Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise.
Ontology highlight
ABSTRACT: Purpose
To enhance the image quality of oncology [18F]-FDG PET scans acquired in shorter times and reconstructed by faster algorithms using deep neural networks.Methods
List-mode data from 277 [18F]-FDG PET/CT scans, from six centres using GE Discovery PET/CT scanners, were split into ¾-, ½- and ¼-duration scans. Full-duration datasets were reconstructed using the convergent block sequential regularised expectation maximisation (BSREM) algorithm. Short-duration datasets were reconstructed with the faster OSEM algorithm. The 277 examinations were divided into training (n = 237), validation (n = 15) and testing (n = 25) sets. Three deep learning enhancement (DLE) models were trained to map full and partial-duration OSEM images into their target full-duration BSREM images. In addition to standardised uptake value (SUV) evaluations in lesions, liver and lungs, two experienced radiologists scored the quality of testing set images and BSREM in a blinded clinical reading (175 series).Results
OSEM reconstructions demonstrated up to 22% difference in lesion SUVmax, for different scan durations, compared to full-duration BSREM. Application of the DLE models reduced this difference significantly for full-, ¾- and ½-duration scans, while simultaneously reducing the noise in the liver. The clinical reading showed that the standard DLE model with full- or ¾-duration scans provided an image quality substantially comparable to full-duration scans with BSREM reconstruction, yet in a shorter reconstruction time.Conclusion
Deep learning-based image enhancement models may allow a reduction in scan time (or injected activity) by up to 50%, and can decrease reconstruction time to a third, while maintaining image quality.
SUBMITTER: Mehranian A
PROVIDER: S-EPMC8803788 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The Centers for Medicare and Medicaid Services coverage includes 3 posttherapy 18F-FDG PET/CT scans per patient and per tumor type. Any additional follow-up 18F-FDG PET/CT scans will be reimbursed at the discretion of a local Medicare administrator, if deemed medically necessary. This study aimed to investigate common clinical indications for performing a fourth or additional follow-up 18F-FDG PET/CT scans that could affect the management of patients. Methods: This was a retrospective institutional review of 433 oncology patients (203 men; mean age, 55 y), including a total of 1,659 fourth or subsequent follow-up PET/CT scans after completion of primary treatment. Twelve indications for performing a fourth or subsequent follow-up PET/CT scan were determined, and the impact of each of the 12 indications on patients' management was evaluated. Results: The primary tumors were breast cancer (92 patients, 426 scans), non-Hodgkin lymphoma (77 patients, 208 scans), Hodgkin disease (41 patients, 182 scans), colorectal cancer (70 patients, 286 scans), melanoma (69 patients, 271 scans), and lung cancer (84 patients, 286 scans). The indications were categorized in 4 groups: PET/CT for diagnosis of tumor recurrence (303/1,659, 18.3%), PET/CT before starting therapy for tumor recurrence (64/1,659, 3.9%), PET/CT to assess therapy response for tumor recurrence (507/1,659, 30.6%), and follow-up PET/CT after completion of treatment for tumor recurrence (785/1,659, 47.3%). Overall, fourth and subsequent follow-up 18F-FDG PET/CT scans resulted in change in management in 31.6% of the scans (356 of 1,128) when the scans were obtained for medical necessities (indications 1-11), and in 5.6% of the scans (30/531) when the scans were obtained without any medical necessity (indication 12). Conclusion: The fourth and subsequent PET/CT scans obtained after completion of primary treatment led to a change in management in 31.6% of the scans when acquired for appropriate clinical reasons. Performing follow-up PET/CT without appropriate medical reason had a low impact on patients' management and should be avoided.
