The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Deep transformer-based personalized dosimetry from SPECT/CT images: a hybrid approach for [177Lu]Lu-DOTATATE radiopharmaceutical therapy.

PURPOSE: Accurate dosimetry is critical for ensuring the safety and efficacy of radiopharmaceutical therapies. In current clinical dosimetry practice, MIRD formalisms are widely employed. However, with the rapid advancement of deep learning (DL) algorithms, there has been an increasing interest in leveraging the calculation speed and automation capabilities for different tasks. We aimed to develop a hybrid transformer-based deep learning (DL) model that incorporates a multiple voxel S-value (MSV) approach for voxel-level dosimetry in [177Lu]Lu-DOTATATE therapy. The goal was to enhance the performance of the model to achieve accuracy levels closely aligned with Monte Carlo (MC) simulations, considered as the standard of reference. We extended our analysis to include MIRD formalisms (SSV and MSV), thereby conducting a comprehensive dosimetry study. METHODS: We used a dataset consisting of 22 patients undergoing up to 4 cycles of [177Lu]Lu-DOTATATE therapy. MC simulations were used to generate reference absorbed dose maps. In addition, MIRD formalism approaches, namely, single S-value (SSV) and MSV techniques, were performed. A UNEt TRansformer (UNETR) DL architecture was trained using five-fold cross-validation to generate MC-based dose maps. Co-registered CT images were fed into the network as input, whereas the difference between MC and MSV (MC-MSV) was set as output. DL results are then integrated to MSV to revive the MC dose maps. Finally, the dose maps generated by MSV, SSV, and DL were quantitatively compared to the MC reference at both voxel level and organ level (organs at risk and lesions). RESULTS: The DL approach showed slightly better performance (voxel relative absolute error (RAE) = 5.28 ± 1.32) compared to MSV (voxel RAE = 5.54 ± 1.4) and outperformed SSV (voxel RAE = 7.8 ± 3.02). Gamma analysis pass rates were 99.0 ± 1.2%, 98.8 ± 1.3%, and 98.7 ± 1.52% for DL, MSV, and SSV approaches, respectively. The computational time for MC was the highest (~2 days for a single-bed SPECT study) compared to MSV, SSV, and DL, whereas the DL-based approach outperformed the other approaches in terms of time efficiency (3 s for a single-bed SPECT). Organ-wise analysis showed absolute percent errors of 1.44 ± 3.05%, 1.18 ± 2.65%, and 1.15 ± 2.5% for SSV, MSV, and DL approaches, respectively, in lesion-absorbed doses. CONCLUSION: A hybrid transformer-based deep learning model was developed for fast and accurate dose map generation, outperforming the MIRD approaches, specifically in heterogenous regions. The model achieved accuracy close to MC gold standard and has potential for clinical implementation for use on large-scale datasets.

TMTV-Net: fully automated total metabolic tumor volume segmentation in lymphoma PET/CT images - a multi-center generalizability analysis.

