feedforward neural networks to estimate the 3D position of photoelectric interactions in monolithic detectors. The ensemble is trained with data generated from optical Monte Carlo simulations only. The originality of our approach is to exploit simulations to obtain reference data, in combination with a variability reduction that the network ensembles offer, thus, removing the need of extensive per-detector calibration measurements. This procedure delivers an ensemble valid for any detector of the same design. We show the capability of the ensemble to solve the 3D positioning problem through testing four different detector designs with Monte Carlo data, measurements from physical detectors and reconstructed images from the MindView scanner. Network ensembles allow the detector to achieve a 2-2.4 mm FWHM, depending on its design, and the associated reconstructed images present improved SNR, CNR and SSIM when compared to those based on the MindView built-in positioning algorithm.