Treatment of snoring using a non-invasive Er:YAG laser with SMOOTH mode (NightLase): a randomized controlled trial.

OBJECTIVES: The aim of this study was to assess safety and efficacy of a non-invasive 2940 nm Er:YAG treatment with SMOOTH mode in reducing snoring in adult patients and to compare its efficacy and safety to sham treatment in a randomized controlled trial setting.  METHODS: 40 primary snoring patients (≥ 18 year, AHI < 15e/h, BMI ≤ 30) were randomized to receive either 3 sessions NightLase or sham laser treatment. The main outcome measures were Snore Outcomes Survey (SOS), the Spouse/Bed Partner Survey (SBPS), a visual analogue snoring scale (bed partner) and a visual analogue pain scale. RESULTS: NightLase was well tolerated, no local anaesthesia was required (mean VAS pain score in NightLase group = 3.0 ± 1.7). No complications occurred. SOS, SBPS and VAS snoring scores improved in the NightLase group (33.7 ± 14.1 to 56.2 ± 16.1) (35.0 ± 17.1 to 61.5 ± 16.4) and (7.9 ± 2.0 to 4.7 ± 2.8) while no changing in the sham group (32.2 ± 14.5 vs 32.1 ± 13.0) (36.7 ± 12.1 vs 34.7 ± 12.7) (8.1 ± 1.7 vs 8.0 ± 1.6), respectively. CONCLUSIONS: NightLase is a safe, minimal invasive treatment that significantly reduced snoring compared to sham treatment.

Serially passaged, conditionally reprogrammed nasal epithelial cells as a model to study epithelial functions and SARS-CoV-2 infection.

Primary airway epithelial cells (pAECs) cultivated at air-liquid interface (ALI) conditions are widely used as surrogates for human in vivo epithelia. To extend the proliferative capacity and to enable serially passaging of pAECs, conditional reprogramming (cr) has been employed in recent years. However, ALI epithelia derived from cr cells often display functional changes with increasing passages. This highlights the need for thorough validation of the ALI cultures for the respective application. In our study, we evaluated the use of serially passaged cr nasal epithelial cells (crNECs) as a model to study SARS-CoV-2 infection and effects on ion and water transport. NECs were obtained from healthy individuals and cultivated as ALI epithelia derived from passages 1, 2, 3, and 5. We compared epithelial differentiation, ion and water transport, and infection with SARS-CoV-2 between passages. Our results show that epithelia maintained major differentiation characteristics and physiological ion and water transport properties through all passages. However, the frequency of ciliated cells, short circuit currents reflecting epithelial Na+ channel (ENaC) and cystic fibrosis transmembrane conductance regulator (CFTR) activity and expression of aquaporin 3 and 5 decreased gradually over passages. crNECs also expressed SARS-CoV-2 receptors angiotensin converting enzyme 2 (ACE2) and transmembrane serin2 protease 2 (TMPRSS2) across all passages and allowed SARS-CoV-2 replication in all passages. In summary, we provide evidence that passaged crNECs provide an appropriate model to study SARS-CoV-2 infection and also epithelial transport function when considering some limitations that we defined herein.

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort.

