Computed Tomography Pulmonary Angiography Images Research Articles

Effects of inlet boundary conditions on blood flow and thrombosis modelling in patients with chronic thromboembolic pulmonary hypertension

To investigate the impact of patient-specific boundary conditions (BC) on blood flow and thrombosis modelling for patients with chronic thromboembolic pulmonary hypertension (CTEPH), three types of BCs were utilized to construct CTEPH models based on computed tomography pulmonary angiography images. First BC type is the patient-specific velocity profiles at the main pulmonary artery using phase contrast MRI (PC-MRI). The other two simplified types are the pulsatile BC and steady BC, which are obtained by spatially and temporally averaging the PC-MRI BC. Hemodynamic features including helical density, time-averaged wall shear stress (TAWSS) and oscillatory shear index (OSI), and thrombosis were compared for the three types BCs. The results indicated that, compared to the MRI BC, steady BC overestimated helical density and TAWSS in the pulmonary arteries by approximately 63.1% and 60%, respectively. The impact of simplified pulsatile BC on TAWSS and OSI in most regions of the pulmonary arteries was negligible with differences within 5%. Regarding thrombosis, the area predicted under pulsatile BC was approximately 80% smaller than that under PC-MRI BC. In conclusion, compared to PC-MRI BC, steady inlet BC tend to overestimate hemodynamic parameters, while pulsatile inlet BC yield similar wall shear stress based on parameters in most regions of the pulmonary artery. Patient-specific PC-MRI inlet BC should be used for accurate predictions of helical flow pattern and thrombus formation.

A review of the use of CT pulmonary angiography in pregnant and postpartum women at an academic centre.

Pulmonary embolism (PE) is a common cause of maternal death during pregnancy and the puerperium yet data on its prevalence in middle-income countries is lacking. We examined the medical records and CTPA (computed tomography pulmonary angiography) images of 67 women in an obstetric high care unit during pregnancy and the puerperium. We aimed to determine the prevalence of PE in a high-risk obstetric population undergoing CTPA, assess associated clinical features in this cohort, and determine the prevalence of alternative CT findings. CTPA detected PE in 11 women (16.42%) and alternative CT findings in 46 (68.6%). Women with PE had a lower systolic blood pressure than those without PE (P = 0.001). Multiple gestation, preterm rupture of membranes, and gestational diabetes were linked to higher PE prevalence. This study, set in an upper middle-income country, demonstrated a higher CTPA yield for PE and alternative diagnoses than in international literature, emphasising context-specific assessments.

The Interpretation Of Computed Tomography Pulmonary Angiography Evaluation Of Compliance Between Emergency Medical Assistants And Radiologists

SUMMARY lntroduction: Computed tomography pulmonary angiography (CTPA) is an effective method far the evaluation of patients with suspected pulmonary thromboembolism (PTE) and should be interpreted quickly and accurately. We aimed ta determine the agreement between emergency medicine assistants (EMAs) and radiology assistants (RA) and specialists (RS) in the evaluation of CTPA Materials and Methods: 11 EMAs, one RA and one RS participated in the study. 100 CTPA images were re-reported. The participating RA evaluated 100 CTPAs and 11 EMAs evaluated 20 randomised CTPAs aut of 100. The Kappa statistic was used ta assess agreement, and the Douglas G. Altman classifıcation (K

Enhancing Pulmonary Embolism Detection in COVID-19 Patients Through Advanced Deep Learning Techniques.

The intersection of COVID-19 and pulmonary embolism (PE) has posed unprecedented challenges in medical diagnostics. The critical nature of PE and its increased incidence during the pandemic underline the need for improved detection methods. This study evaluates the effectiveness of advanced deep learning techniques in enhancing PE detection in post-COVID-19 patients through Computed Tomography Pulmonary Angiography (CTPA) scans. Using a dataset of 746 anonymized CTPA images from 25 patients, we fine-tuned the state-of-the-art Ultralytics YOLOv8 object detection model, which was trained on 676 images with 1,517 annotated bounding boxes and validated on 70 images with 108 bounding boxes. After 200 epochs of training, which lasted approximately 1.021 hours, the YOLOv8 model demonstrated significant diagnostic proficiency, achieving a mean Average Precision (mAP) of 0.683 at an IoU threshold of 0.50 and a mAP of 0.246 at the IoU range of 0.50:0.95 in the validation dataset. Notably, the model reached a maximum precision of 0.85949 and a maximum recall of 0.81481, though these metrics were observed in separate epochs. These findings emphasize the model's potential for high diagnostic accuracy and offer a promising direction for deploying AI tools in clinical settings, significantly contributing to healthcare innovation and patient care post-pandemic.

