Image Denoising of Low-Dose PET Mouse Scans with Deep Learning: Validation Study for Preclinical Imaging Applicability.

PURPOSE: Positron emission tomography (PET) image quality can be improved by higher injected activity and/or longer acquisition time, but both may often not be practical in preclinical imaging. Common preclinical radioactive doses (10 MBq) have been shown to cause deterministic changes in biological pathways. Reducing the injected tracer activity and/or shortening the scan time inevitably results in low-count acquisitions which poses a challenge because of the inherent noise introduction. We present an image-based deep learning (DL) framework for denoising lower count micro-PET images. PROCEDURES: For 36 mice, a 15-min [18F]FDG (8.15 ± 1.34 MBq) PET scan was acquired at 40 min post-injection on the Molecubes ß-CUBE (in list mode). The 15-min acquisition (high-count) was parsed into smaller time fractions of 7.50, 3.75, 1.50, and 0.75 min to emulate images reconstructed at 50, 25, 10, and 5% of the full counts, respectively. A 2D U-Net was trained with mean-squared-error loss on 28 high-low count image pairs. RESULTS: The DL algorithms were visually and quantitatively compared to spatial and edge-preserving denoising filters; the DL-based methods effectively removed image noise and recovered image details much better while keeping quantitative (SUV) accuracy. The largest improvement in image quality was seen in the images reconstructed with 10 and 5% of the counts (equivalent to sub-1 MBq or sub-1 min mouse imaging). The DL-based denoising framework was also successfully applied on the NEMA-NU4 phantom and different tracer studies ([18F]PSMA, [18F]FAPI, and [68 Ga]FAPI). CONCLUSION: Visual and quantitative results support the superior performance and robustness in image denoising of the implemented DL models for low statistics micro-PET. This offers much more flexibility in optimizing preclinical, longitudinal imaging protocols with reduced tracer doses or shorter durations.

Walk-through flat panel total-body PET: a patient-centered design for high throughput imaging at lower cost using DOI-capable high-resolution monolithic detectors.

PURPOSE: Long axial field-of-view (LAFOV) systems have a much higher sensitivity than standard axial field-of-view (SAFOV) PET systems for imaging the torso or full body, which allows faster and/or lower dose imaging. Despite its very high sensitivity, current total-body PET (TB-PET) throughput is limited by patient handling (positioning on the bed) and often a shortage of available personnel. This factor, combined with high system costs, makes it hard to justify the implementation of these systems for many academic and nearly all routine nuclear medicine departments. We, therefore, propose a novel, cost-effective, dual flat panel TB-PET system for patients in upright standing positions to avoid the time-consuming positioning on a PET-CT table; the walk-through (WT) TB-PET. We describe a patient-centered, flat panel PET design that offers very efficient patient throughput and uses monolithic detectors (with BGO or LYSO) with depth-of-interaction (DOI) capabilities and high intrinsic spatial resolution. We compare system sensitivity, component costs, and patient throughput of the proposed WT-TB-PET to a SAFOV (= 26 cm) and a LAFOV (= 106 cm) LSO PET systems. METHODS: Patient width, height (= top head to start of thighs) and depth (= distance from the bed to front of patient) were derived from 40 randomly selected PET-CT scans to define the design dimensions of the WT-TB-PET. We compare this new PET system to the commercially available Siemens Biograph Vision 600 (SAFOV) and Siemens Quadra (LAFOV) PET-CT in terms of component costs, system sensitivity, and patient throughput. System cost comparison was based on estimating the cost of the two main components in the PET system (Silicon Photomultipliers (SiPMs) and scintillators). Sensitivity values were determined using Gate Monte Carlo simulations. Patient throughput times (including CT and scout scan, patient positioning on bed and transfer) were recorded for 1 day on a Siemens Vision 600 PET. These timing values were then used to estimate the expected patient throughput (assuming an equal patient radiotracer injected activity to patients and considering differences in system sensitivity and time-of-flight information) for WT-TB-PET, SAFOV and LAFOV PET. RESULTS: The WT-TB-PET is composed of two flat panels; each is 70 cm wide and 106 cm high, with a 50-cm gap between both panels. These design dimensions were justified by the patient sizes measured from the 40 random PET-CT scans. Each panel consists of 14 × 20 monolithic BGO detector blocks that are 50 × 50 × 16 mm in size and are coupled to a readout with 6 × 6 mm SiPMs arrays. For the WT-TB-PET, the detector surface is reduced by a factor of 1.9 and the scintillator volume by a factor of 2.2 compared to LAFOV PET systems, while demonstrating comparable sensitivity and much better uniform spatial resolution (< 2 mm in all directions over the FOV). The estimated component cost for the WT-TB-PET is 3.3 × lower than that of a 106 cm LAFOV system and only 20% higher than the PET component costs of a SAFOV. The estimated maximum number of patients scanned on a standard 8-h working day increases from 28 (for SAFOV) to 53-60 (for LAFOV in limited/full acceptance) to 87 (for the WT-TB-PET). By scanning faster (more patients), the amount of ordered activity per patient can be reduced drastically: the WT-TB-PET requires 66% less ordered activity per patient than a SAFOV. CONCLUSIONS: We propose a monolithic BGO or LYSO-based WT-TB-PET system with DOI measurements that departs from the classical patient positioning on a table and allows patients to stand upright between two flat panels. The WT-TB-PET system provides a solution to achieve a much lower cost TB-PET approaching the cost of a SAFOV system. High patient throughput is increased by fast patient positioning between two vertical flat panel detectors of high sensitivity. High spatial resolution (< 2 mm) uniform over the FOV is obtained by using DOI-capable monolithic scintillators.

