Robustness of radiomic features in healthy abdominal parenchyma of patients with repeated examinations on dual-layer dual-energy CT.

OBJECTIVES: Robustness of radiomic features in physiological tissue is an important prerequisite for quantitative analysis of tumor biology and response assessment. In contrast to previous studies which focused on different tumors with mostly short scan-re-scan intervals, this study aimed to evaluate the robustness of radiomic features in cancer-free patients and over a clinically encountered inter-scan interval. MATERIALS AND METHODS: Patients without visible tumor burden who underwent at least two portal-venous phase dual energy CT examinations of the abdomen between May 2016 and January 2020 were included, while macroscopic tumor burden was excluded based upon follow-up imaging for all patients (≥3 months). Further, patients were excluded if no follow-up imaging was available, or if the CT protocol showed deviations between repeated examinations. Circular regions of interest were placed and proofread by two board-certified radiologists (4 years and 5 years experience) within the liver (segments 3 and 6), the psoas muscle (left and right), the pancreatic head, and the spleen to obtain radiomic features from normal-appearing organ parenchyma using PyRadiomics. Radiomic feature robustness was tested using the concordance correlation coefficient with a threshold of 0.75 considered indicative for deeming a feature robust. RESULTS: In total, 160 patients with 480 repeated abdominal CT examinations (range: 2-4 per patient) were retrospectively included in this single-center, IRB-approved study. Considering all organs and feature categories, only 4.58 % (25/546) of all features were robust with the highest rate being found in the first order feature category (20.37 %, 22/108). Other feature categories (grey level co-occurrence matrix, grey level dependence matrix, grey level run length matrix, grey level size zone matrix, and neighborhood gray-tone difference matrix) yielded an overall low percentage of robust features (range: 0.00 %-1.19 %). A subgroup analysis revealed the reconstructed field of view and the X-ray tube current as determinants of feature robustness (significant differences in subgroups for all organs, p < 0.001) as well as the size of the region of interest (no significant difference for the pancreatic head with p = 0.135, significant difference with p < 0.001 for all other organs). CONCLUSION: Radiomic feature robustness obtained from cancer-free subjects with repeated examinations using a consistent protocol and CT scanner was limited, with first order features yielding the highest proportion of robust features.

Dual-layer dual-energy CT-derived pulmonary perfusion for the differentiation of acute pulmonary embolism and chronic thromboembolic pulmonary hypertension.

OBJECTIVES: To evaluate dual-layer dual-energy computed tomography (dlDECT)-derived pulmonary perfusion maps for differentiation between acute pulmonary embolism (PE) and chronic thromboembolic pulmonary hypertension (CTEPH). METHODS: This retrospective study included 131 patients (57 patients with acute PE, 52 CTEPH, 22 controls), who underwent CT pulmonary angiography on a dlDECT. Normal and malperfused areas of lung parenchyma were semiautomatically contoured using iodine density overlay (IDO) maps. First-order histogram features of normal and malperfused lung tissue were extracted. Iodine density (ID) was normalized to the mean pulmonary artery (MPA) and the left atrium (LA). Furthermore, morphological imaging features for both acute and chronic PE, as well as the combination of histogram and morphological imaging features, were evaluated. RESULTS: In acute PE, normal perfused lung areas showed a higher mean and peak iodine uptake normalized to the MPA than in CTEPH (both p < 0.001). After normalizing mean ID in perfusion defects to the LA, patients with acute PE had a reduced average perfusion (IDmean,LA) compared to both CTEPH patients and controls (p < 0.001 for both). IDmean,LA allowed for a differentiation between acute PE and CTEPH with moderate accuracy (AUC: 0.72, sensitivity 74%, specificity 64%), resulting in a PPV and NPV for CTEPH of 64% and 70%. Combining IDmean,LA in the malperfused areas with the diameter of the MPA (MPAdia) significantly increased its ability to differentiate between acute PE and CTEPH (sole MPAdia: AUC: 0.76, 95%-CI: 0.68-0.85 vs. MPAdia + 256.3 * IDmean,LA - 40.0: AUC: 0.82, 95%-CI: 0.74-0.90, p = 0.04). CONCLUSION: dlDECT enables quantification and characterization of pulmonary perfusion patterns in acute PE and CTEPH. Although these lack precision when used as a standalone criterion, when combined with morphological CT parameters, they hold potential to enhance differentiation between the two diseases. CLINICAL RELEVANCE STATEMENT: Differentiating between acute PE and CTEPH based on morphological CT parameters is challenging, often leading to a delay in CTEPH diagnosis. By revealing distinct pulmonary perfusion patterns in both entities, dlDECT may facilitate timely diagnosis of CTEPH, ultimately improving clinical management. KEY POINTS: • Morphological imaging parameters derived from CT pulmonary angiography to distinguish between acute pulmonary embolism and chronic thromboembolic pulmonary hypertension lack diagnostic accuracy. • Dual-layer dual-energy CT reveals different pulmonary perfusion patterns between acute pulmonary embolism and chronic thromboembolic pulmonary hypertension. • The identified parameters yield potential to enable more timely identification of patients with chronic thromboembolic pulmonary hypertension.