| S-EPMC5414499 | biostudies-literature
Project description:BackgroundConventional clinical PET scanners typically have an axial field of view (AFOV) of 15-30 cm, resulting in limited coverage and relatively low photon detection efficiency. Taking advantage of the development of long-axial PET/CT, the uEXPLORER PET/CT scanner with an axial coverage of 194 cm increases the effective count rate by approximately 40 times compared to that of conventional PET scanners. Ordered subset expectation maximization (OSEM) is the most widely used iterative algorithm in PET. The major drawback of OSEM is that the iteration process must be stopped before convergence to avoid image degradation due to excessive noise. A new Bayesian penalized-likelihood iterative PET reconstruction, named HYPER iterative, was developed and is now available on the uEXPLORER total-body PET/CT, which incorporates a noise control component by using a penalty function in each iteration and finds the maximum likelihood solution through repeated iterations. To date, its impact on lesion visibility in patients with a full injected dose or half injected dose is unclear. The goal of this study was to determine a proper protocol for routine 18F-FDG uEXPLORER total-body PET/CT scans.ResultsThe uEXPLORER total-body PET/CT images reconstructed using both OSEM and HYPER iterative algorithms of 20 tumour patients were retrospectively reviewed. The quality of the 5 min PET image was excellent (score 5) for all of the dose and reconstruction methods. Using the HYPER iterative method, the PET images reached excellent quality at 1 min with full-dose PET and at 2 min with half-dose PET. The PET image reached a similar excellent quality at 2 min with a full dose and at 3 min with a half dose using OSEM. The noise in the OSEM reconstruction was higher than that in the HYPER iterative. Compared to OSEM, the HYPER iterative had a slightly higher SUVmax and TBR of the lesions for large positive lesions (≥ 2 cm) (SUVmax: up to 9.03% higher in full dose and up to 12.52% higher in half dose; TBR: up to 8.69% higher in full dose and up to 23.39% higher in half dose). For small positive lesions (≤ 10 mm), the HYPER iterative had an obviously higher SUVmax and TBR of the lesions (SUVmax: up to 45.21% higher in full dose and up to 74.96% higher in half dose; TBR: up to 44.91% higher in full dose and up to 93.73% higher in half dose).ConclusionsA 1 min scan with a full dose and a 2 min scan with a half dose are optimal for clinical diagnosis using the HYPER iterative and 2 min and 3 min for OSEM. For quantification of the small lesions, HYPER iterative reconstruction is preferred.
| S-EPMC10495295 | biostudies-literature
Project description:PurposePositron emission tomography (PET) imaging with amyloid-beta (Aβ) tracers and 2-[18F] fluoro-2-Deoxy-D-glucose (18F-FDG) is extensively employed in Alzheimer's disease (AD) studies as biomarkers of AD pathology and neurodegeneration. To reduce cost and additional burdens to the patient, early-frame uptake during Aβ PET scanning has been proposed as a surrogate measure of regional glucose metabolism. Considering the disease state specific impact of AD on neurovascular coupling, we investigated to what extent the information captured in the early frames of an Aβ-PET (18F-florbetapir or 18F-florbetaben) scan is comparable to that of a 18F-FDG PET scan, independent of disease state.MethodA partial correlation was performed on early-frame 18F-florbetapir and 18F-FDG regional data from 100 participants. In a secondary analysis, we compared 92 18F-florbetapir and 21 18F-florbetaben early-frame Aβ scans from cognitively unimpaired and mild cognitive impairment participants to ascertain if regional early-frame information was similar across different Aβ-PET radioligands.ResultsThe partial correlation of early-frame 18F-florbetapir with 18F-FDG was significant in all 84 brain ROIs, with correlation values ranging from 0.61 to 0.94. There were no significant differences between early-frame 18F-florbetapir and 18F-florbetaben images.ConclusionOverall, we find that the regional uptake measurements from early-frame 18F-florbetapir are strongly correlated with regional glucose metabolism as measured in ground-truth 18F-FDG PET scans, regardless of disease state. Future studies should focus on longitudinal early-frame amyloid PET imaging studies to further assess the value of early-frame imaging as a marker of brain metabolic decline.
