Tomography Pulmonary Angiography Research Articles

Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms

Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death. While medical imaging, through computed tomographic pulmonary angiography (CTPA), represents the gold standard for PE diagnosis, it is still susceptible to misdiagnosis or significant diagnosis delays, which may be fatal for critical cases. Despite the recently demonstrated power of deep learning to bring a significant boost in performance in a wide range of medical imaging tasks, there are still very few published researches on automatic pulmonary embolism detection. Herein we introduce a deep learning based approach, which efficiently combines computer vision and deep neural networks for pulmonary embolism detection in CTPA. Our method brings novel contributions along three orthogonal axes: (1) automatic detection of anatomical structures; (2) anatomical aware pretraining, and (3) a dual-hop deep neural net for PE detection. We obtain state-of-the-art results on the publicly available multicenter large-scale RSNA dataset.

PE-Ynet: a novel attention-based multi-task model for pulmonary embolism detection using CT pulmonary angiography (CTPA) scan images.

Pulmonary Embolism (PE) has diverse manifestations with different etiologies such as venous thromboembolism, septic embolism, and paradoxical embolism. In this study, a novel attention-based multi-task model is proposed for PE segmentation and detection from Computed Tomography Pulmonary Angiography (CTPA) images. A Y-Net architecture is used to implement this model, which facilitates segmentation and classification jointly, improving performance and efficiency. It is leveraged with Multi Head Attention (MHA), which allows the model to focus on important regions of the image while suppressing irrelevant information, improving the accuracy of the segmentation and detection tasks. The proposed PE-YNet model is tested with two public datasets, achieving a maximum mean detection and segmentation accuracy of 99.89% and 99.83%, respectively, on the CAD-PE challenge dataset. Similarly, it also achieves a detection accuracy of 99.75% and a segmentation accuracy of 99.81% on the FUMPE dataset. Additionally, sensitivity analysis also shows a high sensitivity of 0.9885 for the localization error ɛ = 0 for the CAD-PE dataset, demonstrating the model's robustness against false predictions compared to state-of-the-art models. Further, this model also exhibits lower inference time, size, and memory usage compared to representative models. An automated PE-YNet tool can assist physicians with PE diagnosis, treatment, and prognosis monitoring in the clinical management of CoVID-19.

Oscillometry Longitudinal Data on COVID-19 Acute Respiratory Syndrome Treated with Non-Invasive Respiratory Support.

Background: Oscillometry allows for the non-invasive measurements of lung mechanics. In COVID-19 ARDS patients treated with Non-Invasive Oxygen Support (NI-OS), we aimed to (1) observe lung mechanics at the patients' admission and their subsequent changes, (2) compare lung mechanics with clinical and imaging data, and (3) evaluate whether lung mechanics helps to predict clinical outcomes. Methods: We retrospectively analyzed the data from 37 consecutive patients with moderate-severe COVID-19 ARDS. Oscillometry was performed on their 1st, 4th, and 7th day of hospitalization. Resistance (R5), reactance (X5), within-breath reactance changes (ΔX5), and the frequency dependence of the resistance (R5-R19) were considered. Twenty-seven patients underwent computed tomographic pulmonary angiography (CTPA): collapsed, poorly aerated, and normally inflated areas were quantified. Adverse outcomes were defined as intubation or death. Results: Thirty-two patients were included in this study. At the first measurement, only 44% of them had an abnormal R5 or X5. In total, 23 patients had measurements performed on their 3rd day and 7 on their 7th day of hospitalization. In general, their R5, R5-R19, and ΔX decreased with time, while their X5 increased. Collapsed areas on the CTPA correlated with the X5 z-score (ρ = -0.38; p = 0.046), while poorly aerated areas did not. Seven patients had adverse outcomes but did not present different oscillometry parameters on their 1st day of hospitalization. Conclusions: Our study confirms the feasibility of oscillometry in critically ill patients with COVID-19 pneumonia undergoing NI-OS. The X5 z-scores indicates collapsed but not poorly aerated lung areas in COVID-19 pneumonia. Our data, which show a severe impairment of gas exchange despite normal reactance in most patients with COVID-19 ARDS, support the hypothesis of a composite COVID-19 ARDS physiopathology.