PURPOSE: Total metabolic tumor volume (TMTV) segmentation has significant value enabling quantitative imaging biomarkers for lymphoma management. In this work, we tackle the challenging task of automated tumor delineation in lymphoma from PET/CT scans using a cascaded approach. METHODS: Our study included 1418 2-[18F]FDG PET/CT scans from four different centers. The dataset was divided into 900 scans for development/validation/testing phases and 518 for multi-center external testing. The former consisted of 450 lymphoma, lung cancer, and melanoma scans, along with 450 negative scans, while the latter consisted of lymphoma patients from different centers with diffuse large B cell, primary mediastinal large B cell, and classic Hodgkin lymphoma cases. Our approach involves resampling PET/CT images into different voxel sizes in the first step, followed by training multi-resolution 3D U-Nets on each resampled dataset using a fivefold cross-validation scheme. The models trained on different data splits were ensemble. After applying soft voting to the predicted masks, in the second step, we input the probability-averaged predictions, along with the input imaging data, into another 3D U-Net. Models were trained with semi-supervised loss. We additionally considered the effectiveness of using test time augmentation (TTA) to improve the segmentation performance after training. In addition to quantitative analysis including Dice score (DSC) and TMTV comparisons, the qualitative evaluation was also conducted by nuclear medicine physicians. RESULTS: Our cascaded soft-voting guided approach resulted in performance with an average DSC of 0.68 ± 0.12 for the internal test data from developmental dataset, and an average DSC of 0.66 ± 0.18 on the multi-site external data (n = 518), significantly outperforming (p < 0.001) state-of-the-art (SOTA) approaches including nnU-Net and SWIN UNETR. While TTA yielded enhanced performance gains for some of the comparator methods, its impact on our cascaded approach was found to be negligible (DSC: 0.66 ± 0.16). Our approach reliably quantified TMTV, with a correlation of 0.89 with the ground truth (p < 0.001). Furthermore, in terms of visual assessment, concordance between quantitative evaluations and clinician feedback was observed in the majority of cases. The average relative error (ARE) and the absolute error (AE) in TMTV prediction on external multi-centric dataset were ARE = 0.43 ± 0.54 and AE = 157.32 ± 378.12 (mL) for all the external test data (n = 518), and ARE = 0.30 ± 0.22 and AE = 82.05 ± 99.78 (mL) when the 10% outliers (n = 53) were excluded. CONCLUSION: TMTV-Net demonstrates strong performance and generalizability in TMTV segmentation across multi-site external datasets, encompassing various lymphoma subtypes. A negligible reduction of 2% in overall performance during testing on external data highlights robust model generalizability across different centers and cancer types, likely attributable to its training with resampled inputs. Our model is publicly available, allowing easy multi-site evaluation and generalizability analysis on datasets from different institutions.

Associations of Vascular Risk and Amyloid Burden with Subsequent Dementia.

OBJECTIVE: Midlife vascular risk factors (MVRFs) are associated with incident dementia, as are amyloid ß (Aß) deposition and neurodegeneration. Whether vascular and Alzheimer disease-associated factors contribute to dementia independently or interact synergistically to reduce cognition is poorly understood. METHODS: Participants in the Atherosclerosis Risk in Communities-Positron Emission Tomography study were followed from 1987-1989 (45-64 years old) through 2016-2017 (74-94 years old), with repeat cognitive assessment and dementia adjudication. In 2011-2013, dementia-free participants underwent brain magnetic resonance imaging (with white matter hyperintensity [WMH] and brain volume measurement) and florbetapir (Aß) positron emission tomography. The relative contributions of vascular risk and injury (MVRFs, WMH volume), elevated Aß standardized uptake value ratio (SUVR), and neurodegeneration (smaller temporoparietal brain regions) to incident dementia were evaluated with adjusted Cox models. RESULTS: In 298 individuals, 36 developed dementia (median follow-up = 4.9 years). Midlife hypertension and Aß each independently predicted dementia risk (hypertension: hazard ratio [HR] = 2.57, 95% confidence interval [CI] = 1.16-5.67; Aß SUVR [per standard deviation (SD)]: HR = 2.57, 95% CI = 1.72-3.84), but did not interact significantly, whereas late life diabetes (HR = 2.50, 95% CI = 1.18-5.28) and Aß independently predicted dementia risk. WMHs (per SD: HR = 1.51, 95% CI = 1.03-2.20) and Aß SUVR (HR = 2.52, 95% CI = 1.83-3.47) independently contributed to incident dementia, but WMHs lost significance when MVRFs were included. Smaller temporoparietal brain regions were associated with incident dementia, independent of Aß and MVRFs (HR = 2.18, 95% CI = 1.18-4.01). INTERPRETATION: Midlife hypertension and late life Aß are independently associated with dementia risk, without evidence for synergy on a multiplicative scale. Given the independent contributions of vascular and amyloid mechanisms, multiple pathways should be considered when evaluating interventions to reduce the burden of dementia. ANN NEUROL 2022;92:607-619.

Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning.