Deep-Learning-Based Image Denoising in Imaging of Urolithiasis: Assessment of Image Quality and Comparison to State-of-the-Art Iterative Reconstructions.

This study aimed to compare the image quality and diagnostic accuracy of deep-learning-based image denoising reconstructions (DLIDs) to established iterative reconstructed algorithms in low-dose computed tomography (LDCT) of patients with suspected urolithiasis. LDCTs (CTDIvol, 2 mGy) of 76 patients (age: 40.3 ± 5.2 years, M/W: 51/25) with suspected urolithiasis were retrospectively included. Filtered-back projection (FBP), hybrid iterative and model-based iterative reconstruction (HIR/MBIR, respectively) were reconstructed. FBP images were processed using a Food and Drug Administration (FDA)-approved DLID. ROIs were placed in renal parenchyma, fat, muscle and urinary bladder. Signal- and contrast-to-noise ratios (SNR/CNR, respectively) were calculated. Two radiologists evaluated image quality on five-point Likert scales and urinary stones. The results showed a progressive decrease in image noise from FBP, HIR and DLID to MBIR with significant differences between each method (p < 0.05). SNR and CNR were comparable between MBIR and DLID, while it was significantly lower in HIR followed by FBP (e.g., SNR: 1.5 ± 0.3; 1.4 ± 0.4; 1.0 ± 0.3; 0.7 ± 0.2, p < 0.05). Subjective analysis confirmed best image quality in MBIR, followed by DLID and HIR, both being superior to FBP (p < 0.05). Diagnostic accuracy for urinary stone detection was best using MBIR (0.94), lowest using FBP (0.84) and comparable between DLID (0.90) and HIR (0.90). Stone size measurements were consistent between all reconstructions and showed excellent correlation (r2 = 0.958-0.975). In conclusion, MBIR yielded the highest image quality and diagnostic accuracy, with DLID producing better results than HIR and FBP in image quality and matching HIR in diagnostic precision.

Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network.

BACKGROUND: In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations. METHODS: In this IRB-approved retrospective single-center study, 187 CECT examinations of the head and neck region from patients with various primary diseases were collected from our local database, and 3656 LNs (19.5 ± 14.9 LNs/CECT, mean ± standard deviation) with a short-axis diameter (SAD) ≥ 5 mm were segmented manually by expert physicians. With these data, we trained an independent fully convolutional neural network based on 3D foveal patches. Testing was performed on 30 independent CECTs with 925 segmented LNs with an SAD ≥ 5 mm. RESULTS: In total, 4,581 LNs were segmented in 217 CECTs. The model achieved an average localization rate (LR), i.e., percentage of localized LNs/CECT, of 78.0% in the validation dataset. In the test dataset, average LR was 81.1% with a mean Dice coefficient of 0.71. For enlarged LNs with a SAD ≥ 10 mm, LR was 96.2%. In the test dataset, the false-positive rate was 2.4 LNs/CECT. CONCLUSIONS: Our trained AI model demonstrated a good overall performance in the consistent automatic localization and 3D segmentation of physiological and metastatic cervical LNs with a SAD ≥ 5 mm on CECTs. This could aid clinical localization and automatic 3D segmentation, which can benefit clinical care and radiomics research. RELEVANCE STATEMENT: Our AI model is a time-saving tool for 3D segmentation of cervical lymph nodes on contrast-enhanced CT scans and serves as a solid base for N staging in clinical practice and further radiomics research. KEY POINTS: • Determination of N status in TNM staging is essential for therapy planning in oncology. • Segmenting cervical lymph nodes manually is highly time-consuming in clinical practice. • Our model provides a robust, automated 3D segmentation of cervical lymph nodes. • It achieves a high accuracy for localization especially of enlarged lymph nodes. • These segmentations should assist clinical care and radiomics research.

