Precise positioning of gamma ray interactions in multiplexed pixelated scintillators using artificial neural networks.

Introduction. The positioning ofγray interactions in positron emission tomography (PET) detectors is commonly made through the evaluation of the Anger logic flood histograms. machine learning techniques, leveraging features extracted from signal waveform, have demonstrated successful applications in addressing various challenges in PET instrumentation.Aim. This paper evaluates the use of artificial neural networks (NN) forγray interaction positioning in pixelated scintillators coupled to a multiplexed array of silicon photomultipliers (SiPM).Methods. An array of 16 Cerium doped Lutetium-based (LYSO) crystal pixels (cross-section 2 × 2 mm2) coupled to 16 SiPM (S13360-1350) were used for the experimental setup. Data from each of the 16 LYSO pixels was recorded, a total of 160000 events. The detectors were irradiated by 511 keV annihilationγrays from a Sodium-22 (22Na) source. Another LYSO crystal was used for electronic collimation. Features extracted from the signal waveform were used to train the model. Two models were tested: i) single multiple-class neural network (mcNN), with 16 possible outputs followed by a softmax and ii) 16 binary classification neural networks (bNN), each one specialized in identifying events occurred in each position.Results. Both NN models showed a mean positioning accuracy above 85% on the evaluation dataset, although the mcNN is faster to train.DiscussionThe method's accuracy is affected by the introduction of misclassified events that interacted in the neighbour's crystals and were misclassified during the dataset acquisition. Electronic collimation reduces this effect, however results could be improved using a more complex acquisition setup, such as a light-sharing configuration.ConclusionsThe methods comparison showed that mcNN and bNN can surpass the Anger logic, showing the feasibility of using these models in positioning procedures of future multiplexed detector systems in a linear configuration.

New Enclosure for in vivo Medical Imaging of Zebrafish With Vital Signs Monitoring.

Lately, the use of zebrafish has gained increased interest in the scientific community as an animal model in preclinical research. However, there is a lack of in vivo imaging tools that ensure animal welfare during acquisition procedures. The use of functional imaging techniques, like Positron Emission Tomography (PET), in zebrafish is limited since it requires the animal to be alive, representing a higher instrumentation complexity when compared to morphological imaging systems. In the present work, a new zebrafish enclosure was developed to acquire in vivo images while monitoring the animal's welfare through its heartbeat. The temperature, dissolved oxygen, and pH range in a closed aquatic environment were tested to ensure that the conditions stay suitable for animal welfare during image acquisitions. The developed system, based on an enclosure with a bed and heartbeat sensors, was tested under controlled conditions in anesthetized fishes. Since the anesthetized zebrafish do not affect the water quality over time, there is no need to incorporate water circulation for the expected time of PET exams (about 30 min). The range of values obtained for the zebrafish heart rate was 88-127 bpm. The developed system has shown promising results regarding the zebrafish's heart rate while keeping the fish still during the long imaging exams. The zebrafish enclosure ensures the animal's well-being during the acquisition of in vivo images in different modalities (PET, Computer Tomography, Magnetic Resonance Imaging), contributing substantially to the preclinical research.