CT Imaging Findings of Pulmonary Artery Stenosis: A Pictorial Review.

Pulmonary artery stenosis represents a group of disorders involving main, branch or peripheral pulmonary arteries with pain, dyspnea, hemoptysis or even no symptoms. Early diagnosis and timely intervention are crucial for reducing mortality, but timely diagnosis is challenging due to the non-specific symptoms. Computed tomography pulmonary angiography (CTPA) is useful in the diagnosis because it can provide more details about abnormal changes in the lumen, vessel wall and adjacent mediastinal structures. Congenital and acquired pulmonary artery anomalies have some characteristics on CTPA, which can be useful for differential diagnosis. Awareness of these conditions is important for radiologists. This pictorial review provides an overview of CTPA imaging features of pulmonary artery stenosis.

The Role of Advanced Post-processing Techniques in Computed Tomography Pulmonary Angiography for the Accurate Diagnosis of Pulmonary Thromboembolism: A Retrospective Study.

Background Computed tomography pulmonary angiography (CTPA) isthe standard diagnostic tool for evaluating patients with suspected pulmonary thromboembolism (PTE) in many institutions. This condition, whether acute or chronic, results in both partial and complete intraluminal filling defects, which exhibit sharp interfaces with intravascular contrast material. Acute PTE that leads to complete arterial occlusion may cause the affected artery to appear enlarged. Chronic PTE often manifests as complete occlusive disease in vessels that are smaller than the adjacent patent vessels. CT imaging with iodinated contrast medium is crucial for many CT applications, including vascular CT angiography and CTPA. A comprehensive review of a case necessitates an integrated approach known as volume visualization, wherein the entire case is treated as a volume of information to be thoroughly reviewed. Advanced post-processing 3D CT techniques, such as maximum intensity projection (MIP), volume rendering (VR), and minimum intensity projection (MinIP) images, are essential for the detailed detection and assessment of the pulmonary vasculature. Materials and methods In this retrospective study, data from 50 patients with suspected PTE were analyzed over a six-month period from March 15 to August 30, 2023, at Saveetha Medical College and Hospital. Patients were selected based on previously recorded clinical symptoms and elevated D-dimer levels. CTPA images, acquired using multi-detector CT imaging with iodinated contrast, were reviewed. Various post-processing techniques were employed, including multiplanar reconstruction (MPR), MIP, MinIP, and VR. The aim of this study was to evaluate the effectiveness of CTPA combined with advanced post-processing techniques in improving early detection, reducing diagnostic time, and increasing accuracy through the detailed visualization of the pulmonary arterial vasculature. Results The study included patients aged from 10 years to70 years, with the highest prevalence of PTE in the 21-35-year age group (46%). Males constituted 56% of the cases. CTPA with advanced post-processing techniques revealed filling defects in 90% of patients, confirming PTE. MPR, MIP, MinIP, and VR effectively highlighted anatomical structures and thrombi, enhancing diagnostic accuracy. These techniques demonstrated high accuracy in identifying PTE, emphasizing their critical role in the early diagnosis and management of thromboembolic events. Conclusion The findings of the study revealed a relatively high incidence of PTE especially in the 21-35-year age group with a slight male predominance. Thesignificant majority of the patients (90%) had filling defects on their CTPA scan. CTPA, in conjunction with the use of post-processing techniques, the localization of thromboembolism sites, as well as the measurement of thrombus width and length, and the calculation of the percentage of blockage were achieved more easily. This facilitatedaccurate diagnosis, leading to improved patient outcomes.

Short-term mortality prediction in acute pulmonary embolism: Radiomics values of skeletal muscle and intramuscular adipose tissue.

