Detection Of Pulmonary Embolism Research Articles

An Enhanced Mask R-CNN Approach for Pulmonary Embolism Detection and Segmentation.

Pulmonary embolism (PE) refers to the occlusion of pulmonary arteries by blood clots, posing a mortality risk of approximately 30%. The detection of pulmonary embolism within segmental arteries presents greater challenges compared with larger arteries and is frequently overlooked. In this study, we developed a computational method to automatically identify pulmonary embolism within segmental arteries using computed tomography (CT) images. The system architecture incorporates an enhanced Mask R-CNN deep neural network trained on PE-containing images. This network accurately localizes pulmonary embolisms in CT images and effectively delineates their boundaries. This study involved creating a local data set and evaluating the model predictions against pulmonary embolisms manually identified by expert radiologists. The sensitivity, specificity, accuracy, Dice coefficient, and Jaccard index values were obtained as 96.2%, 93.4%, 96.%, 0.95, and 0.89, respectively. The enhanced Mask R-CNN model outperformed the traditional Mask R-CNN and U-Net models. This study underscores the influence of Mask R-CNN's loss function on model performance, providing a basis for the potential improvement of Mask R-CNN models for object detection and segmentation tasks in CT images.

New Diagnostic Tools for Pulmonary Embolism Detection.

The presentation of pulmonary embolism (PE) varies from asymptomatic to life-threatening, and management involves multiple specialists. Timely diagnosis of PE is based on clinical presentation, D-dimer testing, and computed tomography pulmonary angiogram (CTPA), and assessment by a Pulmonary Embolism Response Team (PERT) is critical to management. Artificial intelligence (AI) technology plays a key role in the PE workflow with automated detection and flagging of suspected PE in CTPA imaging. HIPAA-compliant communication features of mobile and web-based applications may facilitate PERT workflow with immediate access to imaging, team activation, and real-time information sharing and collaboration. In this review, we describe contemporary diagnostic tools, specifically AI, that are important in the triage and diagnosis of PE.

Evaluation of the Pulmonary Arteries on CTPA With Dual Energy CT: Objective Analysis and Subjective Preferences in a Multireader Study.

To perform qualitative and quantitative evaluation of low-monoenergetic images (50KeV) compared with conventional images (120kVp) in pulmonary embolism (PE) studies and to determine the extent and clinical relevance of these differences as well as radiologists' preferences. One hundred fifty CT examinations for PE detection conducted on a single-source dual-energy CT were retrospectively evaluated. Attenuation, contrast-to-noise-ratio, and signal-to-noise-ratio were obtained in a total of 8 individual pulmonary arteries on each exam-including both central (450/1200=37.5%) and peripheral (750/1200=62.5%) locations. Results were compared between the conventional and low-monoenergetic images. For quality assessment, 41 images containing PE were presented side-by-side as pairs of slices in both conventional and monoenergetic modes and evaluated for ease in embolus detection by 9 radiologists: cardiothoracic specialists (3), noncardiothoracic specialists (3), and residents (3). Paired samples t tests, a-parametric Wilcoxon test, McNemar test, and kappa statistics were performed. Monoenergetic images had an overall statistically significant increased average ratio of 2.09 to 2.26 ( P <0.05) for each measured vessel attenuation, with an increase in signal-to-noise ratio (23.82±9.29 vs. 11.39±3.2) and contrast-to-noise ratio (17.17±6.7 vs 7.27±2.52) ( P <0.05). Moreover, 10/150 (6%) of central pulmonary artery measurements considered suboptimal on conventional mode were considered diagnostic on the monoenergetic images (181±14.6 vs. 387.7±72.4 HU respectively, P <0.05). In the subjective evaluation, noncardiothoracic radiologists showed a preference towards low-monoenergetic images, whereas cardiothoracic radiologists did not (74.4% vs. 57.7%, respectively, P <0.05). The SNR and CNR increase on monoenergetic images may have clinical significance particularly in the setting of sub-optimal PE studies. Noncardiothoracic radiologists and residents prefer low monoenergetic images.