Зв’язок рівня інтерлейкіну-6 з клінічним перебігом гострої тромбоемболії легеневої артерії

The aim – to investigate the possible influence of the level of interleukin-6 (IL-6) on the clinical course and remodeling of the right ventricle (RV) in patients with acute pulmonary embolism (PE).Materials and methods. 56 patients with a diagnosis of acute PE, confirmed by сomputed tomographic pulmonary angiography (CTPA), and in whom the level of IL-6 was determined, were studied. The patients were divided into two groups: 1 group with a normal IL-6 level (less than 5.9 pg/ml), 2 group with an elevated IL-6 level (more than 5.9 pg/ml). Clinical and anamnestic and laboratory-instrumental data were analyzed, statistical analysis of the resulting figures was carried out.Results and discussion. When comparing the groups depending on the level of IL-6, it was found that in group 1, not a single case of high-risk PE was recorded (p=0.052), while there was a significantly higher percentage of moderate-low-risk patients, p<0.05. Patients in group 2 had a higher heart rate (p=0.0006), lower SBP (p=0.04) at admission, and a tendency to increase body mass index (p=0.089). In addition, in group 2, the average levels of leukocytes (p=0.046), d-dimer (p=0.007), CRP (p=0.004) were higher, and the level of lymphocytes (p=0.008) was lower than in group 1, and the trend was determined to an increase in neutrophils (p=0.07) and CPK MB (p=0.89) in the 2nd group. According to the ultrasound data, in group 2 there was more often the detection of thrombosis of the veins of the lower extremities (p=0.003), a significantly larger size of the RV (p=0.02), a tendency to increase the size of the right atrium (RA) and a higher level of systolic pulmonary pressure (p=0.068 ). Analysis of the CTPA showed a greater dilatation of the left LA (p=0.0297) and an increase in the LV/LV index (p=0.0072) in the 2nd group. Correlation analysis revealed an inverse connection with the level of SpO2 (p=0.03) and lymphocytes (p=0.0065), a direct connection with heart rate (p<0.001), the ratio of LV/LV index (p=0.046), with the level of troponin I (p=0.014), D-dimer (p=0.026), leukocytes (p=0.026), neutrophils (0.038) and glucose (0.016), as well as the trend regarding the connection between the IL-6 level and the size of the RV according to echocardiography (p=0.07) and CPK MB level (p=0.086). The data of ROC analysis showed the connection of dilatation of the RV and Il-6 from the level of more than 7.65 pg/ml, with a sensitivity of the indicator of 90 %, specificity of 50 %.Conclusions. An Il-6 level increase is more common in elderly patients, patients with venous thrombosis of the lower extremities, tachycardia, hypotension, and with a greater risk of an adverse course during the hospital period. In 2 groups, a higher level of other markers of inflammation (leukocytes, CRP), larger sizes of the RV, a higher level of pulmonary artery pressure according to echocardiography and values of RV/LV according to CTPA results are observed. A direct connection between IL-6 level and heart rate, troponin level, D-dimer level, LV/LV ratio and inverse connection with saturation and lymphocyte level was established according to correlation analysis. Multivariate regression analysis established an independent connection between the IL-6 level and some laboratory (CPK MB, blood glucose) and echocardiographic parameters (RA, LV ESD, LV EDV, LV ESV, LV EF). The threshold level of Il-6, which is accompanied by dilatation of the RV according to Roc-analysis data, was determined.

Socioeconomic deprivation and illness trajectory in the Scottish population after COVID-19 hospitalization

BackgroundThe associations between deprivation and illness trajectory after hospitalisation for coronavirus disease-19 (COVID-19) are uncertain.MethodsA prospective, multicentre cohort study was conducted on post-COVID-19 patients, enrolled either in-hospital or shortly post-discharge. Two evaluations were carried out: an initial assessment and a follow-up at 28–60 days post-discharge. The study encompassed research blood tests, patient-reported outcome measures, and multisystem imaging (including chest computed tomography (CT) with pulmonary and coronary angiography, cardiovascular and renal magnetic resonance imaging). Primary and secondary outcomes were analysed in relation to socioeconomic status, using the Scottish Index of Multiple Deprivation (SIMD). The EQ-5D-5L, Brief Illness Perception Questionnaire (BIPQ), Patient Health Questionnaire-4 (PHQ-4) for Anxiety and Depression, and the Duke Activity Status Index (DASI) were used to assess health status.ResultsOf the 252 enrolled patients (mean age 55.0 ± 12.0 years; 40% female; 23% with diabetes), deprivation status was linked with increased BMI and diabetes prevalence. 186 (74%) returned for the follow-up. Within this group, findings indicated associations between deprivation and lung abnormalities (p = 0.0085), coronary artery disease (p = 0.0128), and renal inflammation (p = 0.0421). Furthermore, patients with higher deprivation exhibited worse scores in health-related quality of life (EQ-5D-5L, p = 0.0084), illness perception (BIPQ, p = 0.0004), anxiety and depression levels (PHQ-4, p = 0.0038), and diminished physical activity (DASI, p = 0.002). At the 3-month mark, those with greater deprivation showed a higher frequency of referrals to secondary care due to ongoing COVID-19 symptoms (p = 0.0438). However, clinical outcomes were not influenced by deprivation.ConclusionsIn a post-hospital COVID-19 population, socioeconomic deprivation was associated with impaired health status and secondary care episodes. Deprivation influences illness trajectory after COVID-19.

