Deep learning based bilateral filtering for edge-preserving denoising of respiratory-gated PET.

BACKGROUND: Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) - a locally adaptive image filter - allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering. METHODS: Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ( [ 18 F ] FDG, [ 18 F ] L-DOPA, [ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the "optimal" filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs. RESULTS: The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUV max values of the unfiltered images with a low mean ± SD difference of δ SUV max CNN , STD = (-3.9 ± 5.2)% and δ SUV max BF , STD = (-4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUV max values in the vast majority of cases with an overall average difference of δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed. CONCLUSIONS: Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning.

Asphericity derived from [18F]FDG PET as a new prognostic parameter in cervical cancer patients.

The objective of this study was to assess the prognostic value of asphericity (ASP) and standardized uptake ratio (SUR) in cervical cancer patients. Retrospective analysis was performed on a group of 508 (aged 55 ± 12 years) previously untreated cervical cancer patients. All patients underwent a pretreatment [18F]FDG PET/CT study to assess the severity of the disease. The metabolic tumor volume (MTV) of the cervical cancer was delineated with an adaptive threshold method. For the resulting ROIs the maximum standardized uptake value (SUVmax) was measured. In addition, ASP and SUR were determined as previously described. Univariate Cox regression and Kaplan-Meier analysis with respect to event free survival (EFS), overall survival (OS), freedom from distant metastasis (FFDM) and locoregional control (LRC) was performed. Additionally, a multivariate Cox regression including clinically relevant parameters was performed. In the survival analysis, MTV and ASP were shown to be prognostic factors for all investigated endpoints. Tumor metabolism quantified with the SUVmax was not prognostic for any of the endpoints (p > 0.2). The SUR did not reach statistical significance either (p = 0.1, 0.25, 0.066, 0.053, respectively). In the multivariate analysis, the ASP remained a significant factor for EFS and LRC, while MTV was a significant factor for FFDM, indicating their independent prognostic value for the respective endpoints. The alternative parameter ASP has the potential to improve the prognostic value of [18F]FDG PET/CT for event-free survival and locoregional control in radically treated cervical cancer patients.

A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [Formula: see text]F]FDG PET/CT.

PURPOSE: PET-derived metabolic tumor volume (MTV) and total lesion glycolysis of the primary tumor are known to be prognostic of clinical outcome in head and neck cancer (HNC). Including evaluation of lymph node metastases can further increase the prognostic value of PET but accurate manual delineation and classification of all lesions is time-consuming and prone to interobserver variability. Our goal, therefore, was development and evaluation of an automated tool for MTV delineation/classification of primary tumor and lymph node metastases in PET/CT investigations of HNC patients. METHODS: Automated lesion delineation was performed with a residual 3D U-Net convolutional neural network (CNN) incorporating a multi-head self-attention block. 698 [Formula: see text]F]FDG PET/CT scans from 3 different sites and 5 public databases were used for network training and testing. An external dataset of 181 [Formula: see text]F]FDG PET/CT scans from 2 additional sites was employed to assess the generalizability of the network. In these data, primary tumor and lymph node (LN) metastases were interactively delineated and labeled by two experienced physicians. Performance of the trained network models was assessed by 5-fold cross-validation in the main dataset and by pooling results from the 5 developed models in the external dataset. The Dice similarity coefficient (DSC) for individual delineation tasks and the primary tumor/metastasis classification accuracy were used as evaluation metrics. Additionally, a survival analysis using univariate Cox regression was performed comparing achieved group separation for manual and automated delineation, respectively. RESULTS: In the cross-validation experiment, delineation of all malignant lesions with the trained U-Net models achieves DSC of 0.885, 0.805, and 0.870 for primary tumor, LN metastases, and the union of both, respectively. In external testing, the DSC reaches 0.850, 0.724, and 0.823 for primary tumor, LN metastases, and the union of both, respectively. The voxel classification accuracy was 98.0% and 97.9% in cross-validation and external data, respectively. Univariate Cox analysis in the cross-validation and the external testing reveals that manually and automatically derived total MTVs are both highly prognostic with respect to overall survival, yielding essentially identical hazard ratios (HR) ([Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in cross-validation and [Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in external testing). CONCLUSION: To the best of our knowledge, this work presents the first CNN model for successful MTV delineation and lesion classification in HNC. In the vast majority of patients, the network performs satisfactory delineation and classification of primary tumor and lymph node metastases and only rarely requires more than minimal manual correction. It is thus able to massively facilitate study data evaluation in large patient groups and also does have clear potential for supervised clinical application.