Acute pulmonary embolism (APE) is a potentially life-threatening disorder, emphasizing the importance of accurate risk stratification and survival prognosis. The exploration of imaging biomarkers that can reflect patient survival holds the potential to further enhance the stratification of APE patients, enabling personalized treatment and early intervention. Therefore, in this study, we develop computed tomography pulmonary angiography (CTPA) radiomic signatures for the prognosis of 7- and 30-day all-cause mortality in patients with APE. Diagnostic CTPA images from 829 patients with APE were collected. Two hundred thirty-four features from each skeletal muscle (SM), intramuscular adipose tissue (IMAT) and both tissues combined (SM+IMAT) were calculated at the level of thoracic vertebra 12. Radiomic signatures were derived using 10 times repeated three-fold cross-validation on the training data for SM, IMAT and SM+IMAT for predicting 7- and 30-day mortality independently. The performance of the radiomic signatures was then evaluated on held-out test data and compared with the simplified pulmonary embolism severity index (sPESI) score, a well-established biomarker for risk stratification in APE. Predictive accuracy was assessed by the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI), sensitivity and specificity. The radiomic signatures based on IMAT and a combination of SM and IMAT (SM+IMAT) achieved moderate performance for the prediction of 30-day mortality on test data (IMAT: AUC=0.68, 95% CI [0.57-0.78], sensitivity=0.57, specificity=0.73; SM+IMAT: AUC=0.70, 95% CI [0.60-0.79], sensitivity=0.74, specificity=0.54). Radiomic signatures developed for predicting 7-day all-cause mortality showed overall low performance. The clinical signature, that is, sPESI, achieved slightly better performance in terms of AUC on test data compared with the radiomic signatures for the prediction of both 7- and 30-day mortality on the test data (7days: AUC=0.73, 95% CI [0.67-0.79], sensitivity=0.92, specificity=0.16; 30days: AUC=0.74, 95% CI [0.66-0.82], sensitivity=0.97, specificity=0.16). We developed and tested radiomic signatures for predicting 7- and 30-day all-cause mortality in APE using a multicentric retrospective dataset. The present multicentre work shows that radiomics parameters extracted from SM and IMAT can predict 30-day all-cause mortality in patients with APE.

Value of computed tomography pulmonary angiography measurements in predicting 30-day mortality among patients with acute pulmonary embolism

PurposeLate diagnosis is associated with high mortality rates in acute pulmonary embolism (PE), so early diagnosis and risk assessment are crucial. We aim to evaluate computed tomography pulmonary angiography measurements to identify relationships with 30-day mortality in patients with pulmonary embolism. This study investigated the utility of computed tomography pulmonary angiography (CTPA) measures in determining 30-day PE-related mortality and identified various echocardiographic, demographic, and clinical variables that were independently associated with short-term mortality in patients with acute PE.Material and methodsThis retrospective study examined data from July 2018 to April 2023. A total of 118 patients were included in the study. Clinical and demographic characteristics, laboratory findings, echocardiographic data, and CTPA images were retrieved from the electronic database and patient charts.ResultsThe rate of 30-day mortality was 14.41%. Deceased patients were significantly older than survivors (73.53 ± 14.17 vs. 60.23 ± 17.49 years; <i>p</i> = 0.004), but the sex distribution was similar. In multivariable logistic regression, having received radiotherapy for malignancy, high pulmonary artery obstruction index % (> 46.2), high left pulmonary artery diameter (> 23.9 mm), and high coronary artery calcification score (> 5.5) were independently associated with mortality.ConclusionsThese results reveal specific parameters that can assist acute PE management by enabling the identification of critical events. Despite promising results in predicting short-term mortality in acute PE, further prospective cohort studies are needed to confirm the results of the present study.

Beyond pulmonary embolism: Alternative diagnosis and incidental findings on CT pulmonary angiography in sickle cell disease.

Sickle cell disease (SCD) is a genetic hematological disorder associated with severe complications, such as vaso-occlusive crises, acute chest syndrome (ACS), and an increased risk of thromboembolic events, including pulmonary embolism (PE). The diagnosis of PE in SCD patients presents challenges due to the overlapping symptoms with other pulmonary conditions. Our previous study revealed that nearly 96% of computed tomography pulmonary angiography (CTPA) scans in SCD patients were negative for PE, highlighting a gap in understanding the significance of CTPA findings when PE is absent. In this retrospective follow-up study conducted at the Salmaniya Medical Complex in Bahrain, we examined SCD patients with HbSS genotypes who underwent CTPA from January 1, 2018, to December 31, 2021, for suspected PE, but the results were negative. The aim of this study was to identify alternative diagnoses and incidental findings from CTPA scans. Experienced radiologists reviewed the CTPA images and reports to assess potential alternative diagnoses and incidental findings, incorporating an additional analysis of chest X-rays to evaluate the diagnostic value of CTPA. Incidental findings were classified based on their location and clinical significance. Among the 230 evaluated SCD patients (average age 39.7 years; 53% male) who were CTPA negative for PE, 142 (61.7%) had identifiable alternative diagnoses, primarily pneumonia (49.1%). Notably, 88.0% of these alternative diagnoses had been previously suggested by chest radiographs. Furthermore, incidental findings were noted in 164 (71.3%) patients, with 11.0% deemed clinically significant, necessitating immediate action, and 87.8% considered potentially significant, requiring further assessment. Notable incidental findings included thoracic abnormalities such as cardiomegaly (12.2%) and an enlarged pulmonary artery (11.3%), as well as upper abdominal pathologies such as hepatomegaly (19.6%), splenomegaly (20.9%), and gallstones (10.4%). This study underscores the limited additional diagnostic yield of CTPA for identifying alternative diagnoses to PE in SCD patients, with the majority of diagnoses, such as pneumonia, already suggested by chest radiographs. The frequent incidental findings, most of which necessitate further evaluation, highlight the need for a cautious and tailored approach to using CTPA in the SCD population.

