Search

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.

ZusammenfassungKlinisches/methodisches ProblemDie differenzierte Beurteilung von Gasaustauschprozessen, Lungenzirkulation sowie die Erkennung struktureller Veränderungen sind wesentlich für die Therapie von Patienten mit Mukoviszidose (zystische Fibrose, CF). Klinische Lungenfunktionstests sind oft nicht hinreichend spezifisch sowie häufig nicht durchführbar.Radiologische StandardverfahrenStandardverfahren in der Lungendiagnostik sind die konventionell radiologische Thoraxbildgebung und die Computertomographie (CT) zur morphologischen Darstellung. In aktuellen Studien wird zur strukturellen Darstellung der Lunge zusätzlich die Magnetresonanztomographie (MRT) verwendet. Die funktionelle Bildgebung ist vorerst nur auf spezialisierte Zentren beschränkt.Methodische InnovationenZur Darstellung der Lungenventilation stehen die MRT mit hyperpolarisierten Gasen und die Fourier-Dekompositions/Matrix-Pencil-MRT (FD/MP-MRT) zur Verfügung. Zur Perfusionsbestimmung können u. a. die dynamische kontrastmittelverstärkte MRT (DCE-MRT) oder kontrastmittelfreie Methoden wie die FD-MRT angewendet werden.LeistungsfähigkeitDie funktionelle MRT erlaubt einen genaueren Einblick in die Pathophysiologie der Lungenfunktion auf regionaler Ebene. Vorteile gegenüber den röntgenbasierten Verfahren sind die fehlende Strahlenbelastung, die Vielzahl der über verschiedene Kontraste zugänglichen Parameter der Lungenfunktion sowie die gute Wiederholbarkeit.BewertungFunktionelle Messungen sind insbesondere zur frühzeitigen Erkennung von Lungenfunktionseinschränkungen unabdingbar. Ausreichende Erfahrungen in der klinischen Anwendung bei CF existieren nur für bestimmte MRT-Verfahren.Empfehlung für die PraxisEin klinischer Einsatz der genannten Verfahren sollte mit Ausnahme der DCE-MRT nur innerhalb von Studien erfolgen.

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. 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. 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. 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. • 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.

Recent studies with lung MRI (MRI) have shown high sensitivity (Sn) and specificity (Sp) for lung nodule detection and characterization relative to low-dose CT (LDCT). Using this background data, we sought to compare the potential screening performance of MRI vs. LDCT using a Markov model of lung cancer screening.We created a Markov cohort model of lung cancer screening which incorporated lung cancer incidence, progression, and mortality based on gender, age, and smoking burden. Sensitivity (Sn) and Sp for LDCT were taken from the MISCAN Lung Microsimulation and Sn/Sp for MRI was estimated from a published substudy of the German Lung Cancer Screening and Intervention Trial. Screening, work-up, and treatment costs were estimated from published data. Screening with MRI and LDCT was simulated for a cohort of male and female smokers (2 packs per day; 36 pack/years of smoking history) starting at age 60. We calculated the screening performance and cost-effectiveness of MRI screening and performed a sensitivity analysis on MRI Sn/Sp and cost.There was no difference in life expectancy between MRI and LDCT screening (males 13.28 vs. 13.29 life-years; females 14.22 vs. 14.22 life-years). MRI had a favorable cost-effectiveness ratio of $258,169 in men and $403,888 in women driven by fewer false-positive screens. On sensitivity analysis, MRI remained cost effective at screening costs$396 dollars and Sp81%.In this Markov model of lung cancer screening, MRI has a near-equivalent life expectancy benefit and has superior cost-effectiveness relative to LDCT.• In this Markov model of lung cancer screening, there is no difference in mortality between yearly screening with MRI and low-dose CT. • Compared to low-dose CT, screening with MRI led to a reduction in false-positive studies from 26 to 2.8% in men and 26 to 2.6% in women. • Due to similar life-expectancy and reduced false-positive rate, we found a favorable cost-effectiveness ratio of $258,169 in men and $403,888 in women of MRI relative to low-dose CT.

Rationale: Primary ciliary dyskinesia (PCD) is an inherited disorder characterized by heterogeneous airway disease. Traditional lung function techniques (e.g., spirometry) may underestimate severit...

Rationale This study aimed to describe cardiopulmonary function during exercise 3 months after hospital discharge for COVID-19 and compare groups according to dyspnea and intensive care unit (ICU) stay. Methods Participants with COVID-19 discharged from five large Norwegian hospitals were consecutively invited to a multicentre, prospective cohort study. In total, 156 participants (mean age 56.2 years, 60 females) were examined with a cardiopulmonary exercise test (CPET) 3 months after discharge and compared to a reference population. Dyspnea was assessed using the modified Medical Research Council dyspnea scale (mMRC). Results Peak oxygen uptake (V̇O2), Oxygen uptake was reduced in one-third of the participants 3 months after hospitalisation for COVID-19. The most common exercise limitation was deconditioning. Circulatory limitations to exercise were more common than ventilatory limitations.

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600–0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600–0 HU] (r = 0.56, 95% CI = 0.46–0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.

Objectives Rapid communication of CT exams positive for pulmonary embolism (PE) is crucial for timely initiation of anticoagulation and patient outcome. It is unknown if deep learning automated detection of PE on CT Pulmonary Angiograms (CTPA) in combination with worklist prioritization and an electronic notification system (ENS) can improve communication times and patient turnaround in the Emergency Department (ED). Methods In 01/2019, an ENS allowing direct communication between radiology and ED was installed. Starting in 10/2019, CTPAs were processed by a deep learning (DL)-powered algorithm for detection of PE. CTPAs acquired between 04/2018 and 06/2020 (n = 1808) were analysed. To assess the impact of the ENS and the DL-algorithm, radiology report reading times (RRT), radiology report communication time (RCT), time to anticoagulation (TTA), and patient turnaround times (TAT) in the ED were compared for three consecutive time periods. Performance measures of the algorithm were calculated on a per exam level (sensitivity, specificity, PPV, NPV, F1-score), with written reports and exam review as ground truth. Results Sensitivity of the algorithm was 79.6 % (95 %CI:70.8−87.2%), specificity 95.0 % (95 %CI:92.0−97.1%), PPV 82.2 % (95 %CI:73.9−88.3), and NPV 94.1 % (95 %CI:91.4–96 %). There was no statistically significant reduction of any of the observed times (RRT, RCT, TTA, TAT). Conclusion DL-assisted detection of PE in CTPAs and ENS-assisted communication of results to referring physicians technically work. However, the mere clinical introduction of these tools, even if they exhibit a good performance, is not sufficient to achieve significant effects on clinical performance measures.

