Convolutional neural network-based reconstruction for positronium annihilation localization

Jegal, Jin; Jeong, Dongwoo; Seo, E. S.; Park, HyeoungWoo; Kim, Hongjoo

doi:10.1038/s41598-022-11972-5

Cited by 6 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve a higher performance, the network will keep training by updating the weights and bias values until high accuracy is attained. [39][40][41][42] In the case of optoelectronic devices, the weights and bias in the layers are stored to use as inbuilt analog memory array. However, this memory array in an optoelectronic device decays with time once the light stimulus is removed as shown in memory decay (red curve) in Figure 1c.…”

Section: Resultsmentioning

confidence: 99%

Adaptive Convolutional Neural Networks for Enhanced Memory Retention and Restoration in Optoelectronic Vision Devices

Aung

Ahmed

Mazumder

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Optoelectronic devices based on optically responsive materials have gained significant attention due to their low cross talk and reduced power consumption. These devices rely on light‐induced changes in conductance states, which are used to create synaptic weights for image recognition tasks in neural networks. However, a major drawback of such devices is the rapid decay of conductance states after light stimulus removal, which hinders their long‐term memory and performance without a continuous external stimulus in place. To address this issue, a platform neural network scheme is proposed to counter the natural decay of conductance in optoelectronic devices. The approach restores the memory effect of the devices and significantly enhances their performance by several orders of magnitude without using additional energy‐intensive techniques like training pulses or gate fields. Herein, the model is validated experimentally using optoelectronic devices fabricated with two different materials, BP and doped In2O3, and demonstrates the restoration of memory/image retention ability to any material system being studied for optoelectronic synapses and vision. This approach has important implications for the practical application of neuromorphic visual processing technologies, bringing them closer to real‐world applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Adaptive Convolutional Neural Networks for Enhanced Memory Retention and Restoration in Optoelectronic Vision Devices

Aung

Ahmed

Mazumder

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Hence, by extrapolating the result obtained in this study, we anticipate that the use of the high-sensitivity scanners mentioned above will enable τ oPs imaging with a temporal resolution better than 10 ps, which can potentially be further improved using iterative methods [11]. It is worth noting that a temporal resolution of 20 ps was already achieved in the first ex vivo positronium imaging [9], and that other methods for improving the precision of lifetime spectra analysis are actively being developed [11, 58–63].…”

Section: Discussionmentioning

confidence: 99%

First positronium image of the human brainin vivo

Moskal,

Baran,

Bass

et al. 2024

Preprint

View full text Add to dashboard Cite

Positronium, an unstable atom consisting of an electron and a positron, is abundantly produced within the molecular voids of a patient's body during positron emission tomography (PET) diagnosis. Its properties, such as its average lifetime between formation and annihilation into photons, dynamically respond to the submolecular architecture of the tissue and the partial pressure of oxygen molecules. However, the diagnostic information that positronium may deliver about early molecular alterations remains unavailable in clinics with state-of-the-art PET scanners. This study presents the first in vivo images of positronium lifetime in humans. We developed a dedicated J-PET system with multiphoton detection capability for imaging. The measurements of positronium lifetime were performed on a patient with a glioblastoma tumor in the brain. The patient was injected intratumorally with the68Ga radionuclide attached to Substance-P, which accumulates in glioma cells, and intravenously with68Ga attached to the PSMA-11 ligand, which is selective to glioma cells and salivary glands. The 68Ga radionuclide is routinely used in PET for detecting radiopharmaceutical accumulation and was applied for positronium imaging because it can emit an additional prompt gamma. The prompt gamma enables the determination of the time of positronium formation, while the photons from positronium annihilation were used to reconstruct the place and time of its decay. The determined positronium mean lifetime in glioblastoma cells is shorter than in salivary glands, which in turn is shorter than in healthy brain tissues, demonstrating for the first time that positronium imaging can be used to diagnose disease in vivo. This study also demonstrates that if current total-body PET systems were equipped with multiphoton detection capability and the44Sc radionuclide was applied, it would be possible to perform positronium imaging at 6500 times greater sensitivity than achieved in this research. Therefore, it is anticipated that positronium imaging has the potential to bring a new quality of cancer diagnosis in clinics.

show abstract

“…The very first positronium image recently demonstrated using a multi-photon J-PET tomograph was reconstructed with the coincidence resolving time resolution (CRT) of about 500 ps, corresponding to a spatial resolution of 75 mm [2,7]. It is worth noting that the time resolution of PET systems is constantly improving, and there is also the ongoing rapid development of new materials with improved timing properties [41,42] and new detectors for preclinical [43] and clinical [2,8,[44][45][46] studies. The best current clinical time-of-flight (TOF)-PET systems [47] are characterized by CRT of 210 ps, equivalent to a position resolution of about 32 mm along the line of response.…”

Section: Positronium As a Biomarker Of Cancer And Hypoxiamentioning

confidence: 99%

Perspectives on translation of positronium imaging into clinics

Moskal

Stępień

2022

Front. Phys.

View full text Add to dashboard Cite

The image of positronium properties created in the patient’s body during PET examination tells about the inter- and intra-molecular structure of the tissue and the concentration of bio-active molecules in the tissue [2–4]. In this article, we advocate the opinion that total-body PET systems, thanks to their high imaging sensitivity and high time resolution, open up the prospect of translating positronium imaging into clinics.

show abstract

Convolutional neural network-based reconstruction for positronium annihilation localization

Cited by 6 publications

References 17 publications

Adaptive Convolutional Neural Networks for Enhanced Memory Retention and Restoration in Optoelectronic Vision Devices

Adaptive Convolutional Neural Networks for Enhanced Memory Retention and Restoration in Optoelectronic Vision Devices

First positronium image of the human brainin vivo

Perspectives on translation of positronium imaging into clinics

Contact Info

Product

Resources

About