OBJECTIVES: To investigate machine learning classifiers and interpretable models using chest CT for detection of COVID-19 and differentiation from other pneumonias, interstitial lung disease (ILD) and normal CTs. METHODS: Our retrospective multi-institutional study obtained 2446 chest CTs from 16 institutions (including 1161 COVID-19 patients). Training/validation/testing cohorts included 1011/50/100 COVID-19, 388/16/33 ILD, 189/16/33 other pneumonias, and 559/17/34 normal (no pathologies) CTs. A metric-based approach for the classification of COVID-19 used interpretable features, relying on logistic regression and random forests. A deep learning-based classifier differentiated COVID-19 via 3D features extracted directly from CT attenuation and probability distribution of airspace opacities. RESULTS: Most discriminative features of COVID-19 are the percentage of airspace opacity and peripheral and basal predominant opacities, concordant with the typical characterization of COVID-19 in the literature. Unsupervised hierarchical clustering compares feature distribution across COVID-19 and control cohorts. The metrics-based classifier achieved AUC = 0.83, sensitivity = 0.74, and specificity = 0.79 versus respectively 0.93, 0.90, and 0.83 for the DL-based classifier. Most of ambiguity comes from non-COVID-19 pneumonia with manifestations that overlap with COVID-19, as well as mild COVID-19 cases. Non-COVID-19 classification performance is 91% for ILD, 64% for other pneumonias, and 94% for no pathologies, which demonstrates the robustness of our method against different compositions of control groups. CONCLUSIONS: Our new method accurately discriminates COVID-19 from other types of pneumonia, ILD, and CTs with no pathologies, using quantitative imaging features derived from chest CT, while balancing interpretability of results and classification performance and, therefore, may be useful to facilitate diagnosis of COVID-19. KEY POINTS: • Unsupervised clustering reveals the key tomographic features including percent airspace opacity and peripheral and basal opacities most typical of COVID-19 relative to control groups. • COVID-19-positive CTs were compared with COVID-19-negative chest CTs (including a balanced distribution of non-COVID-19 pneumonia, ILD, and no pathologies). Classification accuracies for COVID-19, pneumonia, ILD, and CT scans with no pathologies are respectively 90%, 64%, 91%, and 94%. • Our deep learning (DL)-based classification method demonstrates an AUC of 0.93 (sensitivity 90%, specificity 83%). Machine learning methods applied to quantitative chest CT metrics can therefore improve diagnostic accuracy in suspected COVID-19, particularly in resource-constrained environments.

Atri-U: assisted image analysis in routine cardiovascular magnetic resonance volumetry of the left atrium.

BACKGROUND: Artificial intelligence can assist in cardiac image interpretation. Here, we achieved a substantial reduction in time required to read a cardiovascular magnetic resonance (CMR) study to estimate left atrial volume without compromising accuracy or reliability. Rather than deploying a fully automatic black-box, we propose to incorporate the automated LA volumetry into a human-centric interactive image-analysis process. METHODS AND RESULTS: Atri-U, an automated data analysis pipeline for long-axis cardiac cine images, computes the atrial volume by: (i) detecting the end-systolic frame, (ii) outlining the endocardial borders of the LA, (iii) localizing the mitral annular hinge points and constructing the longitudinal atrial diameters, equivalent to the usual workup done by clinicians. In every step human interaction is possible, such that the results provided by the algorithm can be accepted, corrected, or re-done from scratch. Atri-U was trained and evaluated retrospectively on a sample of 300 patients and then applied to a consecutive clinical sample of 150 patients with various heart conditions. The agreement of the indexed LA volume between Atri-U and two experts was similar to the inter-rater agreement between clinicians (average overestimation of 0.8 mL/m2 with upper and lower limits of agreement of - 7.5 and 5.8 mL/m2, respectively). An expert cardiologist blinded to the origin of the annotations rated the outputs produced by Atri-U as acceptable in 97% of cases for step (i), 94% for step (ii) and 95% for step (iii), which was slightly lower than the acceptance rate of the outputs produced by a human expert radiologist in the same cases (92%, 100% and 100%, respectively). The assistance of Atri-U lead to an expected reduction in reading time of 66%-from 105 to 34 s, in our in-house clinical setting. CONCLUSIONS: Our proposal enables automated calculation of the maximum LA volume approaching human accuracy and precision. The optional user interaction is possible at each processing step. As such, the assisted process sped up the routine CMR workflow by providing accurate, precise, and validated measurement results.

Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm.