18F-Fluorodeoxyglucose Positron Emission Tomography of Head and Neck Cancer: Location and HPV Specific Parameters for Potential Treatment Individualization.

Purpose: 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) is utilized for staging and treatment planning of head and neck squamous cell carcinomas (HNSCC). Some older publications on the prognostic relevance showed inconclusive results, most probably due to small study sizes. This study evaluates the prognostic and potentially predictive value of FDG-PET in a large multi-center analysis. Methods: Original analysis of individual FDG-PET and patient data from 16 international centers (8 institutional datasets, 8 public repositories) with 1104 patients. All patients received curative intent radiotherapy/chemoradiation (CRT) and pre-treatment FDG-PET imaging. Primary tumors were semi-automatically delineated for calculation of SUVmax, SUVmean, metabolic tumor volume (MTV) and total lesion glycolysis (TLG). Cox regression analyses were performed for event-free survival (EFS), overall survival (OS), loco-regional control (LRC) and freedom from distant metastases (FFDM). Results: FDG-PET parameters were associated with patient outcome in the whole cohort regarding clinical endpoints (EFS, OS, LRC, FFDM), in uni- and multivariate Cox regression analyses. Several previously published cut-off values were successfully validated. Subgroup analyses identified tumor- and human papillomavirus (HPV) specific parameters. In HPV positive oropharynx cancer (OPC) SUVmax was well suited to identify patients with excellent LRC for organ preservation. Patients with SUVmax of 14 or less were unlikely to develop loco-regional recurrence after definitive CRT. In contrast FDG PET parameters deliver only limited prognostic information in laryngeal cancer. Conclusion: FDG-PET parameters bear considerable prognostic value in HNSCC and potential predictive value in subgroups of patients, especially regarding treatment de-intensification and organ-preservation. The potential predictive value needs further validation in appropriate control groups. Further research on advanced imaging approaches including radiomics or artificial intelligence methods should implement the identified cut-off values as benchmark routine imaging parameters.

A systematic review on the use of quantitative imaging to detect cancer therapy adverse effects in normal-appearing brain tissue.

Cancer therapy for both central nervous system (CNS) and non-CNS tumors has been previously associated with transient and long-term cognitive deterioration, commonly referred to as 'chemo fog'. This therapy-related damage to otherwise normal-appearing brain tissue is reported using post-mortem neuropathological analysis. Although the literature on monitoring therapy effects on structural magnetic resonance imaging (MRI) is well established, such macroscopic structural changes appear relatively late and irreversible. Early quantitative MRI biomarkers of therapy-induced damage would potentially permit taking these treatment side effects into account, paving the way towards a more personalized treatment planning.This systematic review (PROSPERO number 224196) provides an overview of quantitative tomographic imaging methods, potentially identifying the adverse side effects of cancer therapy in normal-appearing brain tissue. Seventy studies were obtained from the MEDLINE and Web of Science databases. Studies reporting changes in normal-appearing brain tissue using MRI, PET, or SPECT quantitative biomarkers, related to radio-, chemo-, immuno-, or hormone therapy for any kind of solid, cystic, or liquid tumor were included. The main findings of the reviewed studies were summarized, providing also the risk of bias of each study assessed using a modified QUADAS-2 tool. For each imaging method, this review provides the methodological background, and the benefits and shortcomings of each method from the imaging perspective. Finally, a set of recommendations is proposed to support future research.

