Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review.

PURPOSE: This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years. METHODS: The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information. RESULTS: The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works. CONCLUSION: GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.

Patient dose in brain perfusion imaging using an 80-slice CT system.

BACKGROUND AND PURPOSE: Brain CT Perfusion (CTP) is an X-ray imaging technique for the assessment of brain tissue perfusion, which can be used in several different entities. The aim of this study is the evaluation of the radiation dose to patients during a comprehensive brain CT prescription protocol (CPP) consisting of an unenhanced brain CT, a brain CT angiography and a CTP scan. MATERIALS AND METHODS: Eighteen patients were studied using an 80-slice CT system, with an iterative reconstruction algorithm. The volume Computed Tomography Dose Index (CTDIvol) and dose length product (DLP) were recorded from the dose report of the system. The calculation of effective dose (ED) was accomplished using the DLP values. RESULTS: For the CTP examinations, the CTDIvol ranged from 116.0 to 134.8mGy, with the mean value 119.5mGy. The DLP ranged from 463.9 to 539.2mGy·cm, with the mean value 478mGy·cm. For the CPP, the total ED ranged from 3.31 to 5.07mSv, with the mean value 4.37mSv. CONCLUSIONS: These values are lower than the values reported in corresponding studies, including studies utilizing CT systems with more slices.

A novel method for the optimization of positron emission tomography scanners imaging performance.

OBJECTIVE: The aim of the present study was to propose a comprehensive method for positron emission tomography (PET) scanners image quality assessment, by simulation of a thin layer chromatography (TLC) flood source with a previously validated Monte Carlo model. METHODS AND MATERIALS: We used the GATE Monte Carlo package (GEANT4 application for tomographic emission) and the reconstructed images were obtained using the software for tomographic image reconstruction (STIR), with cluster computing. The PET scanner used in this simulation study was the General Electric Discovery-ST (USA). The plane source that was used for the image quality assessment was a TLC plate, consisting of an aluminum (Al) foil, coated with a thin layer of silica and immersed in fluorodeoxyglucose (18F-FDG) bath solution (1 MBq). The influence of different scintillating crystals on PET scanner's image quality, in terms of the modulation transfer function (MTF), the normalized noise power spectrum (NNPS) and the detective quantum efficiency (DQE), were also investigated. Modulation transfer function was estimated from transverse slices of the plane source, whereas the NNPS from the corresponding coronal slices. Images were reconstructed by the commonly used 2D filtered back projection (FBP2D), the Kinahan and Rogers FPB3DRP and the maximum likelihood estimation (MLE)-OSMAPOSL algorithms. Images obtained using the OSMAPOSL algorithm were assessed by using 15 subsets and 3 iterations. RESULTS: The PET scanner configuration, equipped with LuAP crystals, exhibited the optimum MTF values in both 2D and 3D FBP image reconstruction, whereas the corresponding configuration with BGO crystals exhibited the optimum MTF values after the iterative algorithm. The scanner equipped with the BGO crystals was also found to exhibit overall the lowest noise levels and the highest DQE values after algorithms. These finding indicate that the GE Discovery ST PET scanner exhibits the optimum image quality parameters, in terms of MTF, NNPS and DQE, with BGO scintillating crystals. CONCLUSION: Our new method showed that the imaging performance of PET scanners can be fully characterized and further improved by investigation of the imaging chain components through Monte Carlo methods. To this aim, a TLC based plane source was used during the simulation, in order to assess the impact of the scintillating crystal material on PET image quality, with the application of a previously validated Monte Carlo model. The aforementioned plane source can be also useful for the further development of PET and SPET scanners through GATE simulations, for clinical applications.

Quantitative visually lossless compression ratio determination of JPEG2000 in digitized mammograms.

The current study presents a quantitative approach towards visually lossless compression ratio (CR) threshold determination of JPEG2000 in digitized mammograms. This is achieved by identifying quantitative image quality metrics that reflect radiologists' visual perception in distinguishing between original and wavelet-compressed mammographic regions of interest containing microcalcification clusters (MCs) and normal parenchyma, originating from 68 images from the Digital Database for Screening Mammography. Specifically, image quality of wavelet-compressed mammograms (CRs, 10:1, 25:1, 40:1, 70:1, 100:1) is evaluated quantitatively by means of eight image quality metrics of different computational principles and qualitatively by three radiologists employing a five-point rating scale. The accuracy of the objective metrics is investigated in terms of (1) their correlation (r) with qualitative assessment and (2) ROC analysis (A z index), employing pooled radiologists' rating scores as ground truth. The quantitative metrics mean square error, mean absolute error, peak signal-to-noise ratio, and structural similarity demonstrated strong correlation with pooled radiologists' ratings (r, 0.825, 0.823, -0.825, and -0.826, respectively) and the highest area under ROC curve (A z , 0.922, 0.920, 0.922, and 0.922, respectively). For each quantitative metric, the highest accuracy values of corresponding ROC curves were used to define metric cut-off values. The metrics cut-off values were subsequently used to suggest a visually lossless CR threshold, estimated to be between 25:1 and 40:1 for the dataset analyzed. Results indicate the potential of the quantitative metrics approach in predicting visually lossless CRs in case of MCs in mammography.