Voxel-Wise Medical Imaging Transformation and Adaption Based on CycleGAN and Score-Based Diffusion.

Supervised methods, such as those utilized in classification, prediction, and segmentation tasks for medical images, experience a decline in performance when the training and testing datasets violate the i.i.d (independent and identically distributed) assumption. Hence we adopted the CycleGAN(Generative Adversarial Networks) method to cycle training the CT(Computer Tomography) data from different terminals/manufacturers, which aims to eliminate the distribution shift from diverse data terminals. But due to the model collapse problem of the GAN-based model, the images we generated suffer serious radiology artifacts. To eliminate the boundary marks and artifacts, we adopted a score-based generative model to refine the images voxel-wisely. This novel combination of two generative models makes the transformation between diverse data providers to a higher fidelity level without sacrificing any significant features. In future works, we will evaluate the original datasets and generative datasets by experimenting with a broader range of supervised methods.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives.

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Spectral Detector CT-Derived Pulmonary Perfusion Maps and Pulmonary Parenchyma Characteristics for the Semiautomated Classification of Pulmonary Hypertension.

Objectives: To evaluate the usefulness of spectral detector CT (SDCT)-derived pulmonary perfusion maps and pulmonary parenchyma characteristics for the semiautomated classification of pulmonary hypertension (PH). Methods: A total of 162 consecutive patients with right heart catheter (RHC)-proven PH of different aetiologies as defined by the current ESC/ERS guidelines who underwent CT pulmonary angiography (CTPA) on SDCT and 20 patients with an invasive rule-out of PH were included in this retrospective study. Semiautomatic lung segmentation into normal and malperfused areas based on iodine density (ID) as well as automatic, virtual non-contrast-based emphysema quantification were performed. Corresponding volumes, histogram features and the ID SkewnessPerfDef-Emphysema-Index (δ-index) accounting for the ratio of ID distribution in malperfused lung areas and the proportion of emphysematous lung parenchyma were computed and compared between groups. Results: Patients with PH showed a significantly greater extent of malperfused lung areas as well as stronger and more homogenous perfusion defects. In group 3 and 4 patients, ID skewness revealed a significantly more homogenous ID distribution in perfusion defects than in all other subgroups. The δ-index allowed for further subclassification of subgroups 3 and 4 (p < 0.001), identifying patients with chronic thromboembolic PH (CTEPH, subgroup 4) with high accuracy (AUC: 0.92, 95%-CI, 0.85-0.99). Conclusion: Abnormal pulmonary perfusion in PH can be detected and quantified by semiautomated SDCT-based pulmonary perfusion maps. ID skewness in malperfused lung areas, and the δ-index allow for a classification of PH subgroups, identifying groups 3 and 4 patients with high accuracy, independent of reader expertise.

Automated Kidney and Liver Segmentation in MR Images in Patients with Autosomal Dominant Polycystic Kidney Disease: A Multicenter Study.