BACKGROUND: Manually performed diameter measurements on ECG-gated CT-angiography (CTA) represent the gold standard for diagnosis of thoracic aortic dilatation. However, they are time-consuming and show high inter-reader variability. Therefore, we aimed to evaluate the accuracy of measurements of a deep learning-(DL)-algorithm in comparison to those of radiologists and evaluated measurement times (MT). METHODS: We retrospectively analyzed 405 ECG-gated CTA exams of 371 consecutive patients with suspected aortic dilatation between May 2010 and June 2019. The DL-algorithm prototype detected aortic landmarks (deep reinforcement learning) and segmented the lumen of the thoracic aorta (multi-layer convolutional neural network). It performed measurements according to AHA-guidelines and created visual outputs. Manual measurements were performed by radiologists using centerline technique. Human performance variability (HPV), MT and DL-performance were analyzed in a research setting using a linear mixed model based on 21 randomly selected, repeatedly measured cases. DL-algorithm results were then evaluated in a clinical setting using matched differences. If the differences were within 5 mm for all locations, the cases was regarded as coherent; if there was a discrepancy >5 mm at least at one location (incl. missing values), the case was completely reviewed. RESULTS: HPV ranged up to ±3.4 mm in repeated measurements under research conditions. In the clinical setting, 2,778/3,192 (87.0%) of DL-algorithm’s measurements were coherent. Mean differences of paired measurements between DL-algorithm and radiologists at aortic sinus and ascending aorta were −0.45±5.52 and −0.02±3.36 mm. Detailed analysis revealed that measurements at the aortic root were over-/underestimated due to a tilted measurement plane. In total, calculated time saved by DL-algorithm was 3:10 minutes/case. CONCLUSIONS: The DL-algorithm provided coherent results to radiologists at almost 90% of measurement locations, while the majority of discrepent cases were located at the aortic root. In summary, the DL-algorithm assisted radiologists in performing AHA-compliant measurements by saving 50% of time per case.

The differentiated assessment of respiratory mechanics, gas exchange and pulmonary circulation, as well as structural impairment of the lung are essential for the treatment of patients with cystic fibrosis (CF). Clinical lung function measurements are often not sufficiently specific and are often difficult to perform.The standard procedures for pulmonary imaging are chest X‑ray and computed tomography (CT) for assessing lung morphology. In more recent studies, an increasing number of centers are using magnetic resonance imaging (MRI) to assess lung structure and function. However, functional imaging is currently limited to specialized centers.In patients with CF, studies showed that MRI with hyperpolarized gases and Fourier decomposition/matrix pencil MRI (FD/MP-MRI) are feasible for assessing pulmonary ventilation. For pulmonary perfusion, dynamic contrast-enhanced MRI (DCE-MRI) or contrast-free methods, e.g., FD-MRI, can be used.Functional MRI provides more accurate insight into the pathophysiology of pulmonary function at the regional level. Advantages of MRI over X‑ray are its lack of ionizing radiation, the large number of lung function parameters that can be extracted using different contrast mechanisms, and ability to be used repeatedly over time.Early assessment of lung function impairment is needed as the structural changes usually occur later in the course of the disease. However, sufficient experience in clinical application exist only for certain functional lung MRI procedures.Clinical application of the aforementioned techniques, except for DCE-MRI, should be restricted to scientific studies.

Background CT has emerged as an important diagnostic tool in COVID-19, but the underlying pathological changes behind CT findings are not yet fully elucidated. Purpose The purpose of this retrospective study was to correlate CT patterns of fatal cases of COVID-19 with post-mortem pathology observations. Material and Methods The study included 70 lung lobes of 14 patients who died from RT-PCR confirmed COVID-19. All patients underwent ante-mortem CT and autopsy between March 9 and April 30, 2020. Board-certified radiologists and pathologists performed lobe-wise correlations of pulmonary observations. In a consensus reading, 267 radiological and 257 histopathological observations of the lungs were recorded and systematically graded according to severity. These observations were matched and evaluated. Results Predominant CT observations were ground glass opacities (GGO; 59 of 70 lobes examined) and areas of consolidation (33/70). The histopathological observations were consistent with diffuse alveolar damage (70/70), capillary dilatation and congestion (70/70), often accompanied by microthrombi (27/70), superimposed acute bronchopneumonia (17/70) and leukocytoclastic vasculitis (7/70). Four patients had pulmonary emboli. Bronchial wall thickening on CT histologically corresponded with acute bronchopneumonia. GGOs and consolidations corresponded with mixed histopathological observations including capillary dilation and congestion, interstitial edema, diffuse alveolar damage and microthrombosis. Vascular alterations were prominent observations in both CT and histopathology. Conclusion A significant proportion of GGO correlated with the pathologic processes of diffuse alveolar damage, capillary dilatation and congestion and microthrombosis. Our results confirm the presence and underline the importance of vascular alterations as a key pathophysiological driver in lethal COVID-19.