Shear wave elastography values of thrombus in patients with lower extremity deep vein thrombosis for pulmonary embolism detection: the ROC analysis

Rationale: Thrombosis of the iliac (IV) and femoral veins (FV) is one of the most common causes of pulmonary embolism (PE). Modern ultrasound scanners are equipped with the technology of shear wave elastography, which gives a quantitative assessment of thrombus stiffness by Young's modulus reconstruction. However, the lack of convincing data on the role of thrombus stiffness for clinical manifestations of PE hinders the active use of shear wave elastography to diagnose the risk of embolism.&#x0D; Aim: To determine the threshold values of the venous thrombus Young’s modulus for deep venous thrombosis (DVT) of the lower extremities complicated by massive PE and/or PE with acute cor pulmonale (ACP).&#x0D; Materials and methods: This was a single center cross-sectional study in 101 patients who were hospitalized with the diagnosis of acute (duration of less than 2 weeks) or subacute (from 2 weeks to 3 months) IV and FV thrombosis. Doppler ultrasound of the lower extremity veins and echocardiography were done in all patients. Forty eight patients with clinical signs of PE had chest computed tomography. The venous thrombus stiffness was assessed by shear wave elastography with the Young's modulus reconstruction. We performed the ROC analysis for mean values of the Young's modulus for proximal segments of IV and FV thrombi in patients with DVT and massive PE and ACP.&#x0D; Results: PE was diagnosed in 40.6% (26/64) of the patients hospitalized with acute DVT and in 54.1% (20/37) of those with subacute DVT. Echocardiographic signs of ACP in massive PE were found in 47.4% (9/19) of the patients, in submassive and minor PE in 55.6% (15/27). In DVT complicated with PE, the ROC analysis of the shear wave elastography results gave the following threshold values of the mean Young’s modulus for the proximal thrombus segment: for acute IV thrombosis + PE and ACP, ≤ 16.7 kPa (AUC 0.714, sensitivity 100%, specificity 42.1%), in subacute IV thrombosis + PE and APC, ≤ 23.7 kPa (0.939, 100 and 90.9%, respectively), in acute FV thrombosis + massive PE, ≥ 9.5 kPa (0.706, 100 and 50%, respectively), in subacute FV thrombosis + massive PE, ≥ 24.4 kPa (0.550, 60.0 and 68.8%, respectively).&#x0D; Conclusion: Shear wave elastography of deep vein thrombi of the lower extremities makes it possible to identify patients with PE and ACP during acute and subacute IV thrombosis and to determine massive PE in acute FV thrombosis.

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.

Radiology: Cardiothoracic Imaging Highlights 2023.

Radiology: Cardiothoracic Imaging publishes novel research and technical developments in cardiac, thoracic, and vascular imaging. The journal published many innovative studies during 2023 and achieved an impact factor for the first time since its inaugural issue in 2019, with an impact factor of 7.0. The current review article, led by the Radiology: Cardiothoracic Imaging trainee editorial board, highlights the most impactful articles published in the journal between November 2022 and October 2023. The review encompasses various aspects of coronary CT, photon-counting detector CT, PET/MRI, cardiac MRI, congenital heart disease, vascular imaging, thoracic imaging, artificial intelligence, and health services research. Key highlights include the potential for photon-counting detector CT to reduce contrast media volumes, utility of combined PET/MRI in the evaluation of cardiac sarcoidosis, the prognostic value of left atrial late gadolinium enhancement at MRI in predicting incident atrial fibrillation, the utility of an artificial intelligence tool to optimize detection of incidental pulmonary embolism, and standardization of medical terminology for cardiac CT. Ongoing research and future directions include evaluation of novel PET tracers for assessment of myocardial fibrosis, deployment of AI tools in clinical cardiovascular imaging workflows, and growing awareness of the need to improve environmental sustainability in imaging. Keywords: Coronary CT, Photon-counting Detector CT, PET/MRI, Cardiac MRI, Congenital Heart Disease, Vascular Imaging, Thoracic Imaging, Artificial Intelligence, Health Services Research © RSNA, 2024.

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.

CT pulmonary angiography in the emergency department: utilization and positivity rates during various phases of the COVID-19 pandemic.