OBJECTIVES: To evaluate the performance of an AI-powered algorithm for the automatic detection of pulmonary embolism (PE) on chest computed tomography pulmonary angiograms (CTPAs) on a large dataset. METHODS: We retrospectively identified all CTPAs conducted at our institution in 2017 (n = 1499). Exams with clinical questions other than PE were excluded from the analysis (n = 34). The remaining exams were classified into positive (n = 232) and negative (n = 1233) for PE based on the final written reports, which defined the reference standard. The fully anonymized 1-mm series in soft tissue reconstruction served as input for the PE detection prototype algorithm that was based on a deep convolutional neural network comprising a Resnet architecture. It was trained and validated on 28,000 CTPAs acquired at other institutions. The result series were reviewed using a web-based feedback platform. Measures of diagnostic performance were calculated on a per patient and a per finding level. RESULTS: The algorithm correctly identified 215 of 232 exams positive for pulmonary embolism (sensitivity 92.7%; 95% confidence interval [CI] 88.3-95.5%) and 1178 of 1233 exams negative for pulmonary embolism (specificity 95.5%; 95% CI 94.2-96.6%). On a per finding level, 1174 of 1352 findings marked as embolus by the algorithm were true emboli. Most of the false positive findings were due to contrast agent-related flow artifacts, pulmonary veins, and lymph nodes. CONCLUSION: The AI prototype algorithm we tested has a high degree of diagnostic accuracy for the detection of PE on CTPAs. Sensitivity and specificity are balanced, which is a prerequisite for its clinical usefulness. KEY POINTS: • An AI-based prototype algorithm showed a high degree of diagnostic accuracy for the detection of pulmonary embolism on CTPAs. • It can therefore help clinicians to automatically prioritize exams with a high suspection of pulmonary embolism and serve as secondary reading tool. • By complementing traditional ways of worklist prioritization in radiology departments, this can speed up the diagnostic and therapeutic workup of patients with pulmonary embolism and help to avoid false negative calls.

Comprehensive metabolic and morphologic disease characterization in systemic sclerosis: initial results using combined positron emission tomography and magnetic resonance imaging.

BACKGROUND: The aim of this study was to evaluate the role of metabolic and morphologic parameters derived from simultaneous hybrid PET/MRI in correlation to clinical criteria for an image-based characterization of musculoskeletal, esophagus and lymph node involvement in systemic sclerosis (SSc). METHODS: Between November 2013 and May 2015, simultaneous whole-body hybrid PET/MRI was performed in 13 prospectively recruited patients with SSc. A mean dose of 241.3 MBq 2-deoxy-2-[18F]fluoro-D-glucose (FDG) was injected. SUVmean and SUVmax values were measured in the spinal bone marrow, spleen, joints, muscles, fasciae, mediastinal lymph nodes and esophagus. MRI abnormalities were scored as 0 (absent), 1 (moderate) and 2 (marked). In addition, organ and skin involvement were graded with clinical sum score (CSS) and modified Rodnan skin score (mRSS), respectively. RESULTS: Results indicate positive correlations between mRSS and fascial FDG-uptake values (fascia summed SUVmax ρ=0.67; fascia summed SUVmean ρ=0.66) that performed better than the MRI sum score (ρ=0.50). Fascial FDG-uptake is also useful in the differentiation between diffuse and limited SSc. Additionally, FDG-PET detected patients with active mediastinal lymphadenopathy and MRI proved to be useful for the delineation of esophagus involvement. CONCLUSIONS: Fascial FDG-uptake has a strong correlation with mRSS and can discriminate between limited and diffuse SSc. These results and the detection of active lymphadenopathy and esophagus involvement can identify patients with advanced scleroderma. Combined PET/MRI therefore provides complementary information on the complex pathophysiology and may integrate several imaging procedures in one.

Iodine concentration as a perfusion surrogate marker in oncology: Further elucidation of the underlying mechanisms using Volume Perfusion CT with 80 kVp.