Prevalence, risk factors, and clinical characteristics of pulmonary embolism in patients with acute exacerbation of COPD in Plateau regions: a prospective cohort study

Background and objectiveTo investigate pulmonary thromboembolism (PE) in acute exacerbation of chronic obstructive pulmonary disease (AE-COPD) patients in plateau regions, we performed a prospective cohort study to evaluate the prevalence, risk factors and clinical characteristics of PE in the cohort of hospitalized patients at high altitude.MethodsWe did a prospective study with a total of 636 AE-COPD patients in plateau regions. Demographic and clinical data, laboratory data, including ultrasound scans of the lower extremities and cardiac ultrasound, and computed tomographic pulmonary angiography (CTPA) variables were obtained, and comparisons were made between groups with and without PE. We also conducted logistic regression to explore the risk factors of PE.ResultsOf the 636 patients hospitalized with AE-COPD (age 67.0 ± 10.7 years, 445[70.0%] male), 188 patients developed PE (29.6% [95% CI: 26.0%, 33.1%]). Multivariable logistic regression showed that ethnic minorities, D-dimer > 1 mg/L, AST > 40 U/L, chest pain, cardiac insufficiency or respiratory failure, Padua score > 3, and DVT were associated with a higher probability of PE.ConclusionsThe prevalence of PE is high and those with a higher Padua score, the occurrence of deep venous thrombosis, higher neutrophil count, chest pain, cardiac insufficiency or respiratory failure, higher levels of AST, and a higher level of D-dimer had a higher risk of PE. The analysis of AE-COPD may help to provide more accurate screening for PE and improve clinical outcomes of patients with AE-COPD in plateau regions.

Assessing the Prevalence of Pulmonary Embolism and the Clot Burden in Hospitalized Patients with Chronic Obstructive Pulmonary Disease Exacerbation.

This prospective cohort study aimed to assess the pulmonary embolism (PE) rate and clot burden in patients with chronic obstructive pulmonary disease (COPD) exacerbation. A total of 248 patients entered the study, and their clinical probability of PE was assessed using the Geneva score. Patients with high clinical probability underwent computed tomographic pulmonary angiography, while those with low or intermediate probability underwent a d-dimer test. Among the patients analyzed, 14 individuals (5.6%) were confirmed to have PE using computed tomographic pulmonary angiography. A 3-month follow-up revealed 3 cases of PE out of 232 patients initially deemed PE-free. Mortality rates were higher among patients with venous thromboembolism at admission than those diagnosed with PE during follow-up. Pulmonary embolism (PE) prevalence among patients with COPD exacerbation was 5.6%. The results of this study show the importance of screening for PE in patients with COPD presenting with dyspnea. Not all of them are due to COPD exacerbation; a small minority of them can be due to PE, which needs prompt screening, confirmation, and therapy. However, further research with larger cohorts is required to understand better the potential benefits and implications of systematic screening for pulmonary embolism in this specific patient population.

Comparison of pulmonary artery sarcoma and pulmonary thromboembolism according to clinical and computed tomography pulmonary angiography and magnetic resonance imaging characteristics: a single-center retrospective study.