PURPOSE: Attenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images. METHODS: Non-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center). RESULTS: In terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21-14.81%) and FL-PL (CI:11.82-13.84%) models demonstrated excellent agreement with the centralized framework (CI:10.32-12.00%), while FL-based algorithms improved model performance by over 11% compared to CB training strategy (CI: 22.34-26.10%). Furthermore, the Mann-Whitney test between different strategies revealed no significant differences between CZ and FL-based algorithms (p-value > 0.05) in center-categorized mode. At the same time, a significant difference was observed between the different training approaches on the overall dataset (p-value < 0.05). In addition, voxel-wise comparison, with respect to reference CT-ASC, exhibited similar performance for images predicted by CZ (R2 = 0.94), FL-SQ (R2 = 0.93), and FL-PL (R2 = 0.92), while CB model achieved a far lower coefficient of determination (R2 = 0.74). Despite the strong correlations between CZ and FL-based methods compared to reference CT-ASC, a slight underestimation of predicted voxel values was observed. CONCLUSION: Deep learning-based models provide promising results toward quantitative PET image reconstruction. Specifically, we developed two FL models and compared their performance with center-based and centralized models. The proposed FL-based models achieved higher performance compared to center-based models, comparable with centralized models. Our work provided strong empirical evidence that the FL framework can fully benefit from the generalizability and robustness of DL models used for AC/SC in PET, while obviating the need for the direct sharing of datasets between clinical imaging centers.

Differential privacy preserved federated transfer learning for multi-institutional 68Ga-PET image artefact detection and disentanglement.

PURPOSE: Image artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (68Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images. METHODS: Altogether, 1413 patients with 68Ga prostate-specific membrane antigen (PSMA)/DOTA-TATE (TOC) PET/CT scans from 3 countries, including 8 different centres, were enrolled in this study. CT-based attenuation and scatter correction (CT-ASC) was used in all centres for quantitative PET reconstruction. Prior to model training, an experienced nuclear medicine physician reviewed all images to ensure the use of high-quality, artefact-free PET images (421 patients' images). A deep neural network (modified U2Net) was trained on 80% of the artefact-free PET images to utilize centre-based (CeBa), centralized (CeZe) and the proposed differential privacy FTL frameworks. Quantitative analysis was performed in 20% of the clean data (with no artefacts) in each centre. A panel of two nuclear medicine physicians conducted qualitative assessment of image quality, diagnostic confidence and image artefacts in 128 patients with artefacts (256 images for CT-ASC and FTL-ASC). RESULTS: The three approaches investigated in this study for 68Ga-PET imaging (CeBa, CeZe and FTL) resulted in a mean absolute error (MAE) of 0.42 ± 0.21 (CI 95%: 0.38 to 0.47), 0.32 ± 0.23 (CI 95%: 0.27 to 0.37) and 0.28 ± 0.15 (CI 95%: 0.25 to 0.31), respectively. Statistical analysis using the Wilcoxon test revealed significant differences between the three approaches, with FTL outperforming CeBa and CeZe (p-value < 0.05) in the clean test set. The qualitative assessment demonstrated that FTL-ASC significantly improved image quality and diagnostic confidence and decreased image artefacts, compared to CT-ASC in 68Ga-PET imaging. In addition, mismatch and halo artefacts were successfully detected and disentangled in the chest, abdomen and pelvic regions in 68Ga-PET imaging. CONCLUSION: The proposed approach benefits from using large datasets from multiple centres while preserving patient privacy. Qualitative assessment by nuclear medicine physicians showed that the proposed model correctly addressed two main challenging artefacts in 68Ga-PET imaging. This technique could be integrated in the clinic for 68Ga-PET imaging artefact detection and disentanglement using multicentric heterogeneous datasets.

Deep learning-based harmonization of CT reconstruction kernels towards improved clinical task performance.

