Search

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

Statistical SPECT reconstruction can be very time-consuming especially when compensations for collimator and detector response, attenuation, and scatter are included in the reconstruction. This work proposes an accelerated SPECT reconstruction algorithm based on graphics processing unit (GPU) processing. Ordered subset expectation maximization (OSEM) algorithm with CT-based attenuation modelling, depth-dependent Gaussian convolution-based collimator-detector response modelling, and Monte Carlo-based scatter compensation was implemented using OpenCL. The OpenCL implementation was compared against the existing multi-threaded OSEM implementation running on a central processing unit (CPU) in terms of scatter-to-primary ratios, standardized uptake values (SUVs), and processing speed using mathematical phantoms and clinical multi-bed bone SPECT/CT studies. The difference in scatter-to-primary ratios, visual appearance, and SUVs between GPU and CPU implementations was minor. On the other hand, at its best, the GPU implementation was noticed to be 24 times faster than the multi-threaded CPU version on a normal 128 x 128 matrix size 3 bed bone SPECT/CT data set when compensations for collimator and detector response, attenuation, and scatter were included. GPU SPECT reconstructions show great promise as an every day clinical reconstruction tool.

The trade-off between resolution and count sensitivity dominates the performance of standard gamma cameras and dictates the need for relatively high doses of radioactivity of the used radiopharmaceuticals in order to limit image acquisition duration. The introduction of cadmium-zinc-telluride (CZT)-based cameras may overcome some of the limitations against conventional gamma cameras. CZT cameras used for the evaluation of myocardial perfusion have been shown to have a higher count sensitivity compared to conventional single photon emission computed tomography (SPECT) techniques. CZT image quality is further improved by the development of a dedicated three-dimensional iterative reconstruction algorithm, based on maximum likelihood expectation maximization (MLEM), which corrects for the loss in spatial resolution due to line response function of the collimator. All these innovations significantly reduce imaging time and result in a lower patient's radiation exposure compared with standard SPECT. To guide current and possible future users of the CZT technique for myocardial perfusion imaging, the Cardiovascular Committee of the European Association of Nuclear Medicine, starting from the experience of its members, has decided to examine the current literature regarding procedures and clinical data on CZT cameras. The committee hereby aims 1) to identify the main acquisitions protocols; 2) to evaluate the diagnostic and prognostic value of CZT derived myocardial perfusion, and finally 3) to determine the impact of CZT on radiation exposure.

The trade-off between resolution and count sensitivity dominates the performance of standard gamma cameras and dictates the need for relatively high doses of radioactivity of the used radiopharmaceuticals in order to limit image acquisition duration. The introduction of cadmium-zinc-telluride (CZT)-based cameras may overcome some of the limitations against conventional gamma cameras. CZT cameras used for the evaluation of myocardial perfusion have been shown to have a higher count sensitivity compared to conventional single photon emission computed tomography (SPECT) techniques. CZT image quality is further improved by the development of a dedicated three-dimensional iterative reconstruction algorithm, based on maximum likelihood expectation maximization (MLEM), which corrects for the loss in spatial resolution due to line response function of the collimator. All these innovations significantly reduce imaging time and result in a lower patient's radiation exposure compared with standard SPECT. To guide current and possible future users of the CZT technique for myocardial perfusion imaging, the Cardiovascular Committee of the European Association of Nuclear Medicine, starting from the experience of its members, has decided to examine the current literature regarding procedures and clinical data on CZT cameras. The committee hereby aims 1) to identify the main acquisitions protocols; 2) to evaluate the diagnostic and prognostic value of CZT derived myocardial perfusion, and finally 3) to determine the impact of CZT on radiation exposure.

Purpose Traditionally, interpretation of myocardial perfusion imaging (MPI) is based on visual assessment. Computer-based automated analysis might be a simple alternative obviating the need for extensive reading experience. Therefore, the aim of the present study was to compare the diagnostic performance of automated analysis with that of expert visual reading for the detection of obstructive coronary artery disease (CAD). Methods 206 Patients (64% men, age 58.2 ± 8.7 years) with suspected CAD were included prospectively. All patients underwent 99mTc-tetrofosmin single-photon emission computed tomography (SPECT) and invasive coronary angiography with fractional flow reserve (FFR) measurements. Non-corrected (NC) and attenuation-corrected (AC) SPECT images were analyzed both visually as well as automatically by commercially available SPECT software. Automated analysis comprised a segmental summed stress score (SSS), summed difference score (SDS), stress total perfusion deficit (S-TPD), and ischemic total perfusion deficit (I-TPD), representing the extent and severity of hypoperfused myocardium. Subsequently, software was optimized with an institutional normal database and thresholds. Diagnostic performances of automated and visual analysis were compared taking FFR as a reference. Results Sensitivity did not differ significantly between visual reading and most automated scoring parameters, except for SDS, which was significantly higher than visual assessment (p