ObjectivesTo predict ultimate treatment intensity of COVID-19 patients using pulmonary and cardiovascular metrics fully automatically extracted from initial chest CTs.Methods All patients tested positive for SARS-CoV-2 by RT-PCR at our emergency department between March 25 and April 14, 2020 were identified (n=391). For those patients, all initial chest CTs were analyzed (n=85). Multiple pulmonary and cardiovascular metrics were extracted using deep convolutional neural networks. Three clinical treatment intensity groups were defined according to the most intensive treatment of a patient, determined six weeks later: Group 1 (outpatient), group 2 (general ward), and group 3 (intensive care unit; ICU). Univariate analyses were performed to analyze differences between groups. Subsequently, multiple metrics were combined in two binary logistic regression analyses and resulting prediction probabilities used to classify whether a patient needed hospitalization or ICU care. For analysis of discriminatory power, ROC curves were plotted and areas-under-the-curves (AUCs) calculated.ResultsThe mean interval between presentation at the emergency department and the chest CT was 1.4 days. Among others, mean percentage of lung volume affected by opacities (PO) and mean total pericardial volume (TPV) increased statistically significantly with higher treatment intensity [from group 1 to 3, standard deviation in brackets: PO: 0.8%(1.5)–11.6%(13.1)–31.6%(20.1); TPV: 733.4ml(231.7)–866.2ml(211.2)–925.7ml(125.5); both: pConclusions Metrics fully automatically extracted from initial chest CTs increase with treatment intensity of COVID-19 patients. This information can be exploited to prospectively manage allocation of healthcare resources.

Highlights • It is feasible to develop clinically useful AI-based software for quantification of pulmonary opacities in COVID-19 in just 10 days. • An established pipeline for fast transition of prototypes to full clinical implementation is an important key to success. • Human-level performance, even in the presence of advanced disease, was achieved with less than 200 chest CT scans for training of the AI algorithm., Purpose During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic. Method Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66). Results The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up. Conclusions The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

The aim was to evaluate the impact of a modified frozen elephant trunk procedure (mFET) on remodeling of the downstream aorta following acute aortic dissections. Over a period of 8 years, 205 patients (mean age 62.6 ± 12.6 years) underwent a mFET (n = 69, 33.7%) or isolated ascending aorta replacement (n = 136, 66.3%) (iAoA). Aortic diameter was assessed at the aortic arch (AoA), at the mid of the thoracic aorta (mThA), at the thoracoabdominal transition (ThAbd) and at the celiac trunk level (AbdA). Mean follow-up was 3.3 ± 2.6 years. In-hospital mortality was 14% (n = 28), 7% in mFET and 17% in the iAoA group (p = 0.08). At the end of the follow-up, overall survival was 84% (95% CI 70–92%) and 75% (65–82%) and freedom from aorta-related reoperation was 100% and 95% (88–98%) for mFET and iAoA, respectively. At iAoA, the average difference in diameter change per year between mFET and iAoA was for total lumen 0 mm (− 0.95 to 0.94 mm, p = 0.99), and for true lumen, it was 1.23 mm (− 0.09 to 2.55 mm) per year, p = 0.067. False lumen demonstrated a decrease in diameter in mFET as compared to iAoA by − 1.43 mm (− 2.75 to − 0.11 mm), p = 0.034. In mFET, at the aortic arch level the total lumen diameter decreased from 30.7 ± 4.8 mm to 30.1 ± 2.5 mm (Δr + 2.90 ± 3.64 mm) and in iAoA it increased from 31.8 ± 4.9 to 34.6 ± 5.9 mm (Δr + 2.88 ± 4.18 mm). The mFET procedure provides satisfactory clinical outcome at short term and mid-term and has a positive impact on aorta remodeling, especially at the level of the aortic arch.

BACKGROUND Lung perfusion MRI after i.v. gadolinium (Gd) contrast administration is commonly based on spoiled gradient-echo acquisitions, such as volume-interpolated breath-hold examinations (VIBE), suffering from low signal-to-noise in the parenchyma. PURPOSE To investigate the lung signal enhancement ratio (SER) with ultra-fast steady-state free precession (ufSSFP) after Gd-administration. STUDY TYPE Retrospective. SUBJECTS Ten subjects with healthy lungs; nine patients with pulmonary diseases (chronic obstructive pulmonary disease [COPD], lung cancer, pulmonary fibrosis, lung contusion). FIELD STRENGTH/SEQUENCE VIBE and ufSSFP imaging of the chest was performed at 1.5T before and 3 minutes after i.v. gadobenate dimeglumine. ASSESSMENT A workflow including deformable image registration and median filtering was used to compute 3D SER maps. SER was analyzed in the lung, blood pool, liver, muscles, and fat. The artifacts were assessed by a radiologist. In the COPD patients, ufSSFP-SER was compared to 99m Tc-MAA-SPECT/CT by visual scoring of lung enhancement deficits. STATISTICAL TESTS Mean signal, standard deviation (SD), intersubject SD, and coefficient of variation (CV) were calculated for SER. Statistical significance of differences in signal and artifacts were determined using Wilcoxon signed-rank paired test. Intermodality agreement between ufSSFP-SER and SPECT/CT was calculated by Cohen's kappa (κq ). RESULTS In healthy lungs, ufSSFP-SER (99% ± 23%, mean ± pooled intrasubject SD, CV = 23%) was significantly higher (P