OBJECTIVES: To assess the value of iodine concentration (IC) in computed tomography data acquired with 80 kVp, as a surrogate for perfusion imaging in hepatocellular carcinoma (HCC) and lymphoma by comparing iodine related attenuation (IRA) with quantitative Volume Perfusion CT (VPCT)-parameters. METHODS: VPCT-parameters were compared with intra-tumoral IC at 5 time points after the aortic peak enhancement (APE) with a temporal resolution of 3.5 sec in untreated 30 HCC and 30 lymphoma patients. RESULTS: Intra-tumoral perfusion parameters for HCC showed a blood flow (BF) of 52.7 ± 17.0 mL/100 mL/min, blood volume (BV) 12.6 ± 4.3 mL/100 mL, arterial liver perfusion (ALP) 44.4 ± 12.8 mL/100 mL/min. Lesion IC 7 sec after APE was 133.4 ± 57.3 mg/100 mL. Lymphoma showed a BF of 36.8 ± 13.4 mL/100 mL/min, BV of 8.8 ± 2.8 mL/100 mL and IC of 118.2 ± 64.5 mg/100 mL 3.5 sec after APE. Strongest correlations exist for VPCT-derived BF and ALP with IC in HCC 7 sec after APE (r = 0.71 and r = 0.84) and 3.5 sec after APE in lymphoma lesions (r = 0.77). Significant correlations are also present for BV (r = 0.60 and r = 0.65 for HCC and lymphoma, respectively). CONCLUSIONS: We identified a good, time-dependent agreement between VPCT-derived flow values and IC in HCC and lymphoma. Thus, CT-derived ICs 7 sec after APE in HCC and 3.5 sec in lymphoma may be used as surrogate imaging biomarkers for tumor perfusion with 80 kVp. KEY POINTS: • Iodine concentration derived from low kVp CT is regarded as perfusion surrogate • Correlation with Perfusion CT was performed to elucidate timing and histology dependencies • Highest correlation was present 7 sec after aortic peak enhancement in hepatocellular carcinoma • In lymphoma, highest correlation was calculated 3.5 sec after aortic peak enhancement • With these results, further optimization of Dual energy CT protocols is possible.

Image-derived biomarkers and multimodal imaging strategies for lung cancer management.

Non-small-cell lung cancer is the most common type of lung cancer and one of the leading causes of cancer-related death worldwide. For this reason, advances in diagnosis and treatment are urgently needed. With the introduction of new, highly innovative hybrid imaging technologies such as PET/CT, staging and therapy response monitoring in lung cancer patients have substantially evolved. In this review, we discuss the role of FDG PET/CT in the management of lung cancer patients and the importance of new emerging imaging technologies and radiotracer developments on the path to personalized medicine.

Midtreatment evaluation of lymphoma response to chemotherapy by volume perfusion computed tomography.

OBJECTIVE: The aim of this study was to search for chemotherapy-induced perfusion changes of diffuse large B-cell lymphoma, follicular lymphoma, and Hodgkin lymphoma at midtreatment versus baseline volume perfusion computed tomography (VPCT). METHODS: Forty-five consecutive patients with untreated diffuse large B-cell lymphoma, follicular lymphoma, and Hodgkin lymphoma received VPCT examinations of the tumor bulk at baseline and during chemotherapy (midtreatment). Blood flow (BF), blood volume (BV), and transit constant (K-trans) were determined. Treatment response was categorized according to the Cheson criteria into complete or partial remission and stable or relapsed/progressive disease. RESULTS: Midtreatment follow-up showed a reduction in BF, BV, and K-trans in all lymphoma subtypes compared with baseline. The reduction in BV was less pronounced in larger tumors. Notably, BF, BV, and K-trans decreased in the responders (complete remission/partial remission) when compared with the nonresponders (stable or relapsed/progressive disease). Less than 10% reduction in BF was shown to be the best VPCT criterion for the identification of nonresponse. CONCLUSIONS: Chemotherapy-induced perfusion changes in responders are recognizable at midtreatment VPCT.

Explanations for the heterogeneity of splenic enhancement derived from blood flow kinetic measurements using dynamic contrast-enhanced CT (DCE-CT).