| S-EPMC8763988 | biostudies-literature
Project description:Knowledge of the within-subject variability of 18F-FDG PET/MRI measurements is necessary for proper interpretation of quantitative PET or MRI metrics in the context of therapeutic efficacy assessments with integrated PET/MRI scanners. The goal of this study was to determine the test-retest repeatability of these metrics on PET/MRI, with comparison to similar metrics acquired by PET/CT. Methods: This prospective study enrolled subjects with pathology-proven pelvic malignancies. Baseline imaging consisted of PET/CT immediately followed by PET/MRI, using a single 370-MBq 18F-FDG dose. Repeat imaging was performed within 7 d using an identical imaging protocol, with no oncologic therapy between sessions. PET imaging on both scanners consisted of a list-mode acquisition at a single pelvic station. The MRI consisted of 2-point Dixon imaging for attenuation correction, standard sequences for anatomic correlation, and diffusion-weighted imaging. PET data were statically reconstructed using various frame durations and minimizing uptake time differences between sessions. SUV metrics were extracted for both PET/CT and PET/MRI in each imaging session. Apparent diffusion coefficient (ADC) metrics were extracted for both PET/MRI sessions. Results: The study cohort consisted of 14 subjects (13 female, 1 male) with various pelvic cancers (11 cervical, 2 rectal, 1 endometrial). For SUVmax, the within-subject coefficient of variation (wCV) appeared higher for PET/CT (8.5%-12.8%) than PET/MRI (6.6%-8.7%) across all PET reconstructions, though with no significant repeatability differences (all P values ≥ 0.08) between modalities. For lean body mass-adjusted SUVpeak, the wCVs appeared similar for PET/CT (9.9%-11.5%) and PET/MRI (9.2%-11.3%) across all PET reconstructions, again with no significant repeatability differences (all P values ≥ 0.14) between modalities. For PET/MRI, the wCV for ADCmedian of 3.5% appeared lower than the wCVs for SUVmax (6.6%-8.7%) and SULpeak (9.2%-11.3%), though without significant repeatability differences (all P values ≥ 0.23). Conclusion: For solid tumors of the pelvis, the repeatability of the evaluated SUV and ADC metrics on 18F-FDG PET/MRI is both acceptably high and similar to previously published values for 18F-FDG PET/CT and MRI, supporting the use of 18F-FDG PET/MRI for quantitative oncologic treatment response assessments.
| S-EPMC6681694 | biostudies-literature
Project description:IntroductionTumor hypoxia and angiogenesis are implicated in tumor growth and metastases, and anti-angiogenic therapies have an important role in treating patients with metastatic colorectal cancer. However, the prevalence of hypoxia has not been fully evaluated in colorectal liver metastases, and hypoxic response to anti-angiogenic therapy has not been clearly established. The aims of the study were to evaluate the changes seen on 18F-FMISO and 18F-FDG PET scans in patients treated with anti-angiogenic therapy, and to correlate these measures of hypoxia and metabolism with clinical outcomes, and blood biomarkers of angiogenesis.MethodsPatients with metastatic colorectal carcinoma planned for treatment with bevacizumab and chemotherapy received routine staging investigations prior to any treatment, including a FDG PET scan. A FMISO PET scan was performed within 4 weeks of staging tests, with blood specimens collected at that time for serum VEGF and osteopontin measurement. Follow-up FDG and FMISO scans were performed after 1 cycle of treatment. Results were compared to response (RECIST), progression free survival (PFS), and overall survival (OS).ResultsA total of 15 patients were recruited into this prospective trial, of which 13 patients were evaluable for assessment of treatment follow-up. Baseline FDG uptake was higher than FMISO uptake, and there was a significant decrease in FDG uptake (SUVmax and TGV) but not FMISO uptake (SUVmax and TNR) after treatment. There was a positive correlation between FDG and FMISO SUVmax on both baseline and post-treatment PET scans. Blood biomarkers of serum VEGF and osteopontin were significantly correlated with the FDG and FMISO PET parameters.ConclusionsThis study shows that hypoxia in metastatic colorectal cancer, assessed by FMISO PET, shows minor changes following initial treatment with anti-angiogenic therapy, but is associated with therapeutic response. FDG PET uptake changes (SUVmax, TLG) are also associated with response to anti-angiogenic therapy. These findings demonstrate the interplay between tumor metabolism and hypoxic regulation following anti-angiogenic treatment of metastatic colorectal cancer.