OBJECTIVES: To develop a deep learning-based harmonization framework, assessing whether it can improve performance of radiomics models given different kernels in different clinical tasks and additionally generalize to mitigate the effects of new/unobserved kernels on radiomics features. METHODS: Patient data with 2 reconstruction kernels and phantom data with 22 reconstruction kernels were included. Eighty-five patients were studied for lymph node metastasis (LNM) prediction, and 164 patients for differential diagnosis between lung cancer (LC) and pulmonary tuberculosis (TB). Two convolutional neural network (CNN) models were developed to convert images (i) from B70f to B30f (CNNa) and (ii) from B30f to B70f (CNNb). Model performance between the two kernels was evaluated using AUC and compared with other well-known harmonization methods. Patient-normalized feature difference (PNFD) was used to identify the incompatible kernels (i.e., kernel with median PNFD > 1) with baseline (B30f/B70f), and measure the ability of the CNN models to convert the non-comparable kernels. RESULTS: For LC versus pulmonary TB diagnosis, AUCs of CNNa vs. others were 0.85 vs. 0.54-0.74 (p = 0.0001-0.0003), and for CNNb vs. others: 0.87 vs. 0.54-0.86 (p = 0.0001-0.55). For LNM prediction, AUCs of CNNa vs. others were 0.68 vs. 0.56-0.61 (p = 0.10-0.39), and for CNNb vs. others: 0.78 vs. 0.70-0.73 (p = 0.07-0.40). After CNN harmonization, 17 of 20 (85%) of investigated unknown kernels produced comparable radiomics feature values relative to baseline (median PNFD from 1.10-2.31 to 0.23-1.13). CONCLUSION: The CNN harmonization effectively improved performance of radiomics models between reconstruction kernels in different clinical tasks, and reduced feature differences between unknown kernels vs. baseline. KEY POINTS: • The soft (B30f) and sharp (B70f) kernels strongly affect radiomics reproducibility and generalizability. • The convolutional neural network (CNN) harmonization methods performed better than location-scale (ComBat and centering-scaling) and matrix factorization harmonization methods (based on singular value decomposition (SVD) and independent component analysis (ICA)) in both clinical tasks. • The CNN harmonization methods improve feature reproducibility not only between specific kernels (B30f and B70f) from the same scanner, but also between unobserved kernels from different scanners of different vendors.

COMP Report: CPQR technical quality control guidelines for use of positron emission tomography/computed tomography in radiation treatment planning.

Positron emission tomography with x-ray computed tomography (PET/CT) is increasingly being utilized for radiation treatment planning (RTP). Accurate delivery of RT therefore depends on quality PET/CT data. This study covers quality control (QC) procedures required for PET/CT for diagnostic imaging and incremental QC required for RTP. Based on a review of the literature, it compiles a list of recommended tests, performance frequencies, and tolerances, as well as references to documents detailing how to perform each test. The report was commissioned by the Canadian Organization of Medical Physicists as part of the Canadian Partnership for Quality Radiotherapy initiative.

Computational modeling of PET tracer distribution in solid tumors integrating microvasculature.

BACKGROUND: We present computational modeling of positron emission tomography radiotracer uptake with consideration of blood flow and interstitial fluid flow, performing spatiotemporally-coupled modeling of uptake and integrating the microvasculature. In our mathematical modeling, the uptake of fluorodeoxyglucose F-18 (FDG) was simulated based on the Convection-Diffusion-Reaction equation given its high accuracy and reliability in modeling of transport phenomena. In the proposed model, blood flow and interstitial flow are solved simultaneously to calculate interstitial pressure and velocity distribution inside cancer and normal tissues. As a result, the spatiotemporal distribution of the FDG tracer is calculated based on velocity and pressure distributions in both kinds of tissues. RESULTS: Interstitial pressure has maximum value in the tumor region compared to surrounding tissue. In addition, interstitial fluid velocity is extremely low in the entire computational domain indicating that convection can be neglected without effecting results noticeably. Furthermore, our results illustrate that the total concentration of FDG in the tumor region is an order of magnitude larger than in surrounding normal tissue, due to lack of functional lymphatic drainage system and also highly-permeable microvessels in tumors. The magnitude of the free tracer and metabolized (phosphorylated) radiotracer concentrations followed very different trends over the entire time period, regardless of tissue type (tumor vs. normal). CONCLUSION: Our spatiotemporally-coupled modeling provides helpful tools towards improved understanding and quantification of in vivo preclinical and clinical studies.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network.