To evaluate the trends in utilization and results of computed tomography pulmonary angiography (CTPA study) for detection of acute pulmonary embolism (PE) in the Emergency Department (ED) during different phases of COVID-19 public health emergency. We conducted a retrospective review of CTPA studies ordered through our ED in the months of March through May during five consecutive years from 2019 to 2023, designated as pre-pandemic, early, ongoing, recovery, and post-pandemic periods respectively. Collected characteristics included patient age, patient sex, and result of the study. The utilization of CTPA studies for ED patients increased during the early, ongoing, and recovery periods. CTPA study utilization in the post-pandemic period was not significantly different from the pre-pandemic period (p = 0.08). No significant difference in CTPA study utilization was noted in the other periods when stratified by age group or sex, compared to the pre-pandemic period. The positivity rate of acute PE in ED patients was not significantly different in other periods compared to the pre-pandemic period. At our institution, the utilization and positivity rates of CTPA studies for the ED patients were not significantly different in the post-pandemic period compared to the pre-pandemic period. While studies spanning a larger timeframe and involving multiple institutions are needed to test the applicability of this observation to a wider patient population beyond our defined post-pandemic period, we conclude that our study provides some confidence to the ordering provider and the radiologist in embracing the end of COVID-19 public health emergency by the WHO and the United States HHS with respect to CTPA studies.

Detection of acute pulmonary embolism using native repeated magnetic resonance imaging acquisitions under free-breathing and without respiratory or cardiac gating. A diagnostic accuracy study

ObjectivesComputed tomography pulmonary angiography (CTPA) is the gold standard diagnostic method for patients with suspected pulmonary embolism (PE), but it has its drawbacks, including exposure to ionizing radiation and iodinated contrast agent. The present study aims to evaluate the diagnostic performance of our in-house developed non-contrast MRI protocol for PE diagnosis in reference to CTPA. Methods107 patients were included, all of whom underwent MRI immediately before or within 36 hours after CTPA. Additional cases examined only with MRI and a negative result were added to reach a PE prevalence of approximately 20%. The protocol was a non-contrast 2D steady-state free precession (SSFP) sequence under free-breathing, without respiratory or cardiac gating, and repeated five times to capture the vessels at different breathing/cardiac phases. The MRIs were blinded and read by two radiologists and the results were compared to CTPA. ResultsOf the 243 patients included, 47 were positive for PE. Readers 1 and 2 demonstrated 89% and 87% sensitivity, 100% specificity, 98% accuracy and Cohen’s kappa of 0.88 on patient level. In the per embolus comparison, readers 1 and 2 detected, 60 and 59/61 (98, 97%) proximal, 101 and 94/113 (89, 83%) segmental, and 5 and 2/32 (16, 6%) subsegmental emboli, resulting in 81 and 75% sensitivity respectively. ConclusionThe repeated 2D SSFP can reliably be used for the diagnosis of acute PE at the proximal and segmental artery levels.

External validation of the RSNA 2020 pulmonary embolism detection challenge winning deep learning algorithm

PurposeTo evaluate the diagnostic performance and generalizability of the winning DL algorithm of the RSNA 2020 PE detection challenge to a local population using CTPA data from two hospitals. Materials and MethodsConsecutive CTPA images from patients referred for suspected PE were retrospectively analysed. The winning RSNA 2020 DL algorithm was retrained on the RSNA-STR Pulmonary Embolism CT (RSPECT) dataset. The algorithm was tested in hospital A on multidetector CT (MDCT) images of 238 patients and in hospital B on spectral detector CT (SDCT) and virtual monochromatic images (VMI) of 114 patients. The output of the DL algorithm was compared with a reference standard, which included a consensus reading by at least two experienced cardiothoracic radiologists for both hospitals. Areas under the receiver operating characteristic curve (AUCs) were calculated. Sensitivity and specificity were determined using the maximum Youden index. ResultsAccording to the reference standard, PE was present in 73 patients (30.7%) in hospital A and 33 patients (29.0%) in hospital B. For the DL algorithm the AUC was 0.96 (95% CI 0.92–0.98) in hospital A, 0.89 (95% CI 0.81–0.94) for conventional reconstruction in hospital B and 0.87 (95% CI 0.80–0.93) for VMI. ConclusionThe RSNA 2020 pulmonary embolism detection on CTPA challenge winning DL algorithm, retrained on the RSPECT dataset, showed high diagnostic accuracy on MDCT images. A somewhat lower performance was observed on SDCT images, which suggest additional training on novel CT technology may improve generalizability of this DL algorithm.