Towards the optimization of nuclear medicine procedures for better spatial resolution, sensitivity, scan image quality and quantitation measurements by using a new Monte Carlo model featuring PET imaging.

The aim of this study was to develop a Monte-Carlo model that can be used for the optimization of positron emission tomography (PET) procedures and image quality metrics. This model was developed using the Monte Carlo package of Geant4 application for tomographic emission (GATE) and the software for tomographic image reconstruction (STIR) with cluster computing to obtain reconstructed images. The PET scanner used in this study was the General Electric Discovery-ST (US). The GATE model was validated by comparing results obtained in accordance with the National Electrical Manufacturers Association NEMA-NU-2-2001 protocol [Mawlawi et al (2004) and Bettinardi et al (2004)]. All images were reconstructed with the commonly used 2D filtered back projection and the 3D reprojection algorithms. We found that the simulated spatial resolution in terms of full width at half maximum (FWHM) agreed within less than 3.29% in 2D and less than 2.51% in 3D with published data of others, respectively. The 2D values for the sensitivity, scatter fraction and count-rate were found to agree within less than 0.46%, 4.59% and 7.86%, respectively with these published values. Accordingly, our study showed that the corresponding 3D values were found to agree to less than 1.62%, 2.85% and 9.13%, respectively with Mawlawi et al (2004) published values. Sensitivity, which was also estimated without the presence of attenuation material by simulating an ideal source, showed differences between the extrapolated and the ideal source values (with and without attenuation) ranging in 2D from 0.04% to 0.82% (radial location R=0cm) and 0.52% to 0.67% in 3D mode (radial locations R=10cm). The simulated noise equivalent count rate was found to be 94.31kcps in 2D and 66.9kcps in 3D at 70 and 15kBq/mL respectively, compared to 94.08kcps in 2D and 70.88kcps in 3D at 54.6kBq/mL and 14kBq/mL respectively, from the published by others values. The simulated image quality was found in excellent agreement with these published values. In conclusion, our study showed that our Monte Carlo model can be used to assess, optimize, simplify and reduce the simulation time for the quality control procedure of PET scanners. By using this model, sensitivity can be obtained in a more simplified procedure. Reconstructed images by STIR can be also used to obtain radiopharmaceutical distribution of images and direct dose maps, quite useful to nuclear medicine practitioners.

Patient Dose Estimation in Computed Tomography-Guided Biopsy Procedures.

This study establishes typical Diagnostic Reference Levels (DRL) values and assesses patient doses in computed tomography (CT)-guided biopsy procedures. The Effective Dose (ED), Entrance Skin Dose (ESD), and Size-Specific Dose Estimate (SSDE) were calculated using the relevant literature-derived conversion factors. A retrospective analysis of 226 CT-guided biopsies across five categories (Iliac bone, liver, lung, mediastinum, and para-aortic lymph nodes) was conducted. Typical DRL values were computed as median distributions, following guidelines from the International Commission on Radiological Protection (ICRP) Publication 135. DRLs for helical mode CT acquisitions were set at 9.7 mGy for Iliac bone, 8.9 mGy for liver, 8.8 mGy for lung, 7.9 mGy for mediastinal mass, and 9 mGy for para-aortic lymph nodes biopsies. In contrast, DRLs for biopsy acquisitions were 7.3 mGy, 7.7 mGy, 5.6 mGy, 5.6 mGy, and 7.4 mGy, respectively. Median SSDE values varied from 7.6 mGy to 10 mGy for biopsy acquisitions and from 11.3 mGy to 12.6 mGy for helical scans. Median ED values ranged from 1.6 mSv to 5.7 mSv for biopsy scans and from 3.9 mSv to 9.3 mSv for helical scans. The study highlights the significance of using DRLs for optimizing CT-guided biopsy procedures, revealing notable variations in radiation exposure between helical scans covering entire anatomical regions and localized biopsy acquisitions.

Current Clinical Knowledge on GORE EXCLUDER Conformable Abdominal Aortic Aneurysm Repair Endoprosthesis: A Case Series and Literature Review.