OBJECTIVES Patients with severe COVID-19 may be at risk of longer term sequelae. Long-term clinical, immunological, pulmonary and radiological outcomes of patients treated with anti-inflammatory drugs are lacking. METHODS In this single-centre prospective cohort study, we assessed 90-day clinical, immunological, pulmonary and radiological outcomes of hospitalised patients with severe COVID-19 treated with tocilizumab from March 2020 to May 2020. Criteria for tocilizumab administration were oxygen saturation 30/min, C-reactive protein levels >75 mg/l, extensive area of ground-glass opacities or progression on computed tomography (CT). Descriptive analyses were performed using StataIC 16. RESULTS Between March 2020 and May 2020, 50 (27%) of 186 hospitalised patients had severe COVID-19 and were treated with tocilizumab. Of these, 52% were hospitalised on the intensive care unit (ICU) and 12% died. Eleven (22%) patients developed at least one microbiologically confirmed super-infection, of which 91% occurred on ICU. Median duration of hospitalisation was 15 days (interquartile range [IQR] 10–24) with 24 days (IQR 14–32) in ICU patients and 10 days (IQR 7–15) in non-ICU patients. At day 90, 41 of 44 survivors (93%) were outpatients. No long-term adverse events or late-onset infections were identified after acute hospital care. High SARS-CoV-2 antibody titres were found in all but one patient, who was pretreated with rituximab. Pulmonary function tests showed no obstructive patterns, but restrictive patterns in two (5.7%) and impaired diffusion capacities for carbon monoxide in 11 (31%) of 35 patients, which predominated in prior ICU patients. Twenty-one of 35 (60%) CT-scans at day 90 showed residual abnormalities, with similar distributions between prior ICU and non-ICU patients. CONCLUSIONS In this cohort of severe COVID-19 patients, no tocilizumab-related long-term adverse events or late-onset infections were identified. Although chest CT abnormalities were highly prevalent at day 90, the majority of patients showed normal lung function. Trial registration ClinicalTrials.gov NCT04351503

Purpose To design and evaluate a self-trainable natural language processing (NLP)-based procedure to classify unstructured radiology reports. The method enabling the generation of curated datasets is exemplified on CT pulmonary angiogram (CTPA) reports. Method We extracted the impressions of CTPA reports created at our institution from 2016 to 2018 (n = 4397; language: German). The status (pulmonary embolism: yes/no) was manually labelled for all exams. Data from 2016/2017 (n = 2801) served as a ground truth to train three NLP architectures that only require a subset of reference datasets for training to be operative. The three architectures were as follows: a convolutional neural network (CNN), a support vector machine (SVM) and a random forest (RF) classifier. Impressions of 2018 (n = 1377) were kept aside and used for general performance measurements. Furthermore, we investigated the dependence of classification performance on the amount of training data with multiple simulations. Results The classification performance of all three models was excellent (accuracies: 97 %–99 %; F1 scores 0.88–0.97; AUCs: 0.993–0.997). Highest accuracy was reached by the CNN with 99.1 % (95 % CI 98.5–99.6 %). Training with 470 labelled impressions was sufficient to reach an accuracy of > 93 % with all three NLP architectures. Conclusion Our NLP-based approaches allow for an automated and highly accurate retrospective classification of CTPA reports with manageable effort solely using unstructured impression sections. We demonstrated that this approach is useful for the classification of radiology reports not written in English. Moreover, excellent classification performance is achieved at relatively small training set sizes.

Purpose To share experience from a large, ongoing expert reading teleradiology program in Europe and Asia aiming at supporting referring centers to interpret high-resolution computed tomography (HRCT) with respect to presence of Usual Interstitial Pneumonia (UIP)-pattern in patients with suspected Idiopathic Pulmonary Fibrosis (IPF). Method We analyzed data from 01/2014 to 05/2019, including HRCTs from 239 medical centers in 12 European and Asian countries that were transmitted to our Picture Archiving and Communication System (PACS) via a secured internet connection. Structured reports were generated in consensus by a radiologist with over 20 years of experience in thoracic imaging and a pulmonologist with specific expertise in interstitial lung disease according to current guidelines on IPF. Reports were sent to referring physicians. We evaluated patient characteristics, technical issues, report turnaround times and frequency of diagnoses. We also conducted a survey to collect feedback from referring physicians. Results HRCT image data from 703 patients were transmitted (53.5% male). Mean age was 63.7 years (SD:17). In 35.1% of all cases diagnosis was “UIP”/”Typical UIP”. The mean report turnaround time was 1.7 days (SD:2.9). Data transmission errors occurred in 7.1%. Overall satisfaction rate among referring physicians was high (8.4 out of 10; SD:3.2). Conclusions This Eurasian teleradiology program demonstrates the feasibility of cross-border teleradiology for the provision of state-of-the-art reporting despite heterogeneity of referring medical centers and challenges like data transmission errors and language barriers. We also point out important factors for success like the usage of structured reporting templates.

Zusammenfassung: Hintergrund: Mit den technischen Weiterentwicklungen in den vergangenen Jahren hat sich die MRT zu einem methodisch ausgereiften und für spezifische pulmonale Fragestellungen bereits auch klinisch bewährten Untersuchungsverfahren entwickelt. Ohne Strahlenexposition kombiniert sie morphologische und funktionelle Diagnostik und ergänzt das Spektrum der etablierten Verfahren für die bildgebende Diagnostik der Lunge. Ziel der Arbeit und Methoden: Diese Arbeit gibt einen Überblick über die aktuell verwendeten Sequenzen und Techniken zur Darstellung pulmonaler Rundherde und analysiert deren klinischen Stellenwert anhand der aktuellen Studienlage. In Zentrum stehen dabei die Detektion pulmonaler Metastasen, die Detektion primär pulmonaler Malignome bei Personen mit Risikoprofil und die Abklärung pulmonaler Rundherde hinsichtlich ihrer Dignität. Ergebnisse und Diskussion: Die MRT besitzt im Vergleich zum Referenzstandard Niedrigdosis-CT eine Sensitivität von ca. 80 % für die Detektion maligner pulmonaler Rundherde und ist der CT damit etwas unterlegen. Vorteile der MRT gegenüber der Niedrigdosis-CT sind andererseits die höhere Spezifität bei der Differenzierung maligner und benigner pulmonaler Rundherde sowie die fehlende Strahlenexposition. Außerhalb von Studien kann ein breiter Einsatz der MRT als Screeningverfahren zur Detektion und Abklärung pulmonaler Rundherde aufgrund der noch ungenügenden Datenlage derzeit noch nicht empfohlen werden. Das diagnostische Potenzial der MRT für die Früherkennung und das Staging pulmonaler Malignome rechtfertigt aber die weitere Evaluation der MRT als sekundäre Modalität im Rahmen von Studien.