Pulmonary artery sarcoma (PAS) is a very rare malignancy with a poor prognosis; however, its clinical manifestations and imaging findings are often indistinguishable from pulmonary thromboembolism (PTE). We thus aimed to accurately diagnose PAS by comparing the clinical and computed tomography pulmonary angiography (CTPA) and magnetic resonance imaging (MRI) imaging characteristics of PAS and PTE. This case-control study retrospectively enrolled 20 patients with PAS (from March 2017 to September 2022), 40 patients with central acute PTE, and 40 patients with central chronic PTE (from January 2021 to December 2022) in the China-Japan Friendship Hospital. The following clinical and imaging findings were compared between the three groups: initial symptoms; D-dimer, C-reactive protein, and N-terminal pro B-type natriuretic peptide levels; wall-eclipsing sign (WES); scope of lesion involvement; and morphological characteristics. Signal intensity was also observed on different MRI sequences. The D-dimer level in PAS was significantly lower than that in central acute PTE (P<0.001). The WES was present in 17 cases of PAS (85.0%), which was a greater proportion than that of the central acute PTE and chronic PTE groups (all P values <0.001). The involvement of the pulmonary valve or right ventricular outflow tract was observed in five PAS cases but none of the central acute PTE or chronic PTE cases (all P values =0.001). In 19 PAS cases (95.0%), the lesions grew expansively in the central pulmonary artery. The proximal margin of 18 patients with PAS (90.0%) was bulging or lobulated. Nine cases of PAS (45.0%) showed aneurysm-like dilatation (grape-like sign) of the distal pulmonary artery, representing significantly greater proportion than that of the central acute PTE and chronic PTE groups (all P values <0.001). In 37 patients with central acute PTE (92.5%), the clots were observed to be floating in the pulmonary artery lumen with saddle, tubular or polypoid shape. Eccentric filling defects attached to the pulmonary artery wall were observed in 32 cases of central chronic PTE (80.0%). On MRI, PAS lesions were hyperintense on fat-suppressed T2-weighted imaging and diffusion-weighted imaging, demonstrating heterogeneous enhancement. Comprehensive analysis of the clinical data and imaging features on CTPA and MRI can aid in the accurate differential diagnosis of PAS and PTE.

Distinct age-adjusted D-dimer threshold to rule out acute pulmonary embolism in outpatients and inpatients.

The diagnosis of acute pulmonary embolism (PE) is combinations of clinical probability assessments, plasma D-dimer (DD) test results, and/or computed tomographic pulmonary angiography (CTPA). The aim of this study is to explore the appropriate DD cutoff using the immunoturbidimetric method in outpatients and inpatients. We retrospectively enrolled 2689 patients with suspected PE between January 2014 and December 2019. All patients underwent clinical probability assessments, DD tests, and CTPA. We investigated the appropriate cutoff level for plasma DD tests in the correlation analysis and receiver operating characteristic (ROC) curves. Among all patients, 1263 were confirmed acute PE. The age-adjusted DD level was determined to be age × 10μg/L (for patients aged >50 years) in outpatients. This cutoff value resulted in a sensitivity of 96.75% and a specificity of 87.02%, with the area under the curve (AUC) of 0.908 and the number needed to treat (NNT) of 1.18. For inpatients, the age-adjusted cutoff values for the biomarker DD demonstrated poor specificity (13.34%) and NNT (9.88). However, when the DD cutoff was adjusted to 2 × the upper limit of normal (ULN), the sensitivity increased to 93.19%, while the specificity remained at 29.55%, with the AUC of 0.610 and the NNT of 4.76. The optimal DD cut-off value was 3010 μg/L (about 5 × ULN), resulting in a sensitivity of 75.22% and specificity of 61.72%, with the AUC of 0.727 and the NNT of 2.7. Using the immunoturbidimetric method to measure DD, an age-adjusted DD cutoff (age × 10μg/L, if aged >50 years) should be considered for outpatients with suspected PE. For inpatients, increasing the DD cutoff value to at least 2 × ULN yields the best test performance.

Multimodality Fusion Method Based on Multiview Subspace Clustering for Pulmonary Embolism Diagnosis.

Pulmonary embolism (PE) is an important clinical disorder that will result in lung tissue damage or low blood oxygen levels, which need early diagnosis and timely treatment. While computed tomographic pulmonary angiography (CTPA) is the gold standard to diagnose PE, previous studies have verified the effectiveness of combing CTPA and EMR data in computer-aided PE detection or diagnosis. In this paper, we proposed a multimodality fusion method based on multi-view subspace clustering guided feature selection (MSCUFS). The extracted high-dimensional image and EMR features are firstly selected and fused by the MSCUFS, and then are feed into different machine learning models with different fusion strategy to construct the PE classifier. The experiment results showed that the joint fusion strategy with MSCUFS achieved best AUROC of 0.947, surpassing other early fusion and late fusion models. The comparison between single modality and multimodality also illustrated the effectiveness of the proposed method.