Background: Imaging-based total kidney volume (TKV) and total liver volume (TLV) are major prognostic factors in autosomal dominant polycystic kidney disease (ADPKD) and end points for clinical trials. However, volumetry is time consuming and reader dependent in clinical practice. Our aim was to develop a fully automated method for joint kidney and liver segmentation in magnetic resonance imaging (MRI) and to evaluate its performance in a multisequence, multicenter setting. Methods: The convolutional neural network was trained on a large multicenter dataset consisting of 992 MRI scans of 327 patients. Manual segmentation delivered ground-truth labels. The model's performance was evaluated in a separate test dataset of 93 patients (350 MRI scans) as well as a heterogeneous external dataset of 831 MRI scans from 323 patients. Results: The segmentation model yielded excellent performance, achieving a median per study Dice coefficient of 0.92-0.97 for the kidneys and 0.96 for the liver. Automatically computed TKV correlated highly with manual measurements (intraclass correlation coefficient [ICC]: 0.996-0.999) with low bias and high precision (-0.2%±4% for axial images and 0.5%±4% for coronal images). TLV estimation showed an ICC of 0.999 and bias/precision of -0.5%±3%. For the external dataset, the automated TKV demonstrated bias and precision of -1%±7%. Conclusions: Our deep learning model enabled accurate segmentation of kidneys and liver and objective assessment of TKV and TLV. Importantly, this approach was validated with axial and coronal MRI scans from 40 different scanners, making implementation in clinical routine care feasible.Clinical Trial registry name and registration number: The German ADPKD Tolvaptan Treatment Registry (AD[H]PKD), NCT02497521.

Automated mapping and N-Staging of thoracic lymph nodes in contrast-enhanced CT scans of the chest using a fully convolutional neural network.

PURPOSE: To develop a deep-learning (DL)-based approach for thoracic lymph node (LN) mapping based on their anatomical location. METHOD: The training-and validation-dataset included 89 contrast-enhanced computed tomography (CT) scans of the chest. 4201 LNs were semi-automatically segmented and then assigned to LN levels according to their anatomical location. The LN level classification task was addressed by a multi-class segmentation procedure using a fully convolutional neural network. Mapping was performed by firstly determining potential level affiliation for each voxel and then performing majority voting over all voxels belonging to each LN. Mean classification accuracies on the validation data were calculated separately for each level and overall Top-1, Top-2 and Top-3 scores were determined, where a Top-X score describes how often the annotated class was within the top-X predictions. To demonstrate the clinical applicability of our model, we tested its N-staging capabilities in a simulated clinical use case scenario assuming a patient diseased with lung cancer. RESULTS: The artificial intelligence(AI)-based assignment revealed mean classification accuracies of 86.36 % (Top-1), 94.48 % (Top-2) and 96.10 % (Top-3). Best accuracies were achieved for LNs in the subcarinal level 7 (98.31 %) and axillary region (98.74 %). The highest misclassification rates were observed among LNs in adjacent levels. The proof-of-principle application in a simulated clinical use case scenario for automated tumor N-staging showed a mean classification accuracy of up to 96.14 % (Top-1). CONCLUSIONS: The proposed AI approach for automatic classification of LN levels in chest CT as well as the proof-of-principle-experiment for automatic N-staging, revealed promising results, warranting large-scale validation for clinical application.

A Linearized Fit Model for Robust Shape Parameterization of FET-PET TACs.

The kinetic analysis of [Formula: see text]-FET time-activity curves (TAC) can provide valuable diagnostic information in glioma patients. The analysis is most often limited to the average TAC over a large tissue volume and is normally assessed by visual inspection or by evaluating the time-to-peak and linear slope during the late uptake phase. Here, we derived and validated a linearized model for TACs of [Formula: see text]-FET in dynamic PET scans. Emphasis was put on the robustness of the numerical parameters and how reliably automatic voxel-wise analysis of TAC kinetics was possible. The diagnostic performance of the extracted shape parameters for the discrimination between isocitrate dehydrogenase (IDH) wildtype (wt) and IDH-mutant (mut) glioma was assessed by receiver-operating characteristic in a group of 33 adult glioma patients. A high agreement between the adjusted model and measured TACs could be obtained and relative, estimated parameter uncertainties were small. The best differentiation between IDH-wt and IDH-mut gliomas was achieved with the linearized model fitted to the averaged TAC values from dynamic FET PET data in the time interval 4-50 min p.i.. When limiting the acquisition time to 20-40 min p.i., classification accuracy was only slightly lower (-3%) and was comparable to classification based on linear fits in this time interval. Voxel-wise fitting was possible within a computation time ≈ 1 min per image slice. Parameter uncertainties smaller than 80% for all fits with the linearized model were achieved. The agreement of best-fit parameters when comparing voxel-wise fits and fits of averaged TACs was very high (p < 0.001).