BACKGROUND: The heterogeneity of splenic computed tomography (CT) attenuation is still not fully understood. A differentiation of these enhancement patterns and other conditions such as diffuse spleen infiltration can be challenging. PURPOSE: To understand the underlying physiological mechanisms of flow heterogeneity in normal and cirrhosis patients by quantifying perfusion parameters such as blood flow (BF), blood volume (BV), time to peak (TTP), flow extraction product (K(trans)), and mean transit time (MTT) using dynamic contrast-enhanced CT (DCE-CT). MATERIAL AND METHODS: Sixteen patients without splenic or hepatic disease and 16 patients with liver cirrhosis were retrospectively analyzed. Perfusion assessment included rapidly and slowly enhancing areas of the spleen, the entire splenic volume, as well as intra- and inter-observer reliability analysis. RESULTS: Significant differences between rapidly and slowly enhancing areas were found in controls for BF (109.8 mL/100 mL/min vs. 63.5 mL/100 mL/min), BV (37.1 mL/100 mL vs. 18.9 mL/100 mL), MTT (10.1 s vs. 13.0 s), but not for TTP (17.6 s vs. 18.6 s) and K(trans) (40.3 mL/100 mL/min vs. 44.7 mL/100 mL/min). In cirrhotic patients, differences proved significant for BF (90.5 mL/100 mL/min vs. 58.7 mL/100 mL/min), BV (17.5 mL/100 mL vs. 8.8 mL/100 mL), but not for K(trans) (60.9 mL/100 mL/min vs. 50.5 mL/100 mL/min), TTP (18.8 s vs. 20.0 s), and MTT (11.4 s vs. 14.2 s). Differences between rapidly enhancing areas in controls and cirrhotic patients reached a significant level for BV and K(trans). CONCLUSION: Preliminary results suggest that DCE-CT-based splenic perfusion measurements enable detection of different blood flow kinetics presumed to represent the complex and characteristic architecture of splenic vascular channels. It is the separate analysis of flow kinetics through the rapidly enhancing channels that allow for additional differentiation between controls and patients with portal hypertension.

Evaluating the biodistribution for [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET/CT with an inter- and intrapatient based analysis.

BACKGROUND: Liver uptake in [68Ga]Ga-PSMA-11 PET is used as an internal reference in addition to clinical parameters to select patients for [177Lu]Lu-PSMA-617 radioligand therapy (RLT). Due to increased demand, [68Ga]Ga-PSMA-11 was replaced by [18F]F-PSMA-1007, a more lipophilic tracer with different biodistribution and splenic uptake was suggested as a new internal reference. We compared the intra-patient tracer distribution between [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007. METHODS: Fifty patients who underwent PET examinations in two centers with both [18F]F-PSMA-1007 and [68Ga]Ga-PSMA-11 within one year were included. Mean standardized uptake values (SUVmean) were obtained for liver, spleen, salivary glands, blood pool, and bone. Primary tumor, local recurrence, lymph node, bone or visceral metastasis were also assessed for intra- and inter-individual comparison. RESULTS: Liver SUVmean was significantly higher with [18F]F-PSMA-1007 (11.7 ± 3.9) compared to [68Ga]Ga-PSMA-11 (5.4 ± 1.7, p < .05) as well as splenic SUVmean (11.2 ± 3.5 vs.8.1 ± 3.5, p < .05). The blood pool was comparable between the two scans. Malignant lesions did not show higher SUVmean on [18F]F-PSMA-1007. Intra-individual comparison of liver uptake between the two scans showed a linear association for liver uptake with SUVmean [68Ga]Ga-PSMA-11 = 0.33 x SUVmean [18F]F-PSMA-1007 + 1.52 (r = .78, p < .001). CONCLUSION: Comparing biodistribution of [68Ga]Ga and [18F]F tracers, liver uptake on [68Ga]Ga-PSMA-11 PET is the most robust internal reference value. Liver uptake of [18F]F-PSMA-1007 was significantly higher, but so was the splenic uptake. The strong intra-individual association of hepatic accumulation between the two scans may allow using of a conversion factor for [18F]F-PSMA-1007 as a basis for RLT selection.