Efficacy of pulse oximetry for early diagnosis of pulmonary embolism after total knee arthroplasty

IntroductionEarly diagnosis and aggressive treatment of pulmonary embolism (PE) are crucial for preventing severe complications after total knee arthroplasty (TKA). This study aimed to examine the efficacy of measuring oxygen saturation (SpO2) using a pulse oximeter for early diagnosis of PE after total knee arthroplasty (TKA).Materials and methodsWe consecutively examined 1645 patients who underwent TKA between January 2015 and November 2019. Postoperative SpO2 was measured with a pulse oximeter, which was stopped if SpO2 was maintained at ≥ 95% until postoperative day 2 (POD2). To diagnose PE, computed tomographic pulmonary angiography (CTPA) was performed for specific indications, including persistently low SpO2 < 95% (group 1), sudden decrease in SpO2 (group 2), and decrease in SpO2 after POD3 with presenting symptoms (group 3). Also, we divided the patients into unilateral, simultaneous and sequential TKA groups and compared the results with specific statistical techniques.ResultsOf the 1645 patients who underwent TKA, there were 20 patients with PE (1.2%), and symptomatic PE was observed in only 4 patients (0.24%). CTPA was performed in 58 (3.5%) patients, of whom 20 were diagnosed with PE. In groups 1 (n = 34), 2 (n = 21), and 3 (n = 3), CTPA was performed 2.4, 2.6, and 8.3 days after TKA, respectively, and 12, 8, and 0 patients were diagnosed with PE, respectively. Of the 782, 416, and 447 unilateral, simultaneous, and sequential (done in same admission with interval 1 or 2 weeks) patients with TKA, 38, 18, and 2 received CTPA, and 13, 6, and 1 were diagnosed with PE, respectively. All patients diagnosed with PE have persistently low SpO2 < 95% (group 1), or sudden decrease in SpO2 (group 2) until POD2. Of the patients diagnosed with PE, SpO2 decreased without the presentation of symptoms in 16 patients (11 and 5 from groups 1 and 2, respectively) and with the presentation of symptoms, such as mild dyspnea and chest discomfort, in 4 patients (1 and 3 from groups 1 and 2, respectively).ConclusionsMeasuring SpO2 using a pulse oximeter until POD2 was an effective method for early diagnosis of PE after TKA. No case of morbidity or mortality was observed after early diagnosis with early stage CTPA and management of PE. We recommend measuring SpO2 with a pulse oximeter for early diagnosing of PE in TKA.

Pregnancy-adapted YEARS Algorithm: A Retrospective Analysis.

Pulmonary embolism (PE) is an imperative diagnosis to make given its associated morbidity. There is no current consensus in the initial workup of pregnant patients suspected of a PE. Prospective studies have been conducted in Europe using a pregnancy-adapted YEARS algorithm, which showed safe reductions in computed tomography pulmonary angiography (CTPA) imaging in pregnant patients suspected of PE. Our objective in this study was 1)to measure the potential avoidance of CTPA use in pregnant patients if the pregnancy-adapted YEARS algorithm had been applied and 2)to serve as an external validation study of the use of this algorithm in the United States. This study was a single-system retrospective chart analysis. Criteria for inclusion in the cohort consisted of keywords: pregnant; older than 18; chief complaints of shortness of breath, chest pain, tachycardia, hemoptysis, deep vein thromboembolism (DVT), and D-dimer-from January 1, 2019- May 31,2022. We then analyzed this cohort retrospectively using the pregnancy-adapted YEARS algorithm, which includes clinical signs of a DVT, hemoptysis, and PE as the most likely diagnosis with a D-dimer assay. Patients within the cohort were then subdivided into two categories: aligned with the YEARS algorithm, or not aligned with the YEARS algorithm. Patients who did not receive a CTPA were analyzed for a subsequent diagnosis of a PE or DVT within 30 days. A total of 74 pregnant patients were included in this study. There was a PE prevalence of 2.7% (two patients). Of the 36 patients who did not require imaging by the algorithm, seven CTPA were performed. Of the patients who did not receive an initial CTPA, zero were diagnosed with PE or DVT within a 30-day follow-up. In total, 85.1% of all the patients in this study were treated in concordance with the pregnancy-adapted YEARS algorithm. The use of the pregnancy-adapted YEARS algorithm could have resulted in decreased utilization of CTPA in the workup of PE in pregnant patients, and the algorithm showed similar reductions compared to prospective studies done in Europe. The pregnancy-adapted YEARS algorithm was also shown to be similar to the clinical rationale used by clinicians in the evaluation of pregnant patients, which indicates its potential for widespread acceptance into clinical practice.

