arXiv subjects

Stephan Naunheim

Publications and source records attributed to Stephan Naunheim.

6 recordsLinked to original sources

arXiv2026

OptiGAN for Crystal Arrays: Physics-Informed Generative Modeling of Optical Photon Transport in PET Detector Arrays

Monte Carlo simulations of optical photon transport are computationally prohibitive for large-scale optical systems including detector arrays and PET systems, restricting their practical use to single-crystal studies. This work presents an enhanced conditional generative adversarial network capable of replacing optical simulations at the crystal array level, extending our previous single-crystal approach to a 3x3 BGO detector array. We introduce Fourier feature encoding and a learnable latent mapping network as the modifications enabling stable training on the array geometry, together with a physics-informed loss term enforcing the unit-sphere state space $S^2$ of the generated propagation directions as a soft constraint. Training data requirements are reduced eight-fold by exploiting the array's symmetry. Performance is benchmarked against GATE10/Geant4 ground truth, using the fluctuations between independent Monte Carlo runs. The enhanced optiGAN achieves similarity values within 3$\sigma$ agreement of the Monte Carlo baseline across all evaluation conditions. An ablation and attribution analysis shows that the physics-informed loss term reduces low-SSIM bin fractions by a factor of 3.6 on the outer crystals, with a localized trade-off at the central crystal, yielding a net 48% reduction over the full array. The model transitions from electron-emission training data to realistic gamma-photon interactions, producing flood maps that reproduce experimental patterns including photopeak clusters and inter-crystal scatter lines. This proof-of-concept demonstrates that a physics-informed generative model can simulate optical photon transport in segmented scintillator arrays at a training and inference cost accessible on a single workstation GPU.

physics.ins-det↗

arXiv2025

Rethinking Timing Residuals: Advancing PET Detectors with Explicit TOF Corrections

PET is a functional imaging method that visualizes metabolic processes. TOF information can be derived from coincident detector signals and incorporated into image reconstruction to enhance the SNR. PET detectors are typically assessed by their CTR, but timing performance is degraded by various factors. Research on timing calibration seeks to mitigate these degradations and restore accurate timing information. While many calibration methods use analytical approaches, machine learning techniques have recently gained attention due to their flexibility. We developed a residual physics-based calibration approach that combines prior domain knowledge with the power of machine learning models. This approach begins with an initial analytical calibration addressing first-order skews. The remaining deviations, regarded as residual effects, are used to train machine learning models to eliminate higher-order skews. The key advantage is that the experimenter guides the learning process through the definition of timing residuals. In earlier studies, we developed models that directly predicted the expected time difference, which offered corrections only implicitly (implicit correction models). In this study, we introduce a new definition for timing residuals, enabling us to train models that directly predict correction values (explicit correction models). The explicit correction approach significantly simplifies data acquisition, improves linearity, and enhances timing performance from $371 \pm 6$ ps to $281 \pm 5$ ps for coincidences from 430 keV to 590 keV. Additionally, the new definition reduces model size, making it suitable for high-throughput applications like PET scanners. Experiments were conducted using two detector stacks composed of $4 \times 4$ LYSO:Ce,Ca crystals ($3.8\times 3.8\times 20$ mm$^{3}$) coupled to $4 \times 4$ Broadcom NUV-MT SiPMs and digitized with the TOFPET2 ASIC.

physics.ins-det↗

arXiv2023

A Finely Segmented Semi-Monolithic Detector tailored for High Resolution PET

Preclinical research and organ-dedicated applications require high-resolution positron emission tomography (PET) detectors to visualize small structures and understand biological processes at a finer level of detail. Current commercial systems often employ finely pixelated or monolithic scintillators, each with its limitations. We present a semi-monolithic detector, tailored for high-resolution PET applications, and merging concepts of monolithic and pixelated crystals. The detector features slabs measuring (24 x 10 x 1) sq. mm, coupled to a 12 x 12 readout channel photosensor with 4 mm pitch. The slabs are grouped in two arrays of 44 slabs each to achieve a higher optical photon density. We employ a fan beam collimator for fast calibration to train machine-learning-based positioning models for all three dimensions, including slab identification and depth-of-interaction (DOI), utilizing gradient tree boosting (GTB). Energy calculation was based on a position-dependent energy calibration. Using an analytical timing calibration, time skews were corrected for coincidence timing resolution (CTR) estimation. Leveraging machine-learning-based calibration in all three dimensions, we achieved high detector spatial resolution: down to 1.18 mm full width at half maximum (FWHM) detector spatial resolution and 0.75 mm mean absolute error (MAE) in the planar-monolithic direction along the slabs, and 2.14 mm FWHM and 1.03 mm MAE for depth-of-interaction (DOI) at an energy window of (435-585) keV. Correct slab interaction identification exceeded 80%, alongside an energy resolution of 13.8% and a CTR of 450 ps FWHM. Therewith, the introduced finely segmented, high-resolution slab detector demonstrates an appealing performance suitable for high-resolution PET applications. The current benchtop-based detector calibration routine allows these detectors to be used in PET systems.

