Low-dose Data Research Articles

Deep learning-based partial volume correction in standard and low-dose positron emission tomography-computed tomography imaging.

Positron emission tomography (PET) imaging encounters the obstacle of partial volume effects, arising from its limited intrinsic resolution, giving rise to (I) considerable bias, particularly for structures comparable in size to the point spread function (PSF) of the system; and (II) blurred image edges and blending of textures along the borders. We set out to build a deep learning-based framework for predicting partial volume corrected full-dose (FD + PVC) images from either standard or low-dose (LD) PET images without requiring any anatomical data in order to provide a joint solution for partial volume correction and de-noise LD PET images. We trained a modified encoder-decoder U-Net network with standard of care or LD PET images as the input and FD + PVC images by six different PVC methods as the target. These six PVC approaches include geometric transfer matrix (GTM), multi-target correction (MTC), region-based voxel-wise correction (RBV), iterative Yang (IY), reblurred Van-Cittert (RVC), and Richardson-Lucy (RL). The proposed models were evaluated using standard criteria, such as peak signal-to-noise ratio (PSNR), root mean squared error (RMSE), structural similarity index (SSIM), relative bias, and absolute relative bias. Different levels of error were observed for these partial volume correction methods, which were relatively smaller for GTM with a SSIM of 0.63 for LD and 0.29 for FD, IY with an SSIM of 0.63 for LD and 0.67 for FD, RBV with an SSIM of 0.57 for LD and 0.65 for FD, and RVC with an SSIM of 0.89 for LD and 0.94 for FD PVC approaches. However, large quantitative errors were observed for multi-target MTC with an RMSE of 2.71 for LD and 2.45 for FD and RL with an RMSE of 5 for LD and 3.27 for FD PVC approaches. We found that the proposed framework could effectively perform joint de-noising and partial volume correction for PET images with LD and FD input PET data (LD vs. FD). When no magnetic resonance imaging (MRI) images are available, the developed deep learning models could be used for partial volume correction on LD or standard PET-computed tomography (PET-CT) scans as an image quality enhancement technique.

Reducing Contrast Agent Dose in Cardiovascular MR Angiography with Deep Learning.

Contrast-enhanced magnetic resonance angiography (MRA) is used to assess various cardiovascular conditions. However, gadolinium-based contrast agents (GBCAs) carry a risk of dose-related adverse effects. To develop a deep learning method to reduce GBCA dose by 80%. Retrospective and prospective. A total of 1157 retrospective and 40 prospective congenital heart disease patients for training/validation and testing, respectively. A 1.5 T, T1-weighted three-dimensional (3D) gradient echo. A neural network was trained to enhance low-dose (LD) 3D MRA using retrospective synthetic data and tested with prospective LD data. Image quality for LD (LD-MRA), enhanced LD (ELD-MRA), and high-dose (HD-MRA) was assessed in terms of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and a quantitative measure of edge sharpness and scored for perceptual sharpness and contrast on a 1-5 scale. Diagnostic confidence was assessed on a 1-3 scale. LD- and ELD-MRA were assessed against HD-MRA for sensitivity/specificity and agreement of vessel diameter measurements (aorta and pulmonary arteries). SNR, CNR, edge sharpness, and vessel diameters were compared between LD-, ELD-, and HD-MRA using one-way repeated measures analysis of variance with post-hoc t-tests. Perceptual quality and diagnostic confidence were compared using Friedman's test with post-hoc Wilcoxon signed-rank tests. Sensitivity/specificity was compared using McNemar's test. Agreement of vessel diameters was assessed using Bland-Altman analysis. SNR, CNR, edge sharpness, perceptual sharpness, and perceptual contrast were lower (P< 0.05) for LD-MRA compared to ELD-MRA and HD-MRA. SNR, CNR, edge sharpness, and perceptual contrast were comparable between ELD and HD-MRA, but perceptual sharpness was significantly lower. Sensitivity/specificity was 0.824/0.921 for LD-MRA and 0.882/0.960 for ELD-MRA. Diagnostic confidence was 2.72, 2.85, and 2.92 for LD, ELD, and HD-MRA, respectively (PLD-ELD , PLD-HD < 0.05). Vessel diameter measurements were comparable, with biases of 0.238 (LD-MRA) and 0.278 mm (ELD-MRA). Deep learning can improve contrast in LD cardiovascular MRA. 2 TECHNICAL EFFICACY: Stage 2.

Comparison of DCE-MRI of murine model cancers with a low dose and high dose of contrast agent.