A primary pulmonary artery sarcoma masquerading pulmonary embolism: a case report and literature review

BackgroundPrimary pulmonary artery sarcoma (PAS) is an extremely rare malignant tumor with a poor prognosis. The clinical manifestations of PAS are diverse, including dyspnea, chest pain, cough, and hemoptysis. The poor prognosis is often due to delayed diagnosis caused by similarity in imaging findings with pulmonary thromboembolism (PTE). These cues of diagnosis include the “wall eclipsing sign”, lobulated bulging margins, gadolinium enhancement during MRI imaging, and FDG uptake during PET/CT imaging. However, there are still many misdiagnoses.Case presentationThis article reports a woman of reproductive age presenting with a pulmonary artery mass. The computed tomographic pulmonary angiography and positron emission tomography/computed tomography did not show obvious signs of pulmonary artery sarcoma, however, contrast-enhanced echocardiography showed moderate perfusion, which helped differentiate between pulmonary artery sarcoma and pulmonary artery thrombosis, leading to timely surgical treatment.ConclusionsPAS is a rare form of cancer that can occasionally be visually similar to PTE on radiographic images. Early diagnosis of PAS is of vital importance to the prognosis of the patients. There are several visual cues that can help differentiate between the two conditions. Additionally, contrast-enhanced echocardiography provides additional information on tumor perfusion, offering another effective approach for a prompt and accurate diagnosis.

Deep learning in computed tomography pulmonary angiography imaging: A dual-pronged approach for pulmonary embolism detection

The increasing reliance on Computed Tomography Pulmonary Angiography (CTPA) for Pulmonary Embolism (PE) diagnosis presents challenges and a pressing need for improved diagnostic solutions. The primary objective of this study is to leverage deep learning techniques to enhance the Computer Assisted Diagnosis (CAD) of PE. With this aim, we propose a classifier-guided detection approach that effectively leverages the classifier’s probabilistic inference to direct the detection predictions, marking a novel contribution in the domain of automated PE diagnosis. Our classification system includes an Attention-Guided Convolutional Neural Network (AG-CNN) that uses local context by employing an attention mechanism. This approach emulates a human expert's attention by looking at both global appearances and local lesion regions before making a decision. The classifier demonstrates robust performance on the FUMPE dataset, achieving an AUROC of 0.927, sensitivity of 0.862, specificity of 0.879, and an F1-score of 0.805 with the Inception-v3 backbone architecture. Moreover, AG-CNN outperforms the baseline DenseNet-121 model, achieving an 8.1% AUROC gain. While previous research has mostly focused on finding PE in the main arteries, our use of cutting-edge object detection models and ensembling techniques greatly improves the accuracy of detecting small embolisms in the peripheral arteries. Finally, our proposed classifier-guided detection approach further refines the detection metrics, contributing new state-of-the-art to the community: mAP50, sensitivity, and F1-score of 0.846, 0.901, and 0.779, respectively, outperforming the former benchmark with a significant 3.7% improvement in mAP50. Our research aims to elevate PE patient care by integrating AI solutions into clinical workflows, highlighting the potential of human-AI collaboration in medical diagnostics.

Deep Learning based Pulmonary Embolism Detection using Convolutional Feature Maps of CT Pulmonary Angiography Images

Pulmonary Embolism (PE) is a blood clot in the pulmonary arteries of the lungs. Currently, Computerized Tomography Pulmonary Angiography (CTPA) scans are used to diagnose this condition. However, to manually locate the presence of a PE in the scan is laborious. In this paper, the detection of PE and prediction of its features like location, Right Ventricle to Left Ventricle (RV/LV) ratio, and chronicity are automated. First, for the detection of the embolisms, image features from the RSNA Pulmonary Embolism CT (RSPECT) dataset - containing over 12,000 CTPA studies, are extracted by several pre-trained Convolutional Neural Networks (CNN) - AlexNet, Inception V3, ResNet-18, and ResNet-50. Then, various Machine Learning (ML) classifiers are trained on these features and their performances are compared. Second, for the prediction of labels, multi-label classification is performed by training these networks with Binary Cross Entropy Logits (BCE Logits) loss. The results showed that for the detection task, k-NN classifier trained on ResNet-50 features achieved the highest sensitivity of 0.98 with 1.7 false positives per scan and an AUROC score of 97.4%. This system also improved on the state-of-the-art sensitivity score by 0.0975 and AUROC score by 3.4%. For multi-label classification, ResNet-18 performed comparatively better with the best validation loss of 0.07 and weighted macro-average ROC AUC score of 0.61.