OBJECTIVE: We demonstrate the feasibility of direct generation of attenuation and scatter-corrected images from uncorrected images (PET-nonASC) using deep residual networks in whole-body 18F-FDG PET imaging. METHODS: Two- and three-dimensional deep residual networks using 2D successive slices (DL-2DS), 3D slices (DL-3DS) and 3D patches (DL-3DP) as input were constructed to perform joint attenuation and scatter correction on uncorrected whole-body images in an end-to-end fashion. We included 1150 clinical whole-body 18F-FDG PET/CT studies, among which 900, 100 and 150 patients were randomly partitioned into training, validation and independent validation sets, respectively. The images generated by the proposed approach were assessed using various evaluation metrics, including the root-mean-squared-error (RMSE) and absolute relative error (ARE %) using CT-based attenuation and scatter-corrected (CTAC) PET images as reference. PET image quantification variability was also assessed through voxel-wise standardized uptake value (SUV) bias calculation in different regions of the body (head, neck, chest, liver-lung, abdomen and pelvis). RESULTS: Our proposed attenuation and scatter correction (Deep-JASC) algorithm provided good image quality, comparable with those produced by CTAC. Across the 150 patients of the independent external validation set, the voxel-wise REs (%) were - 1.72 ± 4.22%, 3.75 ± 6.91% and - 3.08 ± 5.64 for DL-2DS, DL-3DS and DL-3DP, respectively. Overall, the DL-2DS approach led to superior performance compared with the other two 3D approaches. The brain and neck regions had the highest and lowest RMSE values between Deep-JASC and CTAC images, respectively. However, the largest ARE was observed in the chest (15.16 ± 3.96%) and liver/lung (11.18 ± 3.23%) regions for DL-2DS. DL-3DS and DL-3DP performed slightly better in the chest region, leading to AREs of 11.16 ± 3.42% and 11.69 ± 2.71%, respectively (p value < 0.05). The joint histogram analysis resulted in correlation coefficients of 0.985, 0.980 and 0.981 for DL-2DS, DL-3DS and DL-3DP approaches, respectively. CONCLUSION: This work demonstrated the feasibility of direct attenuation and scatter correction of whole-body 18F-FDG PET images using emission-only data via a deep residual network. The proposed approach achieved accurate attenuation and scatter correction without the need for anatomical images, such as CT and MRI. The technique is applicable in a clinical setting on standalone PET or PET/MRI systems. Nevertheless, Deep-JASC showing promising quantitative accuracy, vulnerability to noise was observed, leading to pseudo hot/cold spots and/or poor organ boundary definition in the resulting PET images.

Dynamic whole-body PET imaging: principles, potentials and applications.

PURPOSE: In this article, we discuss dynamic whole-body (DWB) positron emission tomography (PET) as an imaging tool with significant clinical potential, in relation to conventional standard uptake value (SUV) imaging. BACKGROUND: DWB PET involves dynamic data acquisition over an extended axial range, capturing tracer kinetic information that is not available with conventional static acquisition protocols. The method can be performed within reasonable clinical imaging times, and enables generation of multiple types of PET images with complementary information in a single imaging session. Importantly, DWB PET can be used to produce multi-parametric images of (i) Patlak slope (influx rate) and (ii) intercept (referred to sometimes as "distribution volume"), while also providing (iii) a conventional 'SUV-equivalent' image for certain protocols. RESULTS: We provide an overview of ongoing efforts (primarily focused on FDG PET) and discuss potential clinically relevant applications. CONCLUSION: Overall, the framework of DWB imaging [applicable to both PET/CT(computed tomography) and PET/MRI (magnetic resonance imaging)] generates quantitative measures that may add significant value to conventional SUV image-derived measures, with limited pitfalls as we also discuss in this work.