Dose reduction and image enhancement in micro-CT using deep learning.

BACKGROUND: In preclinical settings, micro-computed tomography (CT) provides a powerful tool to acquire high resolution anatomical images of rodents and offers the advantage to in vivo non-invasively assess disease progression and therapy efficacy. Much higher resolutions are needed to achieve scale-equivalent discriminatory capabilities in rodents as those in humans. High resolution imaging however comes at the expense of increased scan times and higher doses. Specifically, with preclinical longitudinal imaging, there are concerns that dose accumulation may affect experimental outcomes of animal models. PURPOSE: Dose reduction efforts under the ALARA (as low as reasonably achievable) principles are thus a key point of attention. However, low dose CT acquisitions inherently induce higher noise levels which deteriorate image quality and negatively impact diagnostic performance. Many denoising techniques already exist, and deep learning (DL) has become increasingly popular for image denoising, but research has mostly focused on clinical CT with limited studies conducted on preclinical CT imaging. We investigate the potential of convolutional neural networks (CNN) for restoring high quality micro-CT images from low dose (noisy) images. The novelty of the CNN denoising frameworks presented in this work consists of utilizing image pairs with realistic CT noise present in the input as well as the target image used for the model training; a noisier image acquired with a low dose protocol is matched to a less noisy image acquired with a higher dose scan of the same mouse. METHODS: Low and high dose ex vivo micro-CT scans of 38 mice were acquired. Two CNN models, based on a 2D and 3D four-layer U-Net, were trained with mean absolute error (30 training, 4 validation and 4 test sets). To assess denoising performance, ex vivo mice and phantom data were used. Both CNN approaches were compared to existing methods, like spatial filtering (Gaussian, Median, Wiener) and iterative total variation image reconstruction algorithm. Image quality metrics were derived from the phantom images. A first observer study (n = 23) was set-up to rank overall quality of differently denoised images. A second observer study (n = 18) estimated the dose reduction factor of the investigated 2D CNN method. RESULTS: Visual and quantitative results show that both CNN algorithms exhibit superior performance in terms of noise suppression, structural preservation and contrast enhancement over comparator methods. The quality scoring by 23 medical imaging experts also indicates that the investigated 2D CNN approach is consistently evaluated as the best performing denoising method. Results from the second observer study and quantitative measurements suggest that CNN-based denoising could offer a 2-4× dose reduction, with an estimated dose reduction factor of about 3.2 for the considered 2D network. CONCLUSIONS: Our results demonstrate the potential of DL in micro-CT for higher quality imaging at low dose acquisition settings. In the context of preclinical research, this offers promising future prospects for managing the cumulative severity effects of radiation in longitudinal studies.

Performance evaluation of a micro-CT system for laboratory animal imaging with iterative reconstruction capabilities.

BACKGROUND: In recent years, there has been a rapid proliferation in micro-computed tomography (micro-CT) systems becoming more available for routine preclinical research, with applications in many areas, including bone, lung, cancer, and cardiac imaging. Micro-CT provides the means to non-invasively acquire detailed anatomical information, but high-resolution imaging comes at the cost of longer scan times and higher doses, which is not desirable given the potential risks related to x-ray radiation. To achieve dose reduction and higher throughputs without compromising image quality, fewer projections can be acquired. This is where iterative reconstruction methods can have the potential to reduce noise since these algorithms can better handle sparse projection data, compared to filtered backprojection PURPOSE: We evaluate the performance characteristics of a compact benchtop micro-CT scanner that provides iterative reconstruction capabilities with GPU-based acceleration. We thereby investigate the potential benefit of iterative reconstruction for dose reduction. METHODS: Based on a series of phantom experiments, the benchtop micro-CT system was characterized in terms of image uniformity, noise, low contrast detectability, linearity, and spatial resolution. Whole-body images of a plasticized ex vivo mouse phantom were also acquired. Different acquisition protocols (general-purpose versus high-resolution, including low dose scans) and different reconstruction strategies (analytic versus iterative algorithms: FDK, ISRA, ISRA-TV) were compared. RESULTS: Signal uniformity was maintained across the radial and axial field-of-view (no cupping effect) with an average difference in Hounsfield units (HU) between peripheral and central regions below 50. For low contrast detectability, regions with at least ∆HU of 40 to surrounding material could be discriminated (for rods of 2.5 mm diameter). A high linear correlation (R2  = 0.997) was found between measured CT values and iodine concentrations (0-40 mg/ml). Modulation transfer function (MTF) calculations on a wire phantom evaluated a resolution of 10.2 lp/mm at 10% MTF that was consistent with the 8.3% MTF measured on the 50 µm bars (10 lp/mm) of a bar-pattern phantom. Noteworthy changes in signal-to-noise and contrast-to-noise values were found for different acquisition and reconstruction protocols. Our results further showed the potential of iterative reconstruction to deliver images with less noise and artefacts. CONCLUSIONS: In summary, the micro-CT system that was evaluated in the present work was shown to provide a good combination of performance characteristics between image uniformity, low contrast detectability, and resolution in short scan times. With the iterative reconstruction capabilities of this micro-CT system in mind (ISRA and ISRA-TV), the adoption of such algorithms by GPU-based acceleration enables the integration of noise reduction methods which here demonstrated potential for high-quality imaging at reduced doses.