Socioeconomic status and post-covid illness trajectory

Abstract Background The associations between deprivation and illness trajectory after hospitalisation for coronavirus disease-19 (COVID-19) are uncertain. Methods A prospective, multicentre, longitudinal, cohort study involving post-COVID-19 patients enrolled in-hospital or early post-discharge (visit 1) and re-evaluated at 28-60 days post-discharge (visit 2) and in the longer term. Serial research blood tests (biomarkers), digital electrocardiography, and patient-reported outcome measures were obtained at both visits. Novel, multisystem imaging, including chest computed tomography (CT) with pulmonary and coronary angiography, cardiovascular and renal magnetic resonance imaging, was acquired at visit 2. The analysis of primary and secondary outcomes by socioeconomic status was prespecified. The Scottish Index of Multiple Deprivation (SIMD), a small-area measure of social deprivation based on domiciled post code reflecting seven factors including income, employment, education, health, access to services, crime, and housing, and categorized into general population quintiles, was used to measure social deprivation. The EQ-5D-5L, Brief Illness Perception Questionnaire (BIPQ), Patient Health Questionnaire-4 (PHQ-4) for Anxiety and Depression, and the Duke Activity Status Index (DASI) were used to assess health status. Follow-up of clinical outcomes was undertaken using electronic health records. Results Two hundred and fifty-two patients (mean±SD age 55.0 ±12.0 years, body mass index (BMI) 31.3 ±6.9 kg/m2,101 (40%) female, and 59 (23%) with diabetes) were enrolled and had follow-up completed at a median 428 (IQR 385, 538) days. Deprivation status was positively associated with BMI (p=0.0444) and diabetes (p=0.0239). One hundred and eighty-six (74%) patients reattended for investigation 28-60 days post-discharge. Lung ground glass opacity and/or consolidation (p=0.0085), obstructive coronary artery disease (p=0.0128) and renal inflammation (p=0.0421) were associated with deprivation. At 28-60 days post-discharge (n=184), health-related quality of life (EQ-5D-5L utility score, p=0.0084), illness perception, (BIPQ, p=0.0004), anxiety and depression (PHQ-4 score, p=0.0038), physical activity (DASI, p=0.002) and estimated peak oxygen consumption (ml/min/kg) (p=0.002) were worse with greater deprivation. At 3 months (n=252), deprivation status was associated with more referrals to secondary care because of ongoing COVID-19 symptoms (p=0.0438). Clinical outcomes did not associate with deprivation. Conclusion In a post-hospital COVID-19 population, socioeconomic deprivation was associated with impaired health status and secondary care episodes. Deprivation influences illness trajectory after COVID-19.

Diagnostic Yield, Radiation Exposure, and the Role of Clinical Decision Rules to Limit Computed Tomographic Pulmonary Angiography-Associated Complications.

Computed tomographic pulmonary angiography (CT-PA) is associated with significant cost, contrast, and radiation exposure. Clinical decision rules (CDRs) reduce the need for diagnostic imaging; however, their utility in the medical intensive care unit (MICU) remains unknown. We explored the diagnostic yield and complications associated with CT-PA (radiation exposure and contrast-induced acute kidney injury [AKI]) while investigating the efficacy of CDRs to reduce unnecessary testing. All CT-PAs performed in an academic MICU for 4 years were retrospectively reviewed. The Wells and revised Geneva scores (CDRs) and radiation dose per CT-PA were calculated, and the incidence of post-CT-PA AKI was recorded. A total of 439 studies were analyzed; the diagnostic yield was 11% (48 PEs). Positive CT-PAs were associated with a higher Wells score (5.8 versus 3.2, P < 0.001), but similar revised Geneva scores (6.4 versus 6.0, P = 0.32). A Wells score of ≥4 had a positive likelihood ratio of 2.1 with a negative predictive value of 98.2. More than half (88.9%) of patients with a Wells score of ≤4 developed an AKI, with 55.6% of those having recovery of renal function. There is overutilization of CT-PA in the MICU. The Wells score retains its negative predictive value in critically ill adult patients and may aid to limit radiation exposure and contrast-induced AKI in MICU.