Correlation between [¹8F]FDG PET/CT and volume perfusion CT in primary tumours and mediastinal lymph nodes of non-small-cell lung cancer.

PURPOSE: The aim of this study was to investigate correlations between glucose metabolism as determined by [(18)F]FDG PET/CT and tumour perfusion as quantified by volume perfusion CT in primary tumours and mediastinal lymph nodes (MLN) of patients with non-small-cell lung cancer (NSCLC). METHODS: Enrolled in the study were 17 patients with NSCLC. [(18)F]FDG uptake was quantified in terms of SUVmax and SUVavg. Blood flow (BF), blood volume (BV) and flow extraction product (K(trans)) were determined as perfusion parameters. The correlations between the perfusion parameters and [(18)F]FDG uptake values were subsequently evaluated. RESULTS: For the primary tumours, no correlations were found between perfusion parameters and [(18)F]FDG uptake. In MLN, there were negative correlations between BF and SUVavg (r = -0.383), BV and SUVavg (r = -0.406), and BV and SUVmax (r = -0.377), but not between BF and SUVmax, K(trans) and SUVavg, or K(trans) and SUVmax. Additionally, in MLN with SUVmax >2.5 there were negative correlations between BF and SUVavg (r = -0.510), BV and SUVavg (r = -0.390), BF and SUVmax (r = -0.536), as well as BV and SUVmax (r = -0.346). CONCLUSION: Perfusion and glucose metabolism seemed to be uncoupled in large primary tumours, but an inverse correlation was observed in MLN. This information may help improve therapy planning and response evaluation.

GPER1 links estrogens to centrosome amplification and chromosomal instability in human colon cells.

The role of the alternate G protein-coupled estrogen receptor 1 (GPER1) in colorectal cancer (CRC) development and progression is unclear, not least because of conflicting clinical and experimental evidence for pro- and anti-tumorigenic activities. Here, we show that low concentrations of the estrogenic GPER1 ligands, 17ß-estradiol, bisphenol A, and diethylstilbestrol cause the generation of lagging chromosomes in normal colon and CRC cell lines, which manifest in whole chromosomal instability and aneuploidy. Mechanistically, (xeno)estrogens triggered centrosome amplification by inducing centriole overduplication that leads to transient multipolar mitotic spindles, chromosome alignment defects, and mitotic laggards. Remarkably, we could demonstrate a significant role of estrogen-activated GPER1 in centrosome amplification and increased karyotype variability. Indeed, both gene-specific knockdown and inhibition of GPER1 effectively restored normal centrosome numbers and karyotype stability in cells exposed to 17ß-estradiol, bisphenol A, or diethylstilbestrol. Thus, our results reveal a novel link between estrogen-activated GPER1 and the induction of key CRC-prone lesions, supporting a pivotal role of the alternate estrogen receptor in colon neoplastic transformation and tumor progression.

Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT.

PURPOSE/OBJECTIVE: Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams. METHODS & MATERIALS: A cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters. RESULTS: We evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively). CONCLUSION: Re-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.

Reduction in Radiologist Interpretation Time of Serial CT and MR Imaging Findings with Deep Learning Identification of Relevant Priors, Series and Finding Locations.