Texture analysis of iodine maps and conventional images for k-nearest neighbor classification of benign and metastatic lung nodules.

BACKGROUND: The purpose of this study was to analyze if the use of texture analysis on spectral detector CT (SDCT)-derived iodine maps (IM) in addition to conventional images (CI) improves lung nodule differentiation, when being applied to a k-nearest neighbor (KNN) classifier. METHODS: 183 cancer patients who underwent contrast-enhanced, venous phase SDCT of the chest were included: 85 patients with 146 benign lung nodules (BLN) confirmed by either prior/follow-up CT or histopathology and 98 patients with 425 lung metastases (LM) verified by histopathology, 18F-FDG-PET-CT or unequivocal change during treatment. Semi-automatic 3D segmentation of BLN/LM was performed, and volumetric HU attenuation and iodine concentration were acquired. For conventional images and iodine maps, average, standard deviation, entropy, kurtosis, mean of the positive pixels (MPP), skewness, uniformity and uniformity of the positive pixels (UPP) within the volumes of interests were calculated. All acquired parameters were transferred to a KNN classifier. RESULTS: Differentiation between BLN and LM was most accurate, when using all CI-derived features combined with the most significant IM-derived feature, entropy (Accuracy:0.87; F1/Dice:0.92). However, differentiation accuracy based on the 4 most powerful CI-derived features performed only slightly inferior (Accuracy:0.84; F1/Dice:0.89, p=0.125). Mono-parametric lung nodule differentiation based on either feature alone (i.e. attenuation or iodine concentration) was poor (AUC=0.65, 0.58, respectively). CONCLUSIONS: First-order texture feature analysis of contrast-enhanced staging SDCT scans of the chest yield accurate differentiation between benign and metastatic lung nodules. In our study cohort, the most powerful iodine map-derived feature slightly, yet insignificantly increased classification accuracy  compared to classification based on conventional image features only.

Prediction of anemia on enhanced computed tomography of the thorax using virtual non-contrast reconstructions.

ABSTRACT: To determine if anemia can be predicted on enhanced computed tomography (CT) examinations of the thorax using virtual non-contrast (VNC) images, in order to support clinicians especially in diagnosing primary asymptomatic patients in daily routine.In this monocentric study, 100 consecutive patients (50 with proven anemia), who underwent a contrast-enhanced CT examination of the thorax due to various indications were included. Attenuation was measured in the descending thoracic aorta, the intraventricular septum, and the left ventricle cavity both in the conventional contrast-enhanced and in the VNC images.Two experienced radiologists annotated the delineation of a dense interventricular septum or a hyperattenuating aortic wall sign for all patients.Hemoglobin levels were then correlated with the measured attenuation values, as well as the visualization of the aortic wall or interventricular septum.Good correlation was shown between hemoglobin levels and CT attenuation values of the left ventricular cavity (r = .59), aorta (r = .56), and ratio between left ventricular cavity and the intraventricular septum (r = .57). Receiver operating characteristic curve revealed ≤ 36.5 hounsfield units (left ventricular cavity) as the threshold for diagnosing anemia. Predicting anemia by visualization of a hyperattenuating aortic wall or a dense interventricular septum yielded a specificity of 98% and 92%, respectively.Predicting anemia on enhanced CT examinations using VNC is feasible. A threshold value of ≤ 36.5 hounsfield units (left ventricular cavity) best defines anemia. Aortic wall or interventricular septum visualization on VNC is a specific anemia indicator.

Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep Learning.

BACKGROUND: Precise volumetric assessment of brain tumors is relevant for treatment planning and monitoring. However, manual segmentations are time-consuming and impeded by intra- and interrater variabilities. PURPOSE: To investigate the performance of a deep-learning model (DLM) to automatically detect and segment primary central nervous system lymphoma (PCNSL) on clinical MRI. STUDY TYPE: Retrospective. POPULATION: Sixty-nine scans (at initial and/or follow-up imaging) from 43 patients with PCNSL referred for clinical MRI tumor assessment. FIELD STRENGTH/SEQUENCE: T1 -/T2 -weighted, T1 -weighted contrast-enhanced (T1 CE), and FLAIR at 1.0, 1.5, and 3.0T from different vendors and study centers. ASSESSMENT: Fully automated voxelwise segmentation of tumor components was performed using a 3D convolutional neural network (DeepMedic) trained on gliomas (n = 220). DLM segmentations were compared to manual segmentations performed in a 3D voxelwise manner by two readers (radiologist and neurosurgeon; consensus reading) from T1 CE and FLAIR, which served as the reference standard. STATISTICAL TESTS: Dice similarity coefficient (DSC) for comparison of spatial overlap with the reference standard, Pearson's correlation coefficient (r) to assess the relationship between volumetric measurements of segmentations, and Wilcoxon rank-sum test for comparison of DSCs obtained in initial and follow-up imaging. RESULTS: The DLM detected 66 of 69 PCNSL, representing a sensitivity of 95.7%. Compared to the reference standard, DLM achieved good spatial overlap for total tumor volume (TTV, union of tumor volume in T1 CE and FLAIR; average size 77.16 ± 62.4 cm3 , median DSC: 0.76) and tumor core (contrast enhancing tumor in T1 CE; average size: 11.67 ± 13.88 cm3 , median DSC: 0.73). High volumetric correlation between automated and manual segmentations was observed (TTV: r = 0.88, P < 0.0001; core: r = 0.86, P < 0.0001). Performance of automated segmentations was comparable between pretreatment and follow-up scans without significant differences (TTV: P = 0.242, core: P = 0.177). DATA CONCLUSION: In clinical MRI scans, a DLM initially trained on gliomas provides segmentation of PCNSL comparable to manual segmentation, despite its complex and multifaceted appearance. Segmentation performance was high in both initial and follow-up scans, suggesting its potential for application in longitudinal tumor imaging. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Are left atrial diverticula and left-sided septal pouches relevant additional findings in cardiac CT? Correlation between left atrial outpouching structures and ischemic brain alterations.

PURPOSE: To evaluate the correlation between left atrial diverticula (LAD) and left-sided septal pouches (LSSP) with ischemic brain alterations in MRI. METHODS: A retrospective analysis of 174 patients who received both, a dedicated cardiac CT angiography (CCTA) and a brain MRI examination was performed. Two radiologists independently reviewed all examinations for the presence of LAD and LSSP as well as ischemic alterations of the brain. Subsequently, the correlation between these cardiac and cerebral findings as well as to other potentially related risk factors was assessed. RESULTS: 71 LAD (total prevalence 41%) and 65 LSSP (total prevalence 37%) were identified in 174 patients. Combined prevalence was 10%. Ischemic brain alterations were found in patients with a LAD in 42.3% (30/71) and with a LSSP in 64.6% (42/65). Patients without any anatomical variant in the left atrium showed ischemic brain alterations in 39.4% (26/66). The presence of a LSSP was associated with an increased risk for ischemic brain alterations in multivariate logistic regression analysis after adjusting for other risk factors (OR = 3.57, 95% CI = 0.51-2.09, p <  .01). CONCLUSION: In our study cohort LAD and LSSP are highly prevalent anatomical structures within the left atrium. Patients with LSSP showed an approximated 3.5-fold higher probability for ischemic brain alterations. Therefore, LSSP should be considered as a potential risk factor for cardioembolic strokes and its presence should be stated in cardiac CT reports.