The level of C-reactive protein in patients with acute pulmonary embolism

Background. Modern risk stratification in patients with pulmonary embolism (PE) does not consider all possible factors that may influence the course and prognosis of the disease. In view of this, it is promising to study inflammatory markers, especially C-reactive protein (CRP), for their prognostic value in PE. The purpose was to study the clinical and prognostic value of increased CRP levels in patients with PE during hospitalization. Material and methods. One hundred and three patients with diagnosis of acute PE confirmed by computed tomographic pulmonary angiography (CTPA) or by autopsy were examined, their СRP level was evaluated during hospitalization. In addition to a general clinical examination, all patients were screened for PE risk factors and risk of premature death according to the ESC 2019 guidelines. La-boratory tests included quantitative determination of CPK-MB, D-dimer and СRP in addition to basic ones. Electrocardiography, echocardiography, and CTPA were performed as part of the instrumental studies. Results. Depending on the СRP median (26 mg/l), patients were divided into two groups. Group 1 (СRP &lt; 26 mg/l) included 52 people, group 2 (СRP &gt; 26 mg/l) — 51 patients. It was found that in group 1, patients with low risk predominated (p = 0.044) and the average pulmonary embolism severity index was significantly lower (p = 0.011). In group 2, the average blood oxygen saturation (SpO2) during hospitalization was significantly lower (p = 0.004), the average parameters of the left ventricle, namely end-diastolic and end-systolic volume, were significantly greater (p = 0.045 and p = 0.043, respectively), and the ejection fraction was significantly lower (p = 0.002). Also, the average levels of leukocytes (p = 0.0003), neutrophils (p = 0.00001), urea (p = 0.008), CPK-MB (p = 0.028) and erythrocyte sedimentation rate (p = 0.012) were significantly higher in group 2. Correlation analysis revealed a reliable inverse connection between CRP levels and initial SpO2 and a direct relationship between CRP level and the size of the right atrium, CPK-MB level, and increased risk of early mortality from PE. Conclusions. Elevated CRP was found in 92 % of patients with acute PE and was associated with a significant decrease in SpO2 (p &lt; 0.004), increased left ventricular size (p &lt; 0.05), and decreased ejection fraction (p &lt; 0.003). Correlation analysis revealed a relationship between CRP level and the risk according to the pulmonary embolism severity index, SpO2, the level of CPK-MB and the size of the left atrium.

The Diagnostic Role of Lung Ultrasound and Contrast-Enhanced Ultrasound in Pulmonary Embolism.

The diagnosis of pulmonary embolism (PE) relies essentially on a probabilistic approach that requires careful clinical assessments, targeted laboratory tests, and the use of appropriate imaging tools. Nowadays, the diagnostic gold standard is computed tomographic pulmonary angiography. Lung ultrasound (LUS) can play a role in the diagnosis of PE mainly by allowing the visualization of peripheral lung infarctions. Hypoechoic, pleural-based parenchymal consolidation is the most typical and common finding of pulmonary infarction. More than 85% of infarct lesions are wedge-shaped, extending to the pleural surface and are localized to where the patient complains of pleuritic chest pain. Contrast-enhanced ultrasound can be performed in addition to basic ultrasound examination to ascertain nonvascularization of the consolidation, thus confirming that the lesion is an infarct. The aim of this narrative review is to summarize the latest evidence on the application of LUS to the diagnosis of PE, focusing purely on thoracic/lung signs.

Echocardiographic Characteristics of Pulmonary Artery Intimal Sarcoma: Comparison With CTPA.

This study examined the echocardiographic characteristics of patients with pulmonary artery intimal sarcoma (PAIS) and compared the results with those from computed tomographic pulmonary angiography (CTPA). Twenty-six (26) patients were diagnosed with PAIS at the current institution during the study period, and 23 were eligible for analysis. Echocardiography and CTPA examinations were performed in all enrolled patients. The echocardiography results showed that most lesions had expansive growth in the left pulmonary artery (PA); the right PA; or a combination of the left PA, right PA, and main PA, with extension to the pulmonary valve and/or right ventricular outflow tract. These lesions also had distinctive sieve-like echogenic signals. Echocardiography also showed that some lesions had lobulated shapes, were nearly round and echolucent or with calcifications, and moved during imaging. The lesion distribution was similar in CTPA and echocardiography (p=0.361), but CTPA was more sensitive in detection of the complete shape (p=0.023). The unique echocardiographic characteristics of PAIS, especially the "sieve sign", could help in the diagnosis of this cancer. Transthoracic echocardiography is a non-invasive technique that appears effective in detecting PAIS.