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.

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.

Optimisation of virtual monoenergetic reconstructions for the diagnosis of pulmonary embolism using photon-counting detector computed tomography angiography

PurposeComputed tomography (CT) pulmonary angiography is considered the gold standard for pulmonary embolism (PE) diagnosis, relying on the discrimination between contrast and embolus. Photon-counting detector CT (PCD-CT) generates monoenergetic reconstructions through energy-resolved detection. Virtual monoenergetic images (VMI) at low keV can be used to improve pulmonary artery opacification. While studies have assessed VMI for PE diagnosis on dual-energy CT (DECT), there is a lack of literature on optimal settings for PCD-CT-PE reconstructions, warranting further investigation.Material and methodsTwenty-five sequential patients who underwent PCD-CT pulmonary angiography for suspicion of acute PE were retrospectively included in this study. Quantitative metrics including signal-to-noise ratio (SNR) and contrast-to-noise (CNR) ratio were calculated for 4 VMI values (40, 60, 80, and 100 keV). Qualitative measures of diagnostic quality were obtained for proximal to distal pulmonary artery branches by 2 cardiothoracic radiologists using a 5-point modified Likert scale.ResultsSNR and CNR were highest for the 40 keV VMI (49.3 ± 22.2 and 48.2 ± 22.1, respectively) and were inversely related to monoenergetic keV. Qualitatively, 40 and 60 keV both exhibited excellent diagnostic quality (mean main pulmonary artery: 5.0 ± 0 and 5.0 ± 0; subsegmental pulmonary arteries 4.9 ± 0.1 and 4.9 ± 0.1, respectively) while distal segments at high (80-100) keVs had worse quality.Conclusions40 keV was the best individual VMI for the detection of pulmonary embolism by quantitative metrics. Qualitatively, 40-60 keV reconstructions may be used without a significant decrease in subjective quality. VMIs at higher keV lead to reduced opacification of the distal pulmonary arteries, resulting in decreased image quality.

Uncertainty quantification in computed tomography pulmonary angiography.

Computed tomography (CT) imaging of the thorax is widely used for the detection and monitoring of pulmonary embolism (PE). However, CT images can contain artifacts due to the acquisition or the processes involved in image reconstruction. Radiologists often have to distinguish between such artifacts and actual PEs. We provide a proof of concept in the form of a scalable hypothesis testing method for CT, to enable quantifying uncertainty of possible PEs. In particular, we introduce a Bayesian Framework to quantify the uncertainty of an observed compact structure that can be identified as a PE. We assess the ability of the method to operate under high-noise environments and with insufficient data.

Establishment of machine learning-based tool for early detection of pulmonary embolism

Background and objectivesPulmonary embolism (PE) is a complex disease with high mortality and morbidity rate, leading to increasing society burden. However, current diagnosis is solely based on symptoms and laboratory data despite its complex pathology, which easily leads to misdiagnosis and missed diagnosis by inexperienced doctors. Especially, CT pulmonary angiography, the gold standard method, is not widely available. In this study, we aim to establish a rapid and accurate screening model for pulmonary embolism using machine learning technology. Importantly, data required for disease prediction are easily accessed, including routine laboratory data and medical record information of patients. MethodsWe extracted features from patients' routine laboratory results and medical records, including blood routine, biochemical group, blood coagulation routine and other test results, as well as symptoms and medical history information. Samples with a feature loss rate greater than 0.8 were deleted from the original database. Data from 4723 cases were retained, 231 of which were positive for pulmonary embolism. 50 features were retained through the positive and negative statistical hypothesis testing which was used to build the predictive model. In order to avoid identification as majority-class samples caused by the imbalance of sample proportion, we used the method of Synthetic Minority Oversampling Technique (SMOTE) to increase the amount of information on minority samples. Five typical machine learning algorithms were used to model the screening of pulmonary embolism, including Support Vector Machines, Logistic Regression, Random Forest, XGBoost, and Back Propagation Neural Networks. To evaluate model performance, sensitivity, specificity and AUC curve were analyzed as the main evaluation indicators. Furthermore, a baseline model was established using the characteristics of the pulmonary embolism guidelines as a comparison model. ResultsWe found that XGBoost showed better performance compared to other models, with the highest sensitivity and specificity (0.99 and 0.99, respectively). Moreover, it showed significant improvement in performance compared to the baseline model (sensitivity and specificity were 0.76 and 0.76 respectively). More important, our model showed low missed diagnosis rate (0.46) and high AUC value (0.992). Finally, the calculation time of our model is only about 0.05 s to obtain the possibility of pulmonary embolism. ConclusionsIn this study, five machine learning classification models were established to assess the likelihood of patients suffering from pulmonary embolism, and the XGBoost model most significantly improved the precision, sensitivity, and AUC for pulmonary embolism screening. Collectively, we have established an AI-based model to accurately predict pulmonary embolism at early stage.