Artificial intelligence abstracts from the European Congress of Radiology: analysis of topics and compliance with the STARD for abstracts checklist.

OBJECTIVES: To analyze all artificial intelligence abstracts presented at the European Congress of Radiology (ECR) 2019 with regard to their topics and their adherence to the Standards for Reporting Diagnostic accuracy studies (STARD) checklist. METHODS: A total of 184 abstracts were analyzed with regard to adherence to the STARD criteria for abstracts as well as the reported modality, body region, pathology, and use cases. RESULTS: Major topics of artificial intelligence abstracts were classification tasks in the abdomen, chest, and brain with CT being the most commonly used modality. Out of the 10 STARD for abstract criteria analyzed in the present study, on average, 5.32 (SD = 1.38) were reported by the 184 abstracts. Specifically, the highest adherence with STARD for abstracts was found for general interpretation of results of abstracts (100.0%, 184 of 184), clear study objectives (99.5%, 183 of 184), and estimates of diagnostic accuracy (96.2%, 177 of 184). The lowest STARD adherence was found for eligibility criteria for participants (9.2%, 17 of 184), type of study series (13.6%, 25 of 184), and implications for practice (20.7%, 44 of 184). There was no significant difference in the number of reported STARD criteria between abstracts accepted for oral presentation (M = 5.35, SD = 1.31) and abstracts accepted for the electronic poster session (M = 5.39, SD = 1.45) (p = .86). CONCLUSIONS: The adherence with STARD for abstract was low, indicating that providing authors with the related checklist may increase the quality of abstracts.

Scatter Correction Based on GPU-Accelerated Full Monte Carlo Simulation for Brain PET/MRI.

Accurate scatter correction is essential for qualitative and quantitative PET imaging. Until now, scatter correction based on Monte Carlo simulation (MCS) has been recognized as the most accurate method of scatter correction for PET. However, the major disadvantage of MCS is its long computational time, which makes it unfeasible for clinical usage. Meanwhile, single scatter simulation (SSS) is the most widely used method for scatter correction. Nevertheless, SSS has the disadvantage of limited robustness for dynamic measurements and for the measurement of large objects. In this work, a newly developed implementation of MCS using graphics processing unit (GPU) acceleration is employed, allowing full MCS-based scatter correction in clinical 3D brain PET imaging. Starting from the generation of annihilation photons to their detection in the simulated PET scanner, all relevant physical interactions and transport phenomena of the photons were simulated on GPUs. This resulted in an expected distribution of scattered events, which was subsequently used to correct the measured emission data. The accuracy of the approach was validated with simulations using GATE (Geant4 Application for Tomography Emission), and its performance was compared to SSS. The comparison of the computation time between a GPU and a single-threaded CPU showed an acceleration factor of 776 for a voxelized brain phantom study. The speedup of the MCS implemented on the GPU represents a major step toward the application of the more accurate MCS-based scatter correction for PET imaging in clinical routine.

Resolution modeling in projection space using a factorized multi-block detector response function for PET image reconstruction.

Positron emission tomography (PET) images usually suffer from limited resolution and statistical uncertainties. However, a technique known as resolution modeling (RM) can be used to improve image quality by accurately modeling the system's detection process within the iterative reconstruction. In this study, we present an accurate RM method in projection space based on a simulated multi-block detector response function (DRF) and evaluate it on the Siemens hybrid MR-BrainPET system. The DRF is obtained using GATE simulations that consider nearly all the possible annihilation photons from the field-of-view (FOV). Intrinsically, the multi-block DRF allows the block crosstalk to be modeled. The RM blurring kernel is further generated by factorizing the blurring matrix of one line-of-response (LOR) into two independent detector responses, which can then be addressed with the DRF. Such a kernel is shift-variant in 4D projection space without any distance or angle compression, and is integrated into the image reconstruction for the BrainPET insert with single instruction multiple data (SIMD) and multi-thread support. Evaluation of simulations and measured data demonstrate that the reconstruction with RM yields significantly improved resolutions and reduced mean squared error (MSE) values at different locations of the FOV, compared with reconstruction without RM. Furthermore, the shift-variant RM kernel models the varying blurring intensity for different LORs due to the depth-of-interaction (DOI) dependencies, thus avoiding severe edge artifacts in the images. Additionally, compared to RM in single-block mode, the multi-block mode shows significantly improved resolution and edge recovery at locations beyond 10 cm from the center of BrainPET insert in the transverse plane. However, the differences have been observed to be low for patient data between single-block and multi-block mode RM, due to the brain size and location as well as the geometry of the BrainPET insert. In conclusion, the RM method proposed in this study can yield better reconstructed images in terms of resolution and MSE value, compared to conventional reconstruction without RM.