The GORE EXCLUDER Conformable abdominal aortic aneurysm (AAA) Endoprosthesis (CEXC), is currently the newest stent-graft system for treating patients with AAA. CEXC is approved for patients with proximal aortic neck angles ≤90° with a ≥15 mm aortic neck length or proximal aortic neck angles ≤60° with ≥10 mm aortic neck length. The present study describes a clinical series of 5 males with AAA, one of whom had a ruptured infrarenal AAA and a 90° proximal aortic neck angle. All patients were treated with 100% technical success using the CEXC device. Dosimetric data were recorded regarding the total kerma-area product and total fluoroscopy time. During the 30-day follow-up, no device migration or failure was detected, whereas type Ib and II endoleaks were observed in two patients. The type Ib endoleak required re-intervention with limb extension placement, and the type II endoleak was treated with lumbar artery embolization. This clinical series showed that CEXC has no technical defects or AAA-related mortality. We also reviewed the current knowledge on CEXC's clinical outcomes, showing promising technical and clinical results in some studies, even outside the instructions for use. CEXC expands the vascular surgeons' armamentarium against hostile neck anatomy, as it is the only repositionable endovascular aneurysm repair device available. Multicenter, long-term outcome studies should confirm the promising preliminary results of our case series and the literature review.

BMI-Based organ doses in endovascular aneurysm repair interventions utilising Monte Carlo simulation.

In this study, the effect of body-mass-index (BMI) on organ doses (ODs) during infrarenal endovascular-aneurysm-repair (EVAR) procedures was evaluated. Patient- and intra-operative data from fifty-nine EVAR procedures were inserted into VirtualDose-IR software to calculate ODs. For overweight, obesity class-I and obesity class-II, ODs were up to 147%, 412% and 775% higher than those for normal weight-patients, respectively. A large variation was observed in ODs published in literature mainly due to the differences in the software and the technical parameters used for the calculations.

Non-dynamic and multiphase CT protocols for parathyroid glands imaging: a review of technical parameters, radiation dose and diagnostic accuracy.

INTRODUCTION: Our purpose was to review the scientific literature and collect information regarding clinical and technical parameters of different single- or multiphase CT protocols, their diagnostic performance and patient dose during parathyroid imaging. EVIDENCE ACQUISITION: PubMed and Scopus databases were searched for studies investigating the diagnostic performance of CT in detecting parathyroid lesions and the corresponding patients' dose. The following information was retrieved for each article: CT system, number, combination and time interval between phases, scanning length, sensitivity, specificity, accuracy, positive and negative predictive values, contrast enhancement in Hounsfield Units (HUs), technical and exposure parameters, and dose indices. Fifty studies published during the last sixteen years (2005-2021) were reviewed. EVIDENCE SYNTHESIS: A large discrepancy in the number and combination of phases, as well as clinical and technical parameters of the CT protocols was indicated. The variations in patients' doses are mainly due to scanners' technology, number and combination of phases, the extent of scanning length, technical parameters (tube voltage, tube current modulation, pitch, reconstruction algorithms), and patient-related parameters. Technical parameters are not always adjusted appropriately to the clinical question or patient size. These variations indicate a large potential to optimize dose during parathyroid imaging without compromising diagnostic performance. The potential is to decrease the number of phases or use low tube voltage protocols, tube current modulation, iterative reconstruction, and reduce the scanning length during some phases. CONCLUSIONS: The reporting results could inform researchers about the current status of CT parathyroid imaging and guide their future efforts to optimize both patients' dose and corresponding image quality.

A retrospective survey to establish institutional diagnostic reference levels for CT urography examinations based on clinical indications: preliminary results.

Objective. To establish institutional diagnostic reference levels (IDRLs) based on clinical indications (CIs) for three- and four-phase computed tomography urography (CTU).Methods. Volumetric computed tomography dose index (CTDIvol), dose-length product (DLP), patients' demographics, selected CIs like lithiasis, cancer, and other diseases, and protocols' parameters were retrospectively recorded for 198 CTUs conducted on a Toshiba Aquilion Prime 80 scanner. Patients were categorised based on CIs and number of phases. These groups' 75th percentiles of CTDIvoland DLP were proposed as IDRLs. The mean, median and IDRLs were compared with previously published values.Results. For the three-phase protocol, the CTDIvol(mGy) and DLP (mGy.cm) were 22.7/992 for the whole group, 23.4/992 for lithiasis, 22.8/1037 for cancer, and 21.2/981 for other diseases. The corresponding CTDIvol(mGy) and DLP (mGy.cm) values for the four-phase protocol were 28.6/1172, 30.6/1203, 27.3/1077, and 28.7/1252, respectively. A significant difference was found in CTDIvoland DLP between the two protocols, among the phases of three-phase (except cancer) and four-phase protocols (except DLP for other diseases), and in DLP between the second and third phases (except for cancer group). The results are comparable or lower than most studies published in the last decade.Conclusions. The CT technologist must be aware of the critical dose dependence on the scan length and the applied exposure parameters for each phase, according to the patient's clinical background and the corresponding imaging anatomy, which must have been properly targeted by the competent radiologist. When clinically feasible, restricting the number of phases to three instead of four could remarkably reduce the patient's radiation dose. CI-based IDRLs will serve as a baseline for comparison with CTU practice in other hospitals and could contribute to national DRL establishment. The awareness and knowledge of dose levels during CTU will prompt optimisation strategies in CT facilities.