Impact of image reconstruction methods on quantitative accuracy and variability of FDG-PET volumetric and textural measures in solid tumors.

OBJECTIVE: This study aims to assess the impact of different image reconstruction methods on PET/CT quantitative volumetric and textural parameters and the inter-reconstruction variability of these measurements. METHODS: A total of 25 oncology patients with 65 lesions (between 2017 and 2018) and a phantom with signal-to-background ratios (SBR) of 2 and 4 were included. All images were retrospectively reconstructed using OSEM, PSF only, TOF only, and TOFPSF with 3-, 5-, and 6.4-mm Gaussian filters. The metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were measured. The relative percent error (ΔMTV and ΔTLG) with respect to true values, volume recovery coefficients, and Dice similarity coefficient, as well as inter-reconstruction variabilities were quantified and assessed. In clinical scans, textural features (coefficient of variation, skewness, and kurtosis) were determined. RESULTS: Among reconstruction methods, mean ΔMTV differed by -163.5 ± 14.1% to 6.3 ± 6.2% at SBR2 and -42.7 ± 36.7% to 8.6 ± 3.1 at SBR4. Dice similarity coefficient significantly increased by increasing SBR from 2 to 4, ranging from 25.7 to 83.4% between reconstruction methods. Mean ΔTLG was -12.0 ± 1.7 for diameters > 17 mm and -17.8 ± 7.8 for diameters ≤ 17 mm at SBR4. It was -31.7 ± 4.3 for diameters > 17 mm and -14.2 ± 5.8 for diameters ≤ 17 mm at SBR2. Textural features were prone to variations by reconstruction methods (p < 0.05). CONCLUSIONS: Inter-reconstruction variability was significantly affected by the target size, SBR, and cut-off threshold value. In small tumors, inter-reconstruction variability was noteworthy, and quantitative parameters were strongly affected. TOFPSF reconstruction with small filter size produced greater improvements in performance and accuracy in quantitative PET/CT imaging. KEY POINTS: • Quantitative volumetric PET evaluation is critical for the analysis of tumors. • However, volumetric and textural evaluation is prone to important variations according to different image reconstruction settings. • TOFPSF reconstruction with small filter size improves quantitative analysis.

Direct attenuation correction of brain PET images using only emission data via a deep convolutional encoder-decoder (Deep-DAC).

OBJECTIVE: To obtain attenuation-corrected PET images directly from non-attenuation-corrected images using a convolutional encoder-decoder network. METHODS: Brain PET images from 129 patients were evaluated. The network was designed to map non-attenuation-corrected (NAC) images to pixel-wise continuously valued measured attenuation-corrected (MAC) PET images via an encoder-decoder architecture. Image quality was evaluated using various evaluation metrics. Image quantification was assessed for 19 radiomic features in 83 brain regions as delineated using the Hammersmith atlas (n30r83). Reliability of measurements was determined using pixel-wise relative errors (RE; %) for radiomic feature values in reference MAC PET images. RESULTS: Peak signal-to-noise ratio (PSNR) and structural similarity index metric (SSIM) values were 39.2 ± 3.65 and 0.989 ± 0.006 for the external validation set, respectively. RE (%) of SUVmean was - 0.10 ± 2.14 for all regions, and only 3 of 83 regions depicted significant differences. However, the mean RE (%) of this region was 0.02 (range, - 0.83 to 1.18). SUVmax had mean RE (%) of - 3.87 ± 2.84 for all brain regions, and 17 regions in the brain depicted significant differences with respect to MAC images with a mean RE of - 3.99 ± 2.11 (range, - 8.46 to 0.76). Homogeneity amongst Haralick-based radiomic features had the highest number (20) of regions with significant differences with a mean RE (%) of 7.22 ± 2.99. CONCLUSIONS: Direct AC of PET images using deep convolutional encoder-decoder networks is a promising technique for brain PET images. The proposed deep learning method shows significant potential for emission-based AC in PET images with applications in PET/MRI and dedicated brain PET scanners. KEY POINTS: • We demonstrate direct emission-based attenuation correction of PET images without using anatomical information. • We performed radiomics analysis of 83 brain regions to show robustness of direct attenuation correction of PET images. • Deep learning methods have significant promise for emission-based attenuation correction in PET images with potential applications in PET/MRI and dedicated brain PET scanners.