Multisystem inflammatory syndrome complicated by pulmonary embolism in a child

Purpose - to present a clinical case of a particular complication of post-COVID multisystem inflammatory syndrome (MIS) - pulmonary embolism (PE) which developed due to primary hereditary thrombophilia in a child for better understanding of the MIS evolution and prognosis in children (MIS-C). Case report. In an 11-year-old boy who previously had no hemorrhagic manifestations, the first symptoms of the disease occurred in the form of fever and a hemorrhagic rash on the lower extremities. Later, he developed signs of respiratory failure, his condition worsened, and bilateral community-acquired viral pneumonia caused by COVID-19 was diagnosed. The child presented with post-COVID MIS manifested as PE, which caused further genetic examinations for hereditary thrombophilia. Primary thrombophilia was detected (F2 gene - prothrombin (20210 G&gt;A) D68.5). Concomitant hereditary pathology was probably the reason for a severe course of the infection and the development of a complication in the form of PE requiring intensive and long-term anticoagulant therapy. Conclusions. In case of PE detection, especially in young patients, examinations to confirm or rule out hereditary or acquired thrombophilia are required, that defines recurrent venous thromboembolism prevention programs. This clinical case report is a contribution to the study on the issues of MIS-C, defining links between pulmonary complications (transient or persistent) and serious sequelae in the future. The research was carried out in accordance with the principles of the Helsinki Declaration. The informed consent of the patient was obtained for conducting the studies. No conflict of interests was declared by the authors.

Use of a Deep Learning Algorithm for Detection and Triage of Cancer-associated Incidental Pulmonary Embolism

Use of a Deep Learning Algorithm for Detection and Triage of Cancer-associated Incidental Pulmonary Embolism

Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution

PurposeThe purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. Materials and methodsUsing a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. ResultsQuantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850–0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810–0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668–0.760) and of 0.723 (95% CI: 0.668–0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. ConclusionThis study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without manual outlining.

We present a novel computer algorithm to automatically detect and segment pulmonary embolisms (PEs) on computed tomography pulmonary angiography (CTPA). This algorithm is based on deep learning but does not require manual outlines of the PE regions. Given a CTPA scan, both intra- and extra-pulmonary arteries were firstly segmented. The arteries were then partitioned into several parts based on size (radius). Adaptive thresholding and constrained morphological operations were used to identify suspicious PE regions within each part. The confidence of a suspicious region to be PE was scored based on its contrast in the arteries. This approach was applied to the publicly available RSNA Pulmonary Embolism CT Dataset (RSNA-PE) to identify three-dimensional (3-D) PE negative and positive image patches, which were used to train a 3-D Recurrent Residual U-Net (R2-Unet) to automatically segment PE. The feasibility of this computer algorithm was validated on an independent test set consisting of 91 CTPA scans acquired from a different medical institute, where the PE regions were manually located and outlined by a thoracic radiologist (>18 years' experience). An R2-Unet model was also trained and validated on the manual outlines using a 5-fold cross-validation method. The CNN model trained on the high-confident PE regions showed a Dice coefficient of 0.676±0.168 and a false positive rate of 1.86 per CT scan, while the CNN model trained on the manual outlines demonstrated a Dice coefficient of 0.647±0.192 and a false positive rate of 4.20 per CT scan. The former model performed significantly better than the latter model (p<0.01). The promising performance of the developed PE detection and segmentation algorithm suggests the feasibility of training a deep learning network without dedicating significant efforts to manual annotations of the PE regions on CTPA scans.