The purpose of this study was to determine if parameters derived from diffusion-weighted (DW-) and dynamic contrast-enhanced (DCE-) magnetic resonance imaging (MRI) can help to assess early response to peptide receptor radionuclide therapy (PRRT) with 90Y-DOTATOC in neuroendocrine hepatic metastases (NET-HM). Twenty patients (10 male; 10 female; mean age: 59.2 years) with NET-HM were prospectively enrolled in this single-center imaging study. DW-MRI and DCE-MRI studies were performed just before and 48 hours after therapy with 90Y-DOTATOC. Abdominal SPECT/CT was performed 24 hours after therapy. This MRI imaging and therapy session was repeated after a mean interval of 10 weeks. Up to four lesions per patient were evaluated. Response to therapy was evaluated using metastasis sizes at the first and second therapy session as standard for comparison (regressive, stable, and progressive). DW-MRI analysis included the apparent diffusion coefficient (ADC) and parameters related to intravoxel incoherent motion (IVIM), namely, diffusion (D), perfusion fraction (f) and pseudo-diffusion (D∗). DCE-MRI analysis comprised Ktrans, ve and kep. For statistical analysis of group differences, one-way analysis of variance (ANOVA) and appropriate post hoc testing was performed. A total of 51 lesions were evaluated. Seven of 51 lesions (14%) showed size progression, 18/51 (35%) regression, and 26/51 (51%) remained stable. The lesion-to-spleen uptake ratio in SPECT showed a decrease between the two treatment sessions that was significantly stronger in regressive lesions compared with stable (p = 0.013) and progressive lesions (p = 0.021). ANOVA showed significant differences in mean ADC after 48 h (p = 0.026), with higher ADC values for regressive lesions. Regarding IVIM, highest values for D at baseline were seen in regressive lesions (p = 0.023). In DCE-MRI, a statistically significant increase in ve after 10 weeks (p = 0.046) was found in regressive lesions. No differences were observed for the transfer constants Ktrans and kep. Diffusion restriction quantified as ADC was able to differentiate regressive from progressive NET-HMs as early as 48 hours after PRRT. DW-MRI therefore may complement scintigraphy/SPECT for early assessment of response to PRRT. Assessment of perfusion parameters using IVIM and DCE-MRI did not show an additional benefit.

The purpose of this study was to determine if parameters derived from diffusion-weighted (DW-) and dynamic contrast-enhanced (DCE-) magnetic resonance imaging (MRI) can help to assess early response to peptide receptor radionuclide therapy (PRRT) with 90Y-DOTATOC in neuroendocrine hepatic metastases (NET-HM). Twenty patients (10 male; 10 female; mean age: 59.2 years) with NET-HM were prospectively enrolled in this single-center imaging study. DW-MRI and DCE-MRI studies were performed just before and 48 hours after therapy with 90Y-DOTATOC. Abdominal SPECT/CT was performed 24 hours after therapy. This MRI imaging and therapy session was repeated after a mean interval of 10 weeks. Up to four lesions per patient were evaluated. Response to therapy was evaluated using metastasis sizes at the first and second therapy session as standard for comparison (regressive, stable, and progressive). DW-MRI analysis included the apparent diffusion coefficient (ADC) and parameters related to intravoxel incoherent motion (IVIM), namely, diffusion (D), perfusion fraction (f) and pseudo-diffusion (D∗). DCE-MRI analysis comprised Ktrans, ve and kep. For statistical analysis of group differences, one-way analysis of variance (ANOVA) and appropriate post hoc testing was performed. A total of 51 lesions were evaluated. Seven of 51 lesions (14%) showed size progression, 18/51 (35%) regression, and 26/51 (51%) remained stable. The lesion-to-spleen uptake ratio in SPECT showed a decrease between the two treatment sessions that was significantly stronger in regressive lesions compared with stable (p=0.013) and progressive lesions (p=0.021). ANOVA showed significant differences in mean ADC after 48 h (p=0.026), with higher ADC values for regressive lesions. Regarding IVIM, highest values for D at baseline were seen in regressive lesions (p=0.023). In DCE-MRI, a statistically significant increase in ve after 10 weeks (p=0.046) was found in regressive lesions. No differences were observed for the transfer constants Ktrans and kep. Diffusion restriction quantified as ADC was able to differentiate regressive from progressive NET-HMs as early as 48 hours after PRRT. DW-MRI therefore may complement scintigraphy/SPECT for early assessment of response to PRRT. Assessment of perfusion parameters using IVIM and DCE-MRI did not show an additional benefit.

Automated detection and segmentation is a prerequisite for the deployment of image-based secondary analyses, especially for lung tumors. However, currently only applications for lung nodules ≤3 cm exist. Therefore, we tested the performance of a fully automated AI-based lung nodule algorithm for detection and 3D segmentation of primary lung tumors in the context of tumor staging using the CT component of FDG-PET/CT and including all T-categories (T1–T4). FDG-PET/CTs of 320 patients with histologically confirmed lung cancer performed between 01/2010 and 06/2016 were selected. First, the main primary lung tumor within each scan was manually segmented using the CT component of the PET/CTs as reference. Second, the CT series were transferred to a platform with AI-based algorithms trained on chest CTs for detection and segmentation of lung nodules. Detection and segmentation performance were analyzed. Factors influencing detection rates were explored with binominal logistic regression and radiomic analysis. We also processed 94 PET/CTs negative for pulmonary nodules to investigate frequency and reasons of false-positive findings. The ratio of detected tumors was best in the T1-category (90.4%) and decreased continuously: T2 (70.8%), T3 (29.4%), and T4 (8.8%). Tumor contact with the pleura was a strong predictor of misdetection. Segmentation performance was excellent for T1 tumors (r = 0.908, p<0.001) and tumors without pleural contact (r = 0.971, p<0.001). Volumes of larger tumors were systematically underestimated. There were 0.41 false-positive findings per exam. The algorithm tested facilitates a reliable detection and 3D segmentation of T1/T2 lung tumors on FDG-PET/CTs. The detection and segmentation of more advanced lung tumors is currently imprecise due to the conception of the algorithm for lung nodules