RATIONALE AND OBJECTIVES: Finding comparison to relevant prior studies is a requisite component of the radiology workflow. The purpose of this study was to evaluate the impact of a deep learning tool simplifying this time-consuming task by automatically identifying and displaying the finding in relevant prior studies. MATERIALS AND METHODS: The algorithm pipeline used in this retrospective study, TimeLens (TL), is based on natural language processing and descriptor-based image-matching algorithms. The dataset used for testing comprised 3872 series of 246 radiology examinations from 75 patients (189 CTs, 95 MRIs). To ensure a comprehensive testing, five finding types frequently encountered in radiology practice were included: aortic aneurysm, intracranial aneurysm, kidney lesion, meningioma, and pulmonary nodule. After a standardized training session, nine radiologists from three university hospitals performed two reading sessions on a cloud-based evaluation platform resembling a standard RIS/PACS. The task was to measure the diameter of the finding-of-interest on two or more exams (a most recent and at least one prior exam): first without use of TL, and a second session at an interval of at least 21 days with the use of TL. All user actions were logged for each round, including time needed to measure the finding at all timepoints, number of mouse clicks, and mouse distance traveled. The effect of TL was evaluated in total, per finding type, per reader, per experience (resident vs. board-certified radiologist), and per modality. Mouse movement patterns were analyzed with heatmaps. To assess the effect of habituation to the cases, a third round of readings was performed without TL. RESULTS: Across scenarios, TL reduced the average time needed to assess a finding at all timepoints by 40.1% (107 vs. 65 seconds; p < 0.001). Largest accelerations were demonstrated for assessment of pulmonary nodules (-47.0%; p < 0.001). Less mouse clicks (-17.2%) were needed for finding evaluation with TL, and mouse distance traveled was reduced by 38.0%. Time needed to assess the findings increased from round 2 to round 3 (+27.6%; p < 0.001). Readers were able to measure a given finding in 94.4% of cases on the series initially proposed by TL as most relevant series for comparison. The heatmaps showed consistently simplified mouse movement patterns with TL. CONCLUSION: A deep learning tool significantly reduced both the amount of user interactions with the radiology image viewer and the time needed to assess findings of interest on cross-sectional imaging with relevant prior exams.

TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images.

Purpose: To present a deep learning segmentation model that can automatically and robustly segment all major anatomic structures on body CT images. Materials and Methods: In this retrospective study, 1204 CT examinations (from 2012, 2016, and 2020) were used to segment 104 anatomic structures (27 organs, 59 bones, 10 muscles, and eight vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiation therapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, abnormalities, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients to evaluate the model's performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age-dependent volume and attenuation changes. Results: The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major abnormalities. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 vs 0.871; P < .001). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (eg, age and aortic volume [rs = 0.64; P < .001]; age and mean attenuation of the autochthonous dorsal musculature [rs = -0.74; P < .001]). Conclusion: The developed model enables robust and accurate segmentation of 104 anatomic structures. The annotated dataset (https://doi.org/10.5281/zenodo.6802613) and toolkit (https://www.github.com/wasserth/TotalSegmentator) are publicly available.Keywords: CT, Segmentation, Neural Networks Supplemental material is available for this article. © RSNA, 2023See also commentary by Sebro and Mongan in this issue.

Pulmonary transit time of cardiovascular magnetic resonance perfusion scans for quantification of cardiopulmonary haemodynamics.

AIMS: Pulmonary transit time (PTT) is the time blood takes to pass from the right ventricle to the left ventricle via pulmonary circulation. We aimed to quantify PTT in routine cardiovascular magnetic resonance imaging perfusion sequences. PTT may help in the diagnostic assessment and characterization of patients with unclear dyspnoea or heart failure (HF). METHODS AND RESULTS: We evaluated routine stress perfusion cardiovascular magnetic resonance scans in 352 patients, including an assessment of PTT. Eighty-six of these patients also had simultaneous quantification of N-terminal pro-brain natriuretic peptide (NTproBNP). NT-proBNP is an established blood biomarker for quantifying ventricular filling pressure in patients with presumed HF. Manually assessed PTT demonstrated low inter-rater variability with a correlation between raters >0.98. PTT was obtained automatically and correctly in 266 patients using artificial intelligence. The median PTT of 182 patients with both left and right ventricular ejection fraction >50% amounted to 6.8 s (Pulmonary transit time: 5.9-7.9 s). PTT was significantly higher in patients with reduced left ventricular ejection fraction (<40%; P < 0.001) and right ventricular ejection fraction (<40%; P < 0.0001). The area under the receiver operating characteristics curve (AUC) of PTT for exclusion of HF (NT-proBNP <125 ng/L) was 0.73 (P < 0.001) with a specificity of 77% and sensitivity of 70%. The AUC of PTT for the inclusion of HF (NT-proBNP >600 ng/L) was 0.70 (P < 0.001) with a specificity of 78% and sensitivity of 61%. CONCLUSION: PTT as an easily, even automatically obtainable and robust non-invasive biomarker of haemodynamics might help in the evaluation of patients with dyspnoea and HF.