Imager-4D: New Software for Viewing Dynamic PET Scans and Extracting Radiomic Parameters from PET Data.

Extensive research is currently being conducted into dynamic positron emission tomography (PET) acquisitions (including dynamic whole-body imaging) as well as extraction of radiomic features from imaging modalities. We describe a new PET viewing software known as Imager-4D that provides a facile means of viewing and analyzing dynamic PET data and obtaining associated quantitative metrics including radiomic parameters. The Imager-4D was programmed in the Java language utilizing the FX extensions. It is executable on any system for which a Java w/FX compliant virtual machine is available. The software incorporates the ability to view and analyze dynamic data acquired with different types of dynamic protocols. For image display, the program maintains a built-in library of 62 different lookup tables with monochromatic and full-color distributions. The Imager-4D provides multiple display layouts and can display fused images. Multiple methods of volume-of-interest (VOI) selection are available. Dynamic analysis features, such as image summation and full Patlak analysis, are also available. The user interface includes window width and level, blending, and zoom functionality. VOI sizes are adjustable and data from VOIs can either be displayed numerically or graphically within the software or exported. An example case of a 50-year-old woman with metastatic colorectal cancer and thyroiditis is included and demonstrates the steps for a user to obtain standard PET parameters, dynamic data, and radiomic features using selected VOIs. The Imager-4D represents a novel PET viewer that allows the user to view dynamic PET data, to derive dynamic and radiomic parameters from that data, and to combine dynamic data with radiomics ("dynomics"). The Imager-4D is available as a free download. This software has the potential to speed the adoption of advanced analysis of dynamic PET data into routine clinical use.

Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT.

OBJECTIVES: To investigate the impact of parameter settings as used for the generation of radiomics features on their robustness and disease differentiation (nasopharyngeal carcinoma (NPC) versus chronic nasopharyngitis (CN) in FDG PET/CT imaging). METHODS: We studied 106 patients (69/37 NPC/CN, pathology confirmed), and extracted 57 radiomics features under different parameter settings. Robustness was assessed by the intra-class correlation coefficient (ICC). Logistic regression with leave-one-out cross validation was used to generate classification probabilities, and diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). RESULTS: Varying averaging strategies and symmetry, 4/26 GLCM features showed poor range of pairwise ICCs of 0.02-0.98, while depicting good AUCs of 0.82-0.91. Varying distances, 5/26 GLCM features showed ICCs of 0.82-0.99 while corresponding AUCs were 0.52-0.91. 6/13 GLRLM features showed both high AUC (0.81-0.89) and high ICC (0.85-0.99) regarding to averaging strategies. 7/13 GLSZM features showed AUCs of 0.81-0.90 while having ICCs of 0.01-0.99 under different neighbourhoods. 2/5 NGTDM features showed AUCs of 0.81-0.85 while having ICCs of 0.19-0.89 for different window sizes. Differentiating a subset of NPC (stages I-II) form CN, both SumEntropy and SZLGE achieved significantly higher AUCs than metabolically active tumour volume (AUC: 0.91 vs. 0.72, p<0.01). CONCLUSIONS: Radiomics features depicting poor absolute-scale robustness regarding to parameter settings can still lead to good diagnostic performance. As such, robustness of radiomics features should not be overemphasized for removal of features towards assessment of clinical tasks. For differentiating NPC from CN, some radiomics features (e.g. SumEntropy, SZLGE, LGZE) outperformed conventional metrics. KEY POINTS: • Poor robustness did not necessarily translate into poor differentiation performance. • Absolute-scale robustness of radiomics features should not be overemphasized. • Radiomics features SumEntropy, SZLGE and LGZE outperformed conventional metrics.

Linking dopaminergic reward signals to the development of attentional bias: A positron emission tomographic study.

