A new brain dedicated PET scanner with 4D detector information

González-Montoro, Andrea; Barberá, Julio; Sánchez, David; Mondejar, Alvaro; Freire, Marta; Diaz, Karel; Lucero, Alejandro; Jiménez-Serrano, Santiago; Alamo, J.; Morera-Ballester, Constantino; Barrio, John; Cucarella, Neus; Ilisie, Víctor; Moliner, L.; Valladares, Celia; González, Antonio J.; Prior, John O.; Benlloch, J.

doi:10.2478/bioal-2022-0083

Cited by 18 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MRI is better than CT at detecting vasculature and blood flow irregularities and producing high-resolution brain pictures [59]. MEG can watch electrical discharge in the brain and measure the magnetic field made there [61]. Due to its high cost and complexity, PET, also known as PET-CT, is a high-end imaging technology formerly employed in research [56].…”

Section: B Neuroimaging Modalitiesmentioning

confidence: 99%

BrainWave Diagnostics: An Extensive Examination of Determinants of Multiple Neurological Disease from EEG Signals

jain

2023

Preprint

View full text Add to dashboard Cite

BrainWave Diagnostics, an emerging field, leverages electroencephalography (EEG) data for cost-effective and resource-efficient neurological disorder detection. Although EEGs are commonly used for neurological disease detection, their low signal intensity and nonlinear features pose analytical challenges. This review explores the use of high-performance computational tools, machine learning, and deep learning methods in diagnosing a range of neurological disorders, including epilepsy, Parkinson's disease, autism, ADHD, stroke, tumors, schizophrenia, Alzheimer's, depression, and alcohol use disorder. The increasing prevalence of neurological disorders and their resource burden underscores the urgency of these diagnostic advancements. Future research can consider multi-modal approaches, providing practical solutions for neurological disorder detection beyond EEGs, with potential applications in diverse signal analysis domains.

show abstract

Section: B Neuroimaging Modalitiesmentioning

confidence: 99%

BrainWave Diagnostics: An Extensive Examination of Determinants of Multiple Neurological Disease from EEG Signals

jain

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Contrary to this, (semi-)monolithic detector concepts spread the light over multiple channels. Recently, they have gained attention [20], [21] as they provide high SR [22], [23], [24] but also offer intrinsic depth of interaction (DOI) capabilities [25], [26], thus reducing parallax errors at reduced costs compared to segmented topologies. While, for example, the γ-positioning strongly profits from the spread detection information, it creates disadvantages for the timing performance due to an enhancement of timewalk effects [27], [28], [29] and jitter in signal-propagation times [30], [31], which deteriorate CTR.…”

Section: Introductionmentioning

confidence: 99%

Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning—A Residual Physics Approach

Naunheim,

Kuhl,

Schug

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Artificial intelligence (AI) is entering medical imaging, mainly enhancing image reconstruction. Nevertheless, improvements throughout the entire processing, from signal detection to computation, potentially offer significant benefits. This work presents a novel and versatile approach to detector optimization using machine learning (ML) and residual physics. We apply the concept to positron emission tomography (PET), intending to improve the coincidence time resolution (CTR). PET visualizes metabolic processes in the body by detecting photons with scintillation detectors. Improved CTR performance offers the advantage of reducing radioactive dose exposure for patients. Modern PET detectors with sophisticated concepts and read-out topologies represent complex physical and electronic systems requiring dedicated calibration techniques. Traditional methods primarily depend on analytical formulations successfully describing the main detector characteristics. However, when accounting for higher-order effects, additional complexities arise matching theoretical models to experimental reality. Our work addresses this challenge by combining traditional calibration with AI and residual physics, presenting a highly promising approach. We present a residual physics-based strategy using gradient tree boosting and physics-guided data generation. The explainable AI framework SHapley Additive exPlanations (SHAPs) was used to identify known physical effects with learned patterns. In addition, the models were tested against basic physical laws. We were able Manuscript

show abstract

“…Contrary to this, (semi-)monolithic detector concepts spread the light over multiple channels. Recently, they have gained attention [15,16] as they provide high spatial resolution [17][18][19] but also offer intrinsic depth of interaction (DOI) capabilities [20,21] at reduced costs compared to segmented topologies, reducing parallax errors. While, e.g., the γ-positioning strongly profits from the spread detection information, it creates disadvantages for the timing performance due to an enhancement of timewalk effects [22][23][24] and jitter in signal-propagation times [25,26], which deteriorate CTR.…”

Section: Introductionmentioning

confidence: 99%

Improving the Timing Resolution of Positron Emission Tomography Detectors using Boosted Learning -- A Residual Physics Approach

Naunheim¹,

Kuhl²,

Schug³

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial intelligence is finding its way into medical imaging, usually focusing on image reconstruction or enhancing analytical reconstructed images. However, optimizations along the complete processing chain, from detecting signals to computing data, enable significant improvements. Adaptions of the data acquisition and signal processing are potentially easier to translate into clinical applications, as no patient data are involved in the training. At the same time, the robustness of the involved algorithms and their influence on the final image might be easier to demonstrate. Thus, we present an approach toward detector optimization using boosted learning by exploiting the concept of residual physics. In our work, we improve the coincidence time resolution (CTR) of positron emission tomography (PET) detectors. PET enables imaging of metabolic processes by detecting γ-photons with scintillation detectors. Current research exploits light-sharing detectors, where the scintillation light is distributed over and digitized by an array of readout channels. While these detectors demonstrate excellent performance parameters, e.g., regarding spatial resolution, extracting precise timing information for time-of-flight (TOF) becomes more challenging due to deteriorating effects called time skews. Conventional correction methods mainly rely on analytical formulations, theoretically capable of covering all time skew effects, e.g., caused by signal runtimes or physical effects. However, additional effects are involved for lightsharing detectors, so finding suitable analytical formulations can become arbitrarily complicated. The residual physicsbased strategy uses gradient tree boosting (GTB) and a

show abstract

A new brain dedicated PET scanner with 4D detector information

Cited by 18 publications

References 41 publications

BrainWave Diagnostics: An Extensive Examination of Determinants of Multiple Neurological Disease from EEG Signals

BrainWave Diagnostics: An Extensive Examination of Determinants of Multiple Neurological Disease from EEG Signals

Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning—A Residual Physics Approach

Improving the Timing Resolution of Positron Emission Tomography Detectors using Boosted Learning -- A Residual Physics Approach

Contact Info

Product

Resources

About