There are increasing concerns regarding intracellular accumulation of gadolinium (Gd) after multiple dynamic contrast enhanced (DCE) MRI scans. We investigated whether a low dose (LD) of Gd-based contrast agent is as effective as a high dose (HD) for quantitative analysis of DCE-MRI data, and evaluated the use of a split dose protocol to obtain new diagnostic parameters. Female C3H mice (n=6) were injected with mammary carcinoma cells in the hind leg. MRI experiments were performed on 9.4T scanner. DCE-MRI data were acquired with 1.5s temporal resolution before and after a LD (0.04mmol/kg), then again after 30min followed by a HD (0.2mmol/kg) bolus injection of Omniscan. The standard Tofts model was used to extract physiological parameters (Ktrans and ve) with the arterial input function derived from muscle reference tissue. In addition, an empirical mathematical model was used to characterize maximum contrast agent uptake (A), contrast agent uptake rate (α) and washout rate (β and γ). There were moderate to strong correlations (r=0.69-0.97, p<0001) for parameters Ktrans, ve, A, α and β from LD versus HD data. On average, tumor parameters obtained from LD data were significantly larger (p<0.05) than those from HD data. The parameter ratios, Ktrans, ve, A and α calculated from the LD data divided by the HD data, were all significantly larger than 1.0 (p<0.003) for tumor. T2* changes following contrast agent injection affected parameters calculated from HD data, but this was not the case for LD data. The results suggest that quantitative analysis of LD data may be at least as effective for cancer characterization as quantitative analysis of HD data. In addition, the combination of parameters from two different doses may provide useful diagnostic information.

Low dose positron emission tomography emulation from decimated high statistics: A clinical validation study.

The fundamental nature of positron emission tomography (PET), as an event detection system, provides some flexibility for data handling, including retrospective data manipulation. The reorganization of acquisition data allows the emulation of new scans arising from identical radiotracer spatial distributions, but with different statistical compositions, and is especially useful for evaluating the stability and reproducibility of reconstruction algorithms or when investigating extremely low count conditions. This approach is ubiquitous in the research literature but has only been validated, from the point of view of the noise properties, with numerical simulations and phantom data. We present here the first experiment comparing PET images of the same human subjects generated with two separate injections of radiotracer, using actual low dose (LD) data to validate a randomly decimated emulation from a standard dose scan. A key point of the work is focused on the randoms fractions, which scale differently than the trues at varying activity levels. Eleven patients with non-small cell lung cancer were enrolled in the study. Each imaging session consisted of two independent FDG-PET/CT scans: a LD scan followed by a standard dose (SD) scan. Images were first reconstructed, using filtered back-projection (FBP) and OSEM incorporating time-of-flight information and point-spread function modeling (PSFTOF), from the LD and SD datasets comprising all counts from each scanned bed position. The number of true counts was recorded for all LD scans, and independent, count-matched emulations (ELD) were reconstructed from the SD data. Noise distribution within the liver and standardized uptake value reproducibility within a population of contoured, tracer-avid lesion volumes were evaluated across scans and statistics. The randoms fraction estimates were 17.4±1.6% (14.9-19.4) in the LD data and 42±2.3% (37.1-45.5) in the SD data. Eleven lesions were identified and volumes of interest were generated with a 50% threshold isocontour for each lesion, in every image. The distributions of metabolic volumes, means and maxima defined by the contoured volumes-of-interest (VOIs) were similar between the LD and SD sets. A two-tailed, matched t-test was performed on the populations of region statistics for both LD and ELD reconstructions, and the t-statistics were 1.1 (P=0.267) and -0.22 (P=0.828) for the background liver VOIs and -0.54 (P=0.603) and 0.23 (P=0.821) for the lesion VOIs, for FBP and PSFTOF respectively. In every test, the null hypothesis that the two populations had the same mean could not be rejected at the 5% significance level. Our results demonstrate that clinical LD PET scans can indeed be accurately emulated by the statistical decimation of standard dose scans, and this was achieved through validation by images generated with unbiased random coincidence estimations.

Feasibility of low-dose CT with model-based iterative image reconstruction in follow-up of patients with testicular cancer

PurposeWe examine the performance of pure model-based iterative reconstruction with reduced-dose CT in follow-up of patients with early-stage testicular cancer. MethodsSixteen patients (mean age 35.6±7.4years) with stage I or II testicular cancer underwent conventional dose (CD) and low-dose (LD) CT acquisition during CT surveillance. LD data was reconstructed with model-based iterative reconstruction (LD–MBIR). Datasets were objectively and subjectively analysed at 8 anatomical levels. Two blinded clinical reads were compared to gold-standard assessment for diagnostic accuracy. ResultsMean radiation dose reduction of 67.1% was recorded. Mean dose measurements for LD–MBIR were: thorax – 66±11mGycm (DLP), 1.0±0.2mSv (ED), 2.0±0.4mGy (SSDE); abdominopelvic – 128±38mGycm (DLP), 1.9±0.6mSv (ED), 3.0±0.6mGy (SSDE). Objective noise and signal-to-noise ratio values were comparable between the CD and LD–MBIR images. LD–MBIR images were superior (p<0.001) with regard to subjective noise, streak artefact, 2-plane contrast resolution, 2-plane spatial resolution and diagnostic acceptability. All patients were correctly categorised as positive, indeterminate or negative for metastatic disease by 2 readers on LD–MBIR and CD datasets. ConclusionsMBIR facilitated a 67% reduction in radiation dose whilst producing images that were comparable or superior to conventional dose studies without loss of diagnostic utility.