Cardiac parameters obtained from single-photon emission computed tomographic (SPECT) images can be affected by respiratory motion, image filtering, and animal positioning. We investigated the influence of these factors on ultra-high-resolution murine myocardial perfusion SPECT. Five mice were injected with 99m technetium (Tc-99m)-tetrofosmin, and each was scanned in supine and prone positions in a U-SPECT-II scanner with respiratory and electrocardiographic (ECG) gating. ECG-gated SPECT images were created without applying respiratory motion correction or with two different respiratory motion correction strategies. The images were filtered with a range of three-dimensional gaussian kernels, after which end-diastolic volumes (EDVs), end-systolic volumes (ESVs), and left ventricular ejection fractions were calculated. No significant differences in the measured cardiac parameters were detected when any strategy to reduce or correct for respiratory motion was applied, whereas big differences (> 5%) in EDV and ESV were found with regard to different positioning of animals. A linear relationship (p

Objective The aim of this study was to evaluate the value of attenuation correction (AC) of Tc-99m tetrofosmin single-photon emission tomography (SPECT) imaging for the assessment of left ventricular ejection fraction (LVEF).Methods Attenuation corrected and non-attenuation corrected (NC) resting Tc-99m tetrofosmin SPECT were compared for the assessment of LVEF. Planar multi-gated radionuclide angiography (MUGA) served as the reference for LVEF assessment. Patients (n = 56) with left ventricular dysfunction who underwent MUGA and rest gated Tc-99m tetrofosmin SPECT within I month were included.Results The average LVEF on NC gated SPECT was 37.4 +/- 11.8% and on AC SPECT 38.5 +/- 13.4% (P = NS). The absolute mean difference of the LVEF between the MUGA and NC gated SPECT and AC gated SPECT was -0.2% (95% CI -1.7 to 1.3) and -1.3% (95% Cl -2.7 to 0.03), respectively (P = NS both vs. MUGA). The correlation between NC gated SPECT and AC gated SPECT versus MUGA measurement was high with a correlation coefficient of 0.89 (P Conclusions Profile AC gated Tc-99m tetrofosmin SPECT agrees well with MUGA and NC gated Tc-99m tetrofosmin SPECT for the assessment of LVEF. EDVs and ESVs are significantly higher with AC gated SPECT when compared with NC gated SPECT.

Background: Cost-effectiveness is an increasingly important factor in the choice of a test or therapy. Objective: To assess the cost-effectiveness of various methods routinely used for the diagnosis of stable coronary disease in Portugal. Methods: Seven diagnostic strategies were assessed. The cost-effectiveness of each strategy was defined as the cost per correct diagnosis (inclusion or exclusion of obstructive coronary artery disease) in a symptomatic patient. The cost and effectiveness of each method were assessed using Bayesian inference and decision-making tree analyses, with the pretest likelihood of disease ranging from 10\% to 90\%. Results: The cost-effectiveness of diagnostic strategies was strongly dependent on the pretest likelihood of disease. In patients with a pretest likelihood of disease of 0. In patients with a pretest likelihood of disease of >= 60\%, up-front invasive coronary angiography appears to be the most cost-effective strategy. Conclusions: Diagnostic algorithms that include cardiac computed tomography angiography are the most cost-effective in symptomatic patients with suspected stable coronary artery disease and a pretest likelihood of disease of = 60\%), up-front invasive coronary angiography appears to be the most cost-effective strategy. In all pretest likelihoods of disease, strategies based on ischemia appear to be more expensive and less effective compared with those based on anatomical tests. publishersversion published

We introduce a preconditioner for the solution of the Bidomain system governing the propagation of action potentials in the myocardial tissue. The Bidomain model is a degenerate parabolic set of nonlinear reaction-diffusion equations. The nonlinear term describes the ion flux at the cellular level. The degenerate nature of the problem results in a severe ill conditioning of its discretization. Our preconditioning strategy is based on a suitable adaptation of the Monodomain model, a simplified version of the Bidomain one, which is by far simpler to solve, nevertheless is unable to capture significant features of the action potential propagation. The Monodomain preconditioner application to a non-symmetric formulation of the Bidomain system results at the algebraic level in a lower block-triangular preconditioner. We prove optimality of the preconditioner with respect to the mesh size, and corroborate our theoretical results with 3D numerical simulations both on idealized and real ventricle geometries. (C) 2009 Elsevier Inc. All rights reserved.

We introduce an a posteriori modeling error estimator for the effective computation of electric potential propagation in the heart. Starting from the Bidomain problem and an extended formulation of the simplified Monodomain system, we build a hybrid model, called Hybridomain, which is dynamically adapted to be either Bi- or Monodomain ones in different regions of the computational domain according to the error estimator. We show that accurate results can be obtained with the adaptive Hybridomain model with a reduced computational cost compared to the full Bidornain model. We discuss the effectivity of the estimator and the reliability of the results on simulations performed on real human left ventricle geometries retrieved from healthy subjects. (C) 2010 Elsevier B.V. All rights reserved.