OBJECTIVE: To extract pulmonary and cardiovascular metrics from chest CTs of patients with coronavirus disease 2019 (COVID-19) using a fully automated deep learning-based approach and assess their potential to predict patient management. MATERIALS AND METHODS: All initial chest CTs of patients who tested positive for severe acute respiratory syndrome coronavirus 2 at our emergency department between March 25 and April 25, 2020, were identified (n = 120). Three patient management groups were defined: group 1 (outpatient), group 2 (general ward), and group 3 (intensive care unit [ICU]). Multiple pulmonary and cardiovascular metrics were extracted from the chest CT images using deep learning. Additionally, six laboratory findings indicating inflammation and cellular damage were considered. Differences in CT metrics, laboratory findings, and demographics between the patient management groups were assessed. The potential of these parameters to predict patients' needs for intensive care (yes/no) was analyzed using logistic regression and receiver operating characteristic curves. Internal and external validity were assessed using 109 independent chest CT scans. RESULTS: While demographic parameters alone (sex and age) were not sufficient to predict ICU management status, both CT metrics alone (including both pulmonary and cardiovascular metrics; area under the curve [AUC] = 0.88; 95% confidence interval [CI] = 0.79-0.97) and laboratory findings alone (C-reactive protein, lactate dehydrogenase, white blood cell count, and albumin; AUC = 0.86; 95% CI = 0.77-0.94) were good classifiers. Excellent performance was achieved by a combination of demographic parameters, CT metrics, and laboratory findings (AUC = 0.91; 95% CI = 0.85-0.98). Application of a model that combined both pulmonary CT metrics and demographic parameters on a dataset from another hospital indicated its external validity (AUC = 0.77; 95% CI = 0.66-0.88). CONCLUSION: Chest CT of patients with COVID-19 contains valuable information that can be accessed using automated image analysis. These metrics are useful for the prediction of patient management.

Die separate Beurteilung von Atemmechanik, Gasaustauschprozessen und Lungenzirkulation ist wesentlich fur die Diagnose und Therapie von Lungenerkrankungen. Klinische Lungenfunktionstests sind aufgrund ihrer zumeist nur globalen Aussage oft nicht hinreichend spezifisch in der Differenzialdiagnostik oder eingeschrankt sensitiv bei der Detektion fruher pathologischer Veranderungen. Standardverfahren der bildgebenden Lungendiagnostik sind die Computertomographie (CT) zur morphologischen Darstellung und die Perfusions-/Ventilationsszintigraphie bzw. „single photon emission computed tomography“ (SPECT) zur funktionellen Diagnostik. Zur Darstellung der Lungenventilation stehen die MRT mit hyperpolarisierten Gasen, die O2-verstarkte MRT, die MRT mit fluorierten Gasen und die Fourier-Dekompositions-MRT (FD-MRT) zur Verfugung. Zur Perfusionsbestimmung konnen die dynamische kontrastmittelverstarkte MRT (DCE-MRT), das „arterial spin labeling“ (ASL) und die FD-MRT verwendet werden. Bildgebende Verfahren erlauben einen genaueren Einblick in die Pathophysiologie der Lungenfunktion auf regionaler Ebene. Vorteile der MRT sind die fehlende Strahlenbelastung, welche die schonende Akquisition dynamischer Daten ermoglicht sowie die Vielfalt der verfugbaren Kontraste und damit zuganglichen Parameter der Lungenfunktion. Ausreichende klinische Daten existieren nur fur bestimmte Anwendungen der DCE-MRT. Fur die ubrigen Verfahren gibt es lediglich Machbarkeitsstudien und Fallserien mit unterschiedlichem Umfang. Hyperpolarisierte Gase sind technisch bedingt nur eingeschrankt in der Klinik anwendbar. Ein klinischer Einsatz der genannten Verfahren sollte mit Ausnahme der DCE-MRT nur innerhalb von Studien erfolgen.

Objective To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and methods We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

Historically, giant cell arteritis (GCA) was considered to be synonymous with temporal arteritis. However, the disease spectrum of GCA extends much further, and includes vasculitis of the aorta and its branches with or without involvement of the temporal arteries. Imaging is crucial for the diagnosis and follow-up of GCA patients. Large vessel GCA (LV-GCA) often presents as an inflammatory syndrome and is only detected by imaging modalities such as: colour duplex sonography (CDS), computed tomography (CT) / CT angiography (CTA), magnetic resonance imaging (MRI) or 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) / CT. Deciding which imaging modality to use in different clinical situations remains a matter of debate. CDS and MRI enable assessment of the temporal arteries with a presumably higher sensitivity than histology. In the context of a typical presentation, CDS can replace a biopsy. In about a third of patients, the temporal arteries are not involved, thus PET/CT, MRI, CT, or CDS of larger arteries is needed to diagnose GCA. The sensitivity of all modalities is affected by glucocorticoid therapy. Therefore, without delaying therapy, imaging should be performed within a few days of treatment initiation. The use of PET/CT for the work-up of inflammatory syndromes in the elderly reveals vasculitis in approximately 20% of examined patients and uncover relevant diagnoses in the majority of remaining patients. The aorta should be routinely assessed in all GCA patients at diagnosis and during follow-up. MRA or CTA are best suited to characterise structural damage of larger arteries. The role of imaging in monitoring GCA disease activity still needs to be further defined.

