Imaging of acute pulmonary embolism: an update

Moore, Alastair; Wachsmann, Jason; Chamarthy, Murthy R.; Panjikaran, Lloyd Devassy; Tanabe, Yuji; Rajiah, Prabhakar

doi:10.21037/cdt.2017.12.01

Cited by 196 publications

(177 citation statements)

References 121 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…Further exacerbating this signal-to-noise problem are the extreme inter-image and interclass variance unique to CTPA studies caused by a reliance on timing of intravenous contrast injection protocol and patient compliance with breath holding instructions; the variations in breathing motion and timing of contrast bolus injection lead to artifacts and increased noise. 18 Lastly, generalization across institutions particularly in the setting of varying CT scanner models and reconstruction methods present another difficult problem in generalization for automated diagnosis.…”

Section: Introductionmentioning

confidence: 99%

PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

et al. 2020

View full text Add to dashboard Cite

Pulmonary embolism (PE) is a life-threatening clinical problem and computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosis. Prompt diagnosis and immediate treatment are critical to avoid high morbidity and mortality rates, yet PE remains among the diagnoses most frequently missed or delayed. In this study, we developed a deep learning model-PENet, to automatically detect PE on volumetric CTPA scans as an end-to-end solution for this purpose. The PENet is a 77-layer 3D convolutional neural network (CNN) pretrained on the Kinetics-600 dataset and fine-tuned on a retrospective CTPA dataset collected from a single academic institution. The PENet model performance was evaluated in detecting PE on data from two different institutions: one as a hold-out dataset from the same institution as the training data and a second collected from an external institution to evaluate model generalizability to an unrelated population dataset. PENet achieved an AUROC of 0.84 [0.82-0.87] on detecting PE on the hold out internal test set and 0.85 [0.81-0.88] on external dataset. PENet also outperformed current state-of-the-art 3D CNN models. The results represent successful application of an end-to-end 3D CNN model for the complex task of PE diagnosis without requiring computationally intensive and time consuming preprocessing and demonstrates sustained performance on data from an external institution. Our model could be applied as a triage tool to automatically identify clinically important PEs allowing for prioritization for diagnostic radiology interpretation and improved care pathways via more efficient diagnosis.npj Digital Medicine (2020) 3:61 ; https://doi.

show abstract

Section: Introductionmentioning

confidence: 99%

PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In view of the above, it was concluded that the D-dimer may be used as test for prognosis of PE in combination with clinical probability and CT pulmonary angiography that is considered as the gold standard for diagnosing a suspected case of PE. 13 Conclusion PE, though serious clinical problem, is often underrecognized and underdiagnosed all over the world. Diagnosis of PE is more difficult than treatment.…”

Section: Discussionmentioning

confidence: 99%

Application of D-Dimer in Prognosis of Pulmonary Embolism

Gupta

Dhadwad

Gurjar

et al. 2019

IJRSMS

View full text Add to dashboard Cite

Introduction Pulmonary embolism (PE) is a relatively common cardiovascular emergency. It can lead to a variety of outcomes, from potentially reversible right ventricular failure (by occluding the pulmonary arterial bed) to eventual death. The diagnosis of PE is often missed due to its nonspecific clinical presentation. Materials and Methods This is a descriptive cross-sectional study conducted at tertiary care center in India from October 1, 2016 to September 30, 2018, which includes 36 cases of PE. Institutional ethics committee clearance was obtained before start of the study. Written and informed consent was obtained from all patients. Patients were informed regarding purpose, procedures, risks, and benefits of the study in their own vernacular language. Results The age-wise distribution of patients in this study showed that most patients were up to 40 years amounting to 58.4% of cases. Sex-wise distribution also showed that most patients were male (66.7%). Fifty percent of the patients had no thrombosis on Color Doppler findings of the involved limb, and 31.25% had superficial venous thrombosis. Blood investigation revealed that 94.4% patients had troponin negative and 94.4% had D-dimer positive. This study also attempted to correlate the D-dimer findings and Well's score. It can be seen that as per Well's score, 13 patients were with high probability, 18 with moderate probability, and 5 with low probability. Conclusion This study states that D-dimer assays are highly sensitive and have a low rate of false-negative results. The assays have been found safe and effective when the clinical probability of PE is low. When the D-dimer result is negative in patients with low clinical probability of having PE, the presence of acute PE can be safely ruled out without diagnostic imaging.

show abstract

“…17 Bedside-focused ultrasound performed by trained personnel is increasingly being utilized in acute care setting and can provide an immediate assessment of RV size and function, especially in patients with high-clinical suspicion who demonstrate an enlarged and poorly contracting RV who could be rapidly identified and managed accordingly. 18,19…”

Section: Diagnostic Evaluationmentioning

confidence: 99%

“…PE may result in right heart strain, especially in the case of a "saddle embolus"; RV strain/dilatation, hypokinesis (McConnell sign-RV free wall hypokinesia/ akinesia with preserved or hyperkinetic apical segment wall motion), and elevated right atrial pressure. 9,14,18 It can also cause right heart failure and cardiogenic shock due to obstruction. Echocardiography can help determine the severity of RV strain and the need for thrombolysis.…”

Section: Prognostic Tools To Assess Riskmentioning

confidence: 99%

Acute Pulmonary Embolism: Contemporary Approach to Diagnosis, Risk-Stratification, and Management

et al. 2019

View full text Add to dashboard Cite

Pulmonary embolism (PE) affects over 300,000 individuals each year in the United States and is associated with substantial morbidity and mortality. Improvements in the diagnostic performance and availability of computed tomographic pulmonary angiography and D-dimer testing have facilitated the evaluation of patients with suspected PE. High clinical suspicion is required in those with risk factors and/or those that manifest signs or symptoms of venous thromboembolic disease, with validated clinical risk scores such as the Wells and modified Wells score or the PE rule-out criteria helpful in estimating the likelihood for PE. For those with confirmed PE, patients should be categorized and triaged according to the presence or absence of shock or hypotension. Normotensive patients can be further risk-stratified using validated prognostic risk scores, as well as by using imaging and cardiac biomarkers, with those having either signs of right ventricular dysfunction on imaging studies and/or abnormal cardiac biomarkers categorized as being at intermediate-risk and requiring close monitoring and hospital admission. Early discharge and/or home therapy are possible in those that do not manifest any high-risk features. The initial treatment for most patients that are stable consists of anticoagulation, with advanced therapies such as thrombolysis, catheter-based therapies, or surgical embolectomy deferred for those at high risk. Given the heterogeneous presentations of PE and various management strategies available, the development of multidisciplinary PE response teams has emerged to help facilitate decision-making in these patients.

show abstract

Imaging of acute pulmonary embolism: an update

Cited by 196 publications

References 121 publications

PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

Application of D-Dimer in Prognosis of Pulmonary Embolism

Acute Pulmonary Embolism: Contemporary Approach to Diagnosis, Risk-Stratification, and Management

Contact Info

Product

Resources

About