The attention system is shaped by reward history, such that learned reward cues involuntarily draw attention. Recent research has begun to uncover the neural mechanisms by which learned reward cues compete for attention, implicating dopamine (DA) signaling within the dorsal striatum. How these elevated priority signals develop in the brain during the course of learning is less well understood, as is the relationship between value-based attention and the experience of reward during learning. We hypothesized that the magnitude of the striatal DA response to reward during learning contributes to the development of a learned attentional bias towards the cue that predicted it, and examined this hypothesis using positron emission tomography with [11C]raclopride. We measured changes in dopamine release for rewarded versus unrewarded visual search for color-defined targets as indicated by the density and distribution of the available D2/D3 receptors. We then tested for correlations of individual differences in this measure of reward-related DA release to individual differences in the degree to which previously reward-associated but currently task-irrelevant stimuli impair performance in an attention task (i.e., value-driven attentional bias), revealing a significant relationship in the right anterior caudate. The degree to which reward-related DA release was right hemisphere lateralized was also predictive of later attentional bias. Our findings provide support for the hypothesis that value-driven attentional bias can be predicted from reward-related DA release during learning.

The impact of image reconstruction settings on 18F-FDG PET radiomic features: multi-scanner phantom and patient studies.

OBJECTIVES: The purpose of this study was to investigate the robustness of different PET/CT image radiomic features over a wide range of different reconstruction settings. METHODS: Phantom and patient studies were conducted, including two PET/CT scanners. Different reconstruction algorithms and parameters including number of sub-iterations, number of subsets, full width at half maximum (FWHM) of Gaussian filter, scan time per bed position and matrix size were studied. Lesions were delineated and one hundred radiomic features were extracted. All radiomics features were categorized based on coefficient of variation (COV). RESULTS: Forty seven percent features showed COV ≤ 5% and 10% of which showed COV > 20%. All geometry based, 44% and 41% of intensity based and texture based features were found as robust respectively. In regard to matrix size, 56% and 6% of all features were found non-robust (COV > 20%) and robust (COV ≤ 5%) respectively. CONCLUSIONS: Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent, and different settings have different effects on different features. Radiomic features with low COV can be considered as good candidates for reproducible tumour quantification in multi-center studies. KEY POINTS: • PET/CT image radiomics is a quantitative approach assessing different aspects of tumour uptake. • Radiomic features robustness is an important issue over different image reconstruction settings. • Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent. • Robust radiomic features can be considered as good candidates for tumour quantification.

Implementation of absolute quantification in small-animal SPECT imaging: Phantom and animal studies.

PURPOSE: Presence of photon attenuation severely challenges quantitative accuracy in single-photon emission computed tomography (SPECT) imaging. Subsequently, various attenuation correction methods have been developed to compensate for this degradation. The present study aims to implement an attenuation correction method and then to evaluate quantification accuracy of attenuation correction in small-animal SPECT imaging. METHODS: Images were reconstructed using an iterative reconstruction method based on the maximum-likelihood expectation maximization (MLEM) algorithm including resolution recovery. This was implemented in our designed dedicated small-animal SPECT (HiReSPECT) system. For accurate quantification, the voxel values were converted to activity concentration via a calculated calibration factor. An attenuation correction algorithm was developed based on the first-order Chang's method. Both phantom study and experimental measurements with four rats were used in order to validate the proposed method. RESULTS: The phantom experiments showed that the error of -15.5% in the estimation of activity concentration in a uniform region was reduced to +5.1% when attenuation correction was applied. For in vivo studies, the average quantitative error of -22.8 ± 6.3% (ranging from -31.2% to -14.8%) in the uncorrected images was reduced to +3.5 ± 6.7% (ranging from -6.7 to +9.8%) after applying attenuation correction. CONCLUSION: The results indicate that the proposed attenuation correction algorithm based on the first-order Chang's method, as implemented in our dedicated small-animal SPECT system, significantly improves accuracy of the quantitative analysis as well as the absolute quantification.