Accurate segmentations in medical images are the foundations for various clinical applications. Advances in machine learning-based techniques show great potential for automatic image segmentation, but these techniques usually require a huge amount of accurately annotated reference segmentations for training. The guiding hypothesis of this paper was that crowd-algorithm collaboration could evolve as a key technique in large-scale medical data annotation. As an initial step toward this goal, we evaluated the performance of untrained individuals to detect and correct errors made by three-dimensional (3-D) medical segmentation algorithms. To this end, we developed a multistage segmentation pipeline incorporating a hybrid crowd-algorithm 3-D segmentation algorithm integrated into a medical imaging platform. In a pilot study of liver segmentation using a publicly available dataset of computed tomography scans, we show that the crowd is able to detect and refine inaccurate organ contours with a quality similar to that of experts (engineers with domain knowledge, medical students, and radiologists). Although the crowds need significantly more time for the annotation of a slice, the annotation rate is extremely high. This could render crowdsourcing a key tool for cost-effective large-scale medical image annotation.

Objective: This study analyses the diagnostic potential of Diffusion-Weighted Imaging with Background Suppression (DWIBS) in the detection of focal bone marrow lesions from multiple myeloma. The signal and contrast properties of DWIBS are evaluated in correlation with the serum concentration of M-component (MC) and compared with established T1- and T2-weighted sequences. Methods: Data from 103 consecutive studies in 81 patients are analysed retrospectively. Signal intensities and apparent Diffusion Coefficients (ADC) of 79 focal lesions in the lumbar spine or pelvis of 38 patients are determined and contrast-to-noise-ratio (CNR) is calculated. Data from patients with low (20g/dL) MC are evaluated separately. Results: Signal intensities of focal myeloma lesions on T2w-STIR vary significantly depending on the MC, which leads to a loss in CNR in patients with high MC. No signal variation is observed for T1w-TSE and DWIBS. The CNR values provided by DWIBS in patients with high MC are slightly higher than those of T2w-STIR. ADC values in patients with low MC are significantly higher than in patients with high MC. Conclusion: Whole-body DWIBS has the potential to improve the conspicuity of focal myeloma lesions and provides additional biological information by ADC quantification

The process of lung cancer staging is getting increasingly complex and requires distinct input from specialized physicians of radiology, nuclear medicine, thoracic surgery, and pathology. Also after the advent of the revised 8th edition of the TNM classification, noninvasive imaging with CT and 18F-FDG-PET, supplemented by MRI, continues to provide the initial basis for clinical staging by determining the anatomic extent of the disease and thus plays a pivotal role in the diagnosis and management of NSCLC. In cases without distant metastatic disease, pretherapeutic mediastinal staging with invasive methods (mediastinoscopy or endoscopic procedures) is mandatory to determine the most appropriate treatment strategy if imaging findings are positive or in certain scenarios that come along with a high risk of false-negative imaging results. The most important limitation inherent to the current TNM staging system is its purely anatomic character that provides insufficient information related to the many different sorts of novel targeted therapies. This translates also to imaging-derived staging of NSCLC in radiology and nuclear medicine, where—besides higher anatomic resolution and image quality—the most important remaining challenge is to gather more “functional” information and generate a more comprehensive picture of the disease by noninvasive staging methods.

Results of PET/CT examinations are communicated as text-based reports which are frequently not fully structured. Incomplete or missing staging information can be a significant source of staging and treatment errors. We compared standard text-based reports to a manual full 3D-segmentation-based approach with respect to TNM completeness and processing time. TNM information was extracted retrospectively from 395 reports. Moreover, the RIS time stamps of these reports were analyzed. 2995 lesions using a set of 41 classification labels (TNM features + location) were manually segmented on the corresponding image data. Information content and processing time of reports and segmentations were compared using descriptive statistics and modelling. The TNM/UICC stage was mentioned explicitly in only 6% (n=22) of the text-based reports. In 22% (n=86), information was incomplete, most frequently affecting T stage (19%, n=74), followed by N stage (6%, n=22) and M stage (2%, n=9). Full NSCLC-lesion segmentation required a median time of 13.3 min, while the median of the shortest estimator of the text-based reporting time (R1) was 18.1 min (p=0.01). Tumor stage (UICC I/II: 5.2 min, UICC III/IV: 20.3 min, p<0.001), lesion size (p<0.001), and lesion count (n=1: 4.4 min, n=12: 37.2 min, p<0.001) correlated significantly with the segmentation time, but not with the estimators of text-based reporting time. Numerous text-based reports are lacking staging information. A segmentation-based reporting approach tailored to the staging task improves report quality with manageable processing time and helps to avoid erroneous therapy decisions based on incomplete reports. Furthermore, segmented data may be used for multimedia enhancement and automatization.

Lung perfusion MRI after i.v. gadolinium (Gd) contrast administration is commonly based on spoiled gradient-echo acquisitions, such as volume-interpolated breath-hold examinations (VIBE), suffering from low signal-to-noise in the parenchyma.To investigate the lung signal enhancement ratio (SER) with ultra-fast steady-state free precession (ufSSFP) after Gd-administration.Retrospective.Ten subjects with healthy lungs; nine patients with pulmonary diseases (chronic obstructive pulmonary disease [COPD], lung cancer, pulmonary fibrosis, lung contusion).VIBE and ufSSFP imaging of the chest was performed at 1.5T before and 3 minutes after i.v. gadobenate dimeglumine.A workflow including deformable image registration and median filtering was used to compute 3D SER maps. SER was analyzed in the lung, blood pool, liver, muscles, and fat. The artifacts were assessed by a radiologist. In the COPD patients, ufSSFP-SER was compared toMean signal, standard deviation (SD), intersubject SD, and coefficient of variation (CV) were calculated for SER. Statistical significance of differences in signal and artifacts were determined using Wilcoxon signed-rank paired test. Intermodality agreement between ufSSFP-SER and SPECT/CT was calculated by Cohen's kappa (κIn healthy lungs, ufSSFP-SER (99% ± 23%, mean ± pooled intrasubject SD, CV = 23%) was significantly higher (P 10UfSSFP-SER of the lung is a rapid and simple method. Our preliminary data show plausible results in different pulmonary diseases, motivating further evaluation in larger cohorts.2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.