Multivariate Analysis Identifies Eight Novel Loci Associated with Meat Productivity Traits in Sheep.

Despite their economic value, sheep remain relatively poorly studied animals in terms of the number of known loci and genes associated with commercially important traits. This gap in our knowledge can be filled in by performing new genome-wide association studies (GWAS) or by re-analyzing previously documented data using novel powerful statistical methods. This study is focused on the search for new loci associated with meat productivity and carcass traits in sheep. With a multivariate approach applied to publicly available GWAS results, we identified eight novel loci associated with the meat productivity and carcass traits in sheep. Using an in silico follow-up approach, we prioritized 13 genes in these loci. One of eight novel loci near the FAM3C and WNT16 genes has been replicated in an independent sample of Russian sheep populations (N = 108). The novel loci were added to our regularly updated database increasing the number of known loci to more than 140.

A convolutional neural network for fully automated blood SUV determination to facilitate SUR computation in oncological FDG-PET.

PURPOSE: The standardized uptake value (SUV) is widely used for quantitative evaluation in oncological FDG-PET but has well-known shortcomings as a measure of the tumor's glucose consumption. The standard uptake ratio (SUR) of tumor SUV and arterial blood SUV (BSUV) possesses an increased prognostic value but requires image-based BSUV determination, typically in the aortic lumen. However, accurate manual ROI delineation requires care and imposes an additional workload, which makes the SUR approach less attractive for clinical routine. The goal of the present work was the development of a fully automated method for BSUV determination in whole-body PET/CT. METHODS: Automatic delineation of the aortic lumen was performed with a convolutional neural network (CNN), using the U-Net architecture. A total of 946 FDG PET/CT scans from several sites were used for network training (N = 366) and testing (N = 580). For all scans, the aortic lumen was manually delineated, avoiding areas affected by motion-induced attenuation artifacts or potential spillover from adjacent FDG-avid regions. Performance of the network was assessed using the fractional deviations of automatically and manually derived BSUVs in the test data. RESULTS: The trained U-Net yields BSUVs in close agreement with those obtained from manual delineation. Comparison of manually and automatically derived BSUVs shows excellent concordance: the mean relative BSUV difference was (mean ± SD) = (- 0.5 ± 2.2)% with a 95% confidence interval of [- 5.1,3.8]% and a total range of [- 10.0, 12.0]%. For four test cases, the derived ROIs were unusable (< 1 ml). CONCLUSION: CNNs are capable of performing robust automatic image-based BSUV determination. Integrating automatic BSUV derivation into PET data processing workflows will significantly facilitate SUR computation without increasing the workload in the clinical setting.

Time efficient scatter correction for time-of-flight PET: the immediate scatter approximation.

Utilization of time-of-flight (TOF) information allows us to improve image quality and convergence rate in iterative PET image reconstruction. In order to obtain quantitatively correct images accurate scatter correction (SC) is required that accounts for the non-uniform distribution of scatter events over the TOF bins. However, existing simplified TOF-SC algorithms frequently exhibit limited accuracy while the currently accepted reference method-the TOF extension of the single scatter simulation approach (TOF-SSS)-is computationally demanding and can substantially slow down the reconstruction. In this paper we propose and evaluate a new accelerated TOF-SC algorithm in order to improve this situation. The key idea of the algorithm is the use of an immediate scatter approximation (ISA) for scatter time distribution calculation which speeds up estimation of the required TOF scatter by a factor of up to five in comparison to TOF-SSS. The proposed approach was evaluated in dedicated phantom measurements providing challenging high activity contrast conditions as well as in representative clinical patient data sets. Our results show that ISA is a viable alternative to TOF-SSS. The reconstructed images are in excellent quantitative agreement with those obtained with TOF-SSS while overall reconstruction time can be reduced by a factor of two in whole-body studies, even when using a listmode reconstruction not optimized for speed.