physics.med-ph↗

arXiv2023

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

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 (SHAP) was used to identify known physical effects with learned patterns. In addition, the models were tested against basic physical laws. We were able to improve the CTR significantly (more than 20%) for clinically relevant detectors of 19 mm height, reaching CTRs of 185 ps (450-550 keV).

cs.LG↗

arXiv2022

A Semi-Monolithic Detector providing intrinsic DOI-encoding and sub-200 ps CRT TOF-Capabilities for Clinical PET Applications

Current clinical PET systems utilize detectors where the scintillator typically contains single elements of 3 - 6 mm width and about 20 mm height. While providing good TOF performance, this design limits the spatial resolution and causes radial astigmatism as the DOI remains unknown. We propose an alternative, aiming to combine the advantages of current detectors with the DOI capabilities shown for monolithic concepts, based on semi-monolithic scintillators (slabs). An array of 8 monolithic LYSO slabs of dimensions 3.9 x 32 x 19 mm3 was read out by a 64-channel photosensor containing digital SiPMs. The position estimation in the detector's monolithic and DOI direction was based on a calibration with a fan beam collimator and the machine learning technique gradient tree boosting (GTB). We achieved a positioning performance in terms of mean absolute error (MAE) of 1.44 mm and 2.12 mm for DOI considering a wide energy window of 300 - 700 keV. The energy resolution was determined to be 11.3%. We established both an analytical and machine-learning-based timing calibration approach and applied them for a first-photon trigger. The analytical timing calibration corrects for electronic and optical time skews leading to 240 ps coincidence resolving time (CRT) for a pair of slab-detectors. The CRT was significantly improved by utilizing GTB to predict the time difference based on specific training data and applied on top of the analytical calibration. We achieved 209 ps for the wide energy window and 198 ps for a narrow selection around the photopeak (411 - 561 keV). To maintain the detector's sensitivity, no filters were applied to the data during processing. Overall, the semi-monolithic detector provides attractive performance characteristics. Especially, a good CRT can be achieved while introducing DOI capabilities to the detector, making the concept suitable for clinical PET scanners.

physics.ins-det↗

arXiv2022

Evaluation of semi-monolithic scintillators with integrated RF shielding material for a higher integration of PET/MRI systems

The integration of PET into MRI to form a hybrid system requires often compromises for both subsystems. For example, the integration might come at the cost of a reduced PET detector height or a reduced MRI examination volume diameter. Here, we propose a so-called shared-volume concept to use the volume required for both subsystems more efficiently, in which the MR transparency of the scintillator is exploited by integrating the RF shielding into the scintillator of the PET detector. Semi-monolithic scintillator prototypes (PVC slabs) of 7 mm and 12 mm height with integrated copper foil between every and every other slab, respectively, were investigated to evaluate the shielding effectiveness (SE). The SE was measured with probes on a test bench system. In addition, the PET detector performance was evaluated by determining the positioning using gradient tree boosting, energy and timing resolution using digital SiPM arrays (DPC3200, PDPC) in three LYSO scintillator configurations: ESR separation (Slab$\mathrm{_{ESR}}$), ESR with copper foil in between (Slab$\mathrm{_{ESR+Cu}}$), and purely copper foil separation (Slab$\mathrm{_{Cu}}$). The prototype with shielding between each slab and 12 mm height showed the highest SE with 31 dB (mean) in combination with a supporting frame. While Slab$\mathrm{_{Cu}}$ was best for positioning, followed by Slab$\mathrm{_{ESR}}$ and Slab$\mathrm{_{ESR+Cu}}$, the Slab$\mathrm{_{ESR}}$ had the best energy resolution (10.6 %), followed by Slab$\mathrm{_{ESR+Cu}}$ (11.2 %) and Slab$\mathrm{_{Cu}}$ (12.6 %). For the timing resolution, Slab$\mathrm{_{ESR}}$ and Slab$\mathrm{_{Cu}}$ achieved 279 ps and 288 ps, respectively. Slab$\mathrm{_{ESR+Cu}}$ performed worst (293 ps). The scintillator-based RF shielding shows good RF shielding with similar PET performance, demonstrating the potential for more effective integration of PET detectors into MRI systems.

physics.ins-det↗