| S-EPMC8010243 | biostudies-literature
Project description:Radiomics analysis of [18F]-fluorodeoxyglucose ([18F]-FDG) PET images could be leveraged for personalised cancer medicine. However, the inherent sensitivity of radiomic features to intensity discretisation and voxel interpolation complicates its clinical translation. In this work, we evaluated the robustness of tumour [18F]-FDG-PET radiomic features to 174 different variations in intensity resolution or voxel size, and determined whether implementing parameter range conditions or dependency corrections could improve their robustness. Using 485 patient images spanning three cancer types: non-small cell lung cancer (NSCLC), melanoma, and lymphoma, we observed features were more sensitive to intensity discretisation than voxel interpolation, especially texture features. In most of our investigations, the majority of non-robust features could be made robust by applying parameter range conditions. Correctable features, which were generally fewer than conditionally robust, showed systematic dependence on bin configuration or voxel size that could be minimised by applying corrections based on simple mathematical equations. Melanoma images exhibited limited robustness and correctability relative to NSCLC and lymphoma. Our study provides an in-depth characterisation of the sensitivity of [18F]-FDG-PET features to image processing variations and reinforces the need for careful selection of imaging biomarkers prior to any clinical application.
| S-EPMC11251269 | biostudies-literature
Project description:BackgroundThe clinical diagnosis of deep sternal wound infection (DSWI) is supported by imaging findings including 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG-PET/CT). To avoid misinterpretation due to normal post-surgery inflammation we assessed normal imaging findings in non-infected patients after sternotomy.MethodsThis is a prospective cohort study including non-infectious patients with sternotomy. All patients underwent 18F-FDG-PET/CT at either 5 weeks (group 1), 12 weeks (group 2) or 52 weeks (group 3) post-surgery. 18F-FDG uptake was scored visually in five categories and assessed quantitatively.ResultsA total of 44 patients were included. Sternal mean SUVmax was 7.34 (± 1.86), 5.22 (± 2.55) and 3.20 (± 1.80) in group 1, 2 and 3, respectively (p < 0.01). Sternal mean SUVmean was 3.84 (± 1.00), 2.69 (± 1.32) and 1.71 (± 0.98) in group 1, 2 and 3 (p < 0.01). All patients in group 1 had elevated uptake whereas group 2 and 3 showed 2/15 (13%) and 11/20 (55%) patients respectively with no elevated uptake. Group 3 still showed an elevated uptake pattern in in 9/20 (45%) and in 3/9 (33%) with a high-grade diffuse uptake pattern.ConclusionThis study shows significant lower sternal 18F-FDG at 55 weeks compared to 5 weeks post-sternotomy however elevated uptake patterns may persist.
| S-EPMC10261398 | biostudies-literature
Project description:BackgroundDiagnosis of vasculitis is challenging. To avoid invasive approaches, clinical guidelines recommend the use of diagnostic imaging. This study aimed at evaluating the diagnostic accuracy of [18F]-fluorodeoxyglucose ([18F]FDG) position emission tomography/computed tomography (PET/CT) in large vessel vasculitis (LVV) and how this is affected by inter-operator variability.MethodsA total of 279 patients who performed [18F]-FDG PET/CT for suspicion of LVV were retrospectively analyzed. We tested the qualitative and semi-quantitative analysis and parameters influencing image quality and interpretation. Exams were evaluated by two readers with different experience and their performance was compared.ResultsLVV diagnosis was confirmed in 81 patients. [18F]-FDG PET/CT accuracy was 73% and 67% for the expert reader and less experienced reader, respectively. The expert reader overall performed better than the less experienced one, with higher accuracy in patients with normal BMI (77.3 vs. 63.8%), normal level of glycemia (73.3 vs. 65%), younger age (76.6 vs. 68.2%), and when no therapy was in course at time of imaging (76.7 vs. 66.7%). The diagnostic performance of both readers did not improve using semi-quantitative parameters.ConclusionsWe confirmed the appropriateness of the recommended criteria for image acquisition and interpretation, underlining the importance of experience in image interpretation for the optimal diagnostic performance of [18F]FDG PET/CT in vasculitis.