Dynamic susceptibility contrast parametric imaging using accelerated dual-contrast echo planar imaging with keyhole.

BACKGROUND: Echo planar imaging (EPI) is one of the methods of choice in dynamic susceptibility contrast MRI (DSC-MRI) because it provides a sufficient temporal resolution. However, the relatively long readout duration of EPI often imposes limitations on increased spatial coverage or the use of multiple contrasts. PURPOSE: To develop a DSC-MRI method using EPIK (EPI with keyhole) to provide dual-contrast (TE1 and TE2 ) information with a higher spatial coverage than EPI. To compare results from the community-standard EPI method and the proposed EPIK method. STUDY TYPE: Prospective. SUBJECTS: One healthy subject and 17 brain tumor patients. FIELD STRENGTH/SEQUENCE: 3 T/accelerated EPI and dual-contrast EPIK sequences. ASSESSMENT: After an initial evaluation using healthy in vivo images, the use of the proposed method for DSC-MRI was verified with brain tumor patients. The parametric images (eg, CBF and CBV) and arterial input function (AIF), obtained from both the EPI and EPIK, were compared. STATISTICAL TESTS: The ratio of AIF peak height of the proposed method to that of EPI was computed. The ratio computation was also performed for the time-to-peak (TTP) in the AIF curves. From the obtained CBF and CBV maps, the tumor-to-brain (TBR) ratio was also calculated for each imaging method and the results were compared. RESULTS: For the same temporal resolution (1.5 sec), EPIK yielded dual-contrast (TEs of 13/33 msec) with an increased spatial coverage (24 slices) and less geometric distortions than EPI; EPI provided single contrast (TE of 32 msec) with 20 slices. The obtained parametric values (eg, AIF peak, TTP, and TBR) had similar characteristics between EPI and the proposed method. DATA CONCLUSION: The dual-contrast data produced by EPIK in DSC-MRI allowed T1 -corrected parametric images without the need of second contrast injection and an enhanced estimation of the AIF. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:628-640.

PET attenuation correction for rigid MR Tx/Rx coils from 176Lu background activity.

One challenge for PET-MR hybrid imaging is the correction for attenuation of the 511 keV annihilation radiation by the required RF transmit and/or RF receive coils. Although there are strategies for building PET transparent Tx/Rx coils, such optimised coils still cause significant attenuation of the annihilation radiation leading to artefacts and biases in the reconstructed activity concentrations. We present a straightforward method to measure the attenuation of Tx/Rx coils in simultaneous MR-PET imaging based on the natural 176Lu background contained in the scintillator of the PET detector without the requirement of an external CT scanner or PET scanner with transmission source. The method was evaluated on a prototype 3T MR-BrainPET produced by Siemens Healthcare GmbH, both with phantom studies and with true emission images from patient/volunteer examinations. Furthermore, the count rate stability of the PET scanner and the x-ray properties of the Tx/Rx head coil were investigated. Even without energy extrapolation from the two dominant γ energies of 176Lu to 511 keV, the presented method for attenuation correction, based on the measurement of 176Lu background attenuation, shows slightly better performance than the coil attenuation correction currently used. The coil attenuation correction currently used is based on an external transmission scan with rotating 68Ge sources acquired on a Siemens ECAT HR + PET scanner. However, the main advantage of the presented approach is its straightforwardness and ready availability without the need for additional accessories.