Primary ciliary dyskinesia (PCD) is characterized by functional abnormalities of the cilia, leading to chronic airway infection and remodeling. Lung function tests like inert gas washout measurements detect ventilation inhomogeneity, but cannot determine its origin. Novel magnetic resonance imaging (MRI) methods such as Matrix Pencil (MP) decomposition MRI can visualize functional changes in the lung without the administration of contrast agents and the need for breathing maneuvers. This study investigates the correlation between functional and morphological MRI and lung function indices in patients with PCD. Thirty-one patients with PCD (mean age 13.5 years, range 5–28) underwent MRI and lung function tests on the same day. Functional MP-MRI provided semi-quantitative measures of the perfusion (RQ) and ventilation (RFV) impairment as percentages of the affected lung volume. Morphological MRI was evaluated using a score derived from cystic fibrosis. Lung function tests provided information about global (lung clearance index, LCI) ventilation inhomogeneity. Both MRI and inert gas washout measurements detected functional impairment in PCD: RFV ranged from 11% to 29% and RQ ranged from 9% to 28%. RFV and RQ moderately correlated with LCI (r=0.4, p=0.04; r=0.4, p=0.03, respectively). Total morphology scores strongly correlated with LCI (r=0.6, p Functional MP-MRI is a novel, sensitive and non-invasive method to detect and visualize perfusion and ventilation abnormalities. For the first time we could show a correlation between a lung function test and a functional and structural MRI in patients with PCD.

Introduction: High resolution computed tomography (HRCT) is essential in the diagnostic algorithm for idiopathic pulmonary fibrosis (IPF). If identifiable causes of interstitial lung disease (ILD) are absent, an HRCT showing a typical usual interstitial pneumonia (UIP) pattern is diagnostic for IPF. Here we report first experiences with a teleradiology-project that offers physicians the possibility for second opinion HRCT read regarding the presence of UIP pattern in patients with suspected IPF. Methods: HRCT were uploaded through a secured internet connection. Only images in original Digital Imaging and Communication in Medicine (DICOM) format were accepted. HRCTs were assessed by a radiologist and a pulmonologist, both experienced in the diagnosis of ILD. According to current guidelines each HRCT was rated showing either typical UIP pattern, possible UIP pattern, or being inconsistent with UIP pattern. Results: Between March 2015 and January 2017 we received 160 HRCTs for a second opinion read from physicians in 10 different Eastern European countries. All images were of diagnostic quality. In 58/160 (36%) patients a typical UIP pattern was diagnosed, possible UIP pattern was detected in 27/160 (17%), and in 75/160 (47%) patients the prevailing pattern was considered as inconsistent with UIP. Conclusions: Our data demonstrate a useful application of teleradiology to provide expert reading of HRCT in patients with suspected IPF, particularly when local radiological expertise is limited. This project is not intended to replace local multidisciplinary panels, but to support local panels by providing specific expertise. More experience will be needed to define the role of teleradiology in patients with suspected IPF.

The minimum apparent diffusion coefficient (ADCmin) derived from diffusion-weighted MRI (DW-MRI) and the maximum standardized uptake value (SUVmax) of FDG-PET are markers of aggressiveness in lung cancer. The numeric correlation of the two parameters has been extensively studied, but their spatial interplay is not well understood. After FDG-PET and DW-MRI coregistration, values and location of ADCmin- and SUVmax-voxels were analyzed. The upper limit of the 95% confidence interval for registration accuracy of sequential PET/MRI was 12 mm, and the mean distance (D) between ADCmin- and SUVmax-voxels was 14.0 mm (average of two readers). Spatial mismatch (D > 12 mm) between ADCmin and SUVmax was found in 9/25 patients. A considerable number of mismatch cases (65%) was also seen in a control group that underwent simultaneous PET/MRI. In the entire patient cohort, no statistically significant correlation between SUVmax and ADCmin was seen, while a moderate negative linear relationship (r = −0.5) between SUVmax and ADCmin was observed in tumors with a spatial match (D ≤ 12 mm). In conclusion, spatial mismatch between ADCmin and SUVmax is found in a considerable percentage of patients. The spatial connection of the two parameters SUVmax and ADCmin has a crucial influence on their numeric correlation.

Lung function tests are commonly used to monitor lung disease in cystic fibrosis (CF). While practical, they cannot locate the exact origin of functional impairment. Contemporary magnetic resonance imaging (MRI) techniques provide information on the location of disease but the need for contrast agents constrains their repeated application. We examined the correlation between functional MRI, performed without administration of contrast agent, and lung clearance index (LCI) from nitrogen multiple-breath washout (N2-MBW).40 children with CF (median (range) age 12.0 (6–18) years) and 12 healthy age-matched controls underwent functional and structural MRI and lung function tests on the same day. Functional MRI provided semiquantitative measures of perfusion (RQ) and ventilation (RFV) impairment as percentages of affected lung volume. Morphological MRI was evaluated using CF-specific scores. LCI measured global ventilation inhomogeneity.MRI detected functional impairment in CF:RFV19–38% andRQ16–35%.RFVandRQcorrelated strongly with LCI (r=0.76, pNoninvasive functional MRI is a promising method to detect and visualise perfusion and ventilation impairment in CF without the need for contrast agents.

Real-time three-dimensional echocardiography (RT3DE) is superior to two-dimensional echocardiography in assessing left atrial (LA) parameters, but to date algorithms developed for the left ventricle were applied due to a lack of dedicated LA software. In addition, no data are available on RT3DE assessment of active atrial contraction. The aim of this study was to validate a novel RT3DE analysis tool specifically dedicated to evaluate the LA. Cardiac magnetic resonance imaging (MRI) served as standard of reference. Fifty-five patients scheduled for pulmonary vein isolation underwent cardiac MRI and RT3DE. On ultrasound image datasets, a dynamic polyhedron model of the LA was generated from which LA maximum and minimum volumes (LAmax and LAmin), passive atrial emptying fraction (LAEF), and active atrial ejection fraction (LAEFtrue) were derived and compared to values obtained from cardiac MRI. High intraclass correlations between RT3DE and MRI were found for LAmax (r = 0.94, p