Pulmonary lesion assessment: comparison of whole-body hybrid MR/PET and PET/CT imaging--pilot study.

PURPOSE: To compare the performance of magnetic resonance (MR)/positron emission tomography (PET) imaging in the staging of lung cancer with that of PET/computed tomography (CT) as the reference standard and to compare the quantification accuracy of a new whole-body MR/PET system with corresponding PET/CT data sets. MATERIALS AND METHODS: Institutional review board approval and informed consent were obtained. Ten patients in whom bronchial carcinoma was proven or clinically suspected underwent clinically indicated fluorine 18 fluorodeoxyglucose (FDG) PET/CT and, immediately thereafter, whole-body MR/PET imaging with a new hybrid whole-body system (3.0-T MR imager with integrated PET system). Attenuation correction of MR/PET images was segmentation based with fat-water separation. Tumor-to-liver ratios were calculated and compared between PET/CT and MR/PET imaging. Tumor staging on the basis of the PET/CT and MR/PET studies was performed by two readers. Spearman rank correlation was used for comparison of data. RESULTS: MR/PET imaging provided diagnostic image quality in all patients, with good tumor delineation. Most lesions (nine of 10) showed pronounced FDG uptake. One lesion was morphologically suspicious for malignancy at CT and MR imaging but showed no FDG uptake. MR/PET imaging had higher mean tumor-to-liver ratios than did PET/CT (4.4 ± 2.0 [standard deviation] for PET/CT vs 8.0 ± 3.9 for MR/PET imaging). Significant correlation regarding the tumor-to-liver ratio was found between both imaging units (ρ = 0.93; P < .001). Identical TNM scores based on MR/PET and PET/CT data were found in seven of 10 patients. Differences in T and/or N staging occurred mainly owing to modality-inherent differences in lesion size measurement. CONCLUSION: MR/PET imaging of the lung is feasible and provides diagnostic image quality in the assessment of pulmonary masses. Similar lesion characterization and tumor stage were found in comparing PET/CT and MR/PET images in most patients.

Utilization of Artificial Intelligence-based Intracranial Hemorrhage Detection on Emergent Noncontrast CT Images in Clinical Workflow.

Authors implemented an artificial intelligence (AI)-based detection tool for intracranial hemorrhage (ICH) on noncontrast CT images into an emergent workflow, evaluated its diagnostic performance, and assessed clinical workflow metrics compared with pre-AI implementation. The finalized radiology report constituted the ground truth for the analysis, and CT examinations (n = 4450) before and after implementation were retrieved using various keywords for ICH. Diagnostic performance was assessed, and mean values with their respective 95% CIs were reported to compare workflow metrics (report turnaround time, communication time of a finding, consultation time of another specialty, and turnaround time in the emergency department). Although practicable diagnostic performance was observed for overall ICH detection with 93.0% diagnostic accuracy, 87.2% sensitivity, and 97.8% negative predictive value, the tool yielded lower detection rates for specific subtypes of ICH (eg, 69.2% [74 of 107] for subdural hemorrhage and 77.4% [24 of 31] for acute subarachnoid hemorrhage). Common false-positive findings included postoperative and postischemic defects (23.6%, 37 of 157), artifacts (19.7%, 31 of 157), and tumors (15.3%, 24 of 157). Although workflow metrics such as communicating a critical finding (70 minutes [95% CI: 54, 85] vs 63 minutes [95% CI: 55, 71]) were on average reduced after implementation, future efforts are necessary to streamline the workflow all along the workflow chain. It is crucial to define a clear framework and recognize limitations as AI tools are only as reliable as the environment in which they are deployed. Keywords: CT, CNS, Stroke, Diagnosis, Classification, Application Domain © RSNA, 2022.