| S-EPMC9689655 | biostudies-literature
Project description:In Mild Cognitive Impairment (MCI), the study of brain metabolism, provided by 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) can be integrated with brain perfusion through pseudo-Continuous Arterial Spin Labeling Magnetic Resonance sequences (MR pCASL). Cortical hypometabolism identification generally relies on wide control group datasets; pCASL control groups are instead not publicly available yet, due to lack of standardization in the acquisition parameters. This study presents a quantitative pipeline to be applied to PET and pCASL data to coherently analyze metabolism and perfusion inside 16 matching cortical regions of interest (ROIs) derived from the AAL3 atlas. The PET line is tuned on 36 MCI patients and 107 healthy control subjects, to agree in identifying hypometabolic regions with clinical reference methods (visual analysis supported by a vendor tool and Statistical Parametric Mapping, SPM, with two parametrizations here identified as SPM-A and SPM-B). The analysis was conducted for each ROI separately. The proposed PET analysis pipeline obtained accuracy 78 % and Cohen's к 60 % vs visual analysis, accuracy 79 % and Cohen's к 58 % vs SPM-A, accuracy 77 % and Cohen's к 54 % vs SPM-B. Cohen's к resulted not significantly different from SPM-A and SPM-B Cohen's к when assuming visual analysis as reference method (p-value 0.61 and 0.31 respectively). Considering SPM-A as reference method, Cohen's к is not significantly different from SPM-B Cohen's к as well (p-value = 1.00). The complete PET-pCASL pipeline was then preliminarily applied on 5 MCI patients and metabolism-perfusion regional correlations were assessed. The proposed approach can be considered as a promising tool for PET-pCASL joint analyses in MCI, even in the absence of a pCASL control group, to perform metabolism-perfusion regional correlation studies, and to assess and compare perfusion in hypometabolic or normo-metabolic areas.
| S-EPMC10755331 | biostudies-literature
Project description:Active surveillance for patients with esophageal cancer and a clinically complete response (cCR) after neoadjuvant chemoradiotherapy (nCRT) is being studied. Active surveillance requires accurate clinical response evaluations. 18F-FDG PET/CT might be able to detect local tumor recurrence after nCRT as soon as the esophagus recovers from radiation-induced esophagitis. The aims of this study were to assess the value of serial 18F-FDG PET/CT scans for detecting local recurrence in patients beyond 3 mo after nCRT and to determine when radiation-induced esophagitis has resolved. Methods: This retrospective multicenter study included patients who had cCR after nCRT, who initially declined surgery, and who subsequently underwent active surveillance. Clinical response evaluations included 18F-FDG PET/CT, endoscopic biopsies, and endoscopic ultrasound with fine-needle aspiration at regular intervals. SUVmax normalized for lean body mass (SULmax) was measured at the primary tumor site. The percentage change in SULmax (Δ%SULmax) between the last follow-up scan and the scan at 3 mo after nCRT was calculated. Tumor recurrence was defined as biopsy-proven vital tumor at the initial tumor site. Results: Of 41 eligible patients, 24 patients had recurrent disease at a median of 6.5 mo after nCRT and 17 patients remained cancer free during a median follow-up of 24 mo after nCRT. Five of 24 patients with tumor recurrence had sudden intense SULmax increases of greater than 180%. In 19 of 24 patients with tumor recurrence, SULmax gradually increased (median Δ%SULmax, +18%), whereas SULmax decreased (median Δ%SULmax, -12%) in patients with ongoing cCR (P < 0.001, independent-samples t test). In patients with ongoing cCR, SULmax was lowest at 11 mo after nCRT. Conclusion: Serial 18F-FDG PET/CT might be a useful tool for detecting tumor recurrence during active surveillance. In patients with ongoing cCR, the lowest SULmax was reached at 11 mo after nCRT, suggesting that radiation-induced esophagitis had mostly resolved by that time. These findings warrant further evaluation in a larger cohort.
| S-EPMC8049375 | biostudies-literature