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.

Computerized Tomography Pulmonary Angiography Image Simulation using Cycle Generative Adversarial Network from Chest CT imaging in Pulmonary Embolism Patients

This study primarily focused on developing a system to generate simulated computed tomography pulmonary angiography (CTPA) images for pulmonary embolism diagnosis and aiding medical practitioners gain a more intuitive understanding of the occurrence of pulmonary embolism (PE) in diagnosis. Compared to existing methods, this system provides a non-invasive and cost-effective way to identify patients with possible pulmonary embolism. The research methodology employed the use of CycleGAN architecture to simulate CTPA images and additional implement classifier modulus to enhance ability to restore pulmonary vessel features, using computed tomography (CT) images from 22 patients and their corresponding CTPA images as training data. The experimental and simulation results provide a new approach to clinical diagnosis, which can assist physicians in the complex screening process, allowing physicians to assess whether a patient needs to undergo detailed testing for CTPA, improving the speed of detection of PE and significantly reducing the number of undetected patients.

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.

RV size may predict death in unstable patients with PE.

Pulmonary emboli (PE) is a life threatening condition that discovered in many patients only "post mortem". Sub massive and massive PE that led to hemodynamic collapse characterized by right ventricular (RV) dysfunction, leading to a higher risk of death. To assess the ability to predict in hospital death of patients with acute PE, using a non-gated computed tomography pulmonary angiography (CTPA), based on the dimensions of the right ventricle. A retrospective study that analyzed CTPA images of patients admitted with acute PE during the years 2012-2017. The cohort study included 300 patients with documented acute PE, among them 255 hospitalized in medical (non-intensive care unit) wards, 45 were hospitalized in an intensive care unit (ICU). Among the 45 patients admitted to the ICU 8% died. Larger RV diameters predicted mortality (OR = 10.14, 95% CI [1.09-93.86]) as well as lower systolic and diastolic blood pressure measurements (p = 0.001 and 0.01). Among the 255 patients admitted to the Internal Medicine Ward 7% died. Older age (p = 0.028), sepsis and cancer (both p < 0.001), high WBCs count (p < 0.001), and renal failure (p < 0.001) predicted death. Lower blood pressure (systolic and diastolic) (p < 0.001, 0.008), older age (p < 0.007), sepsis (p < 0.001), cancer (p = 0.006), higher WBCs count (p < 0.001), and impaired renal function (p < 0.001) predicted death in patients admitted with acute PE. Clinical parameters and hematological parameters could predict death of patients admitted with acute PE. RV diameter, measured by the non-ECG gated CTPA, had an additive predictive value for patients who admitted to the ICU.

Probability-Based Two-Stage CNN for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiography

Pulmonary embolism (PE) can impede the normal flow of blood, which can result in reduced oxygen levels in vital organs and be life-threatening. Therefore, early detection and treatment of PE can effectively reduce mortality. Computed tomography pulmonary angiography (CTPA) is the clearest and most immediate tool available for PE diagnosis. With an increase in the CTPA image quality and number of slices, physician fatigue associated with interpreting these images during the diagnostic process has also increased. Therefore, this study proposes a modified two-stage convolutional neural network-based approach to automatically detect areas suspected of containing PE in CTPA images to reduce the burden of diagnosis on doctors. The main functions for eliminating false positives include principal component analysis, enlarged feature map (EFM), and probability-based anchor point extraction (PAE). Experimental results showed that although EFM can slightly improve the accuracy for small-object detection, it significantly increases the time required for training. PAE can reduce the training time and slightly improve detection accuracy. But the simultaneous use of EFM and PAE can significantly increase sensitivity (10.57%) with an increase of only 29 min in the training time.

Diagnostic Yield of CT Pulmonary Angiogram in the Diagnosis of Pulmonary Embolism and Its Predictive Factors.

Introduction Computed tomography pulmonary angiography (CTPA) is the reference investigation of choice to diagnose pulmonary embolism (PE). Nevertheless, the use of CTPA should be weighed against its risks, such as radiation and contrast-induced nephropathy. We aim to assess the yield of CTPA in diagnosing PE at a tertiary centre in Malaysia. We also identify predictive factors associated with the yield of CTPA in this cohort. Methods This was a cross-sectional study involving all patients who had had CTPA done at Hospital Tengku Ampuan Afzan, Kuantan, Malaysia, from January 1, 2021, to November 30, 2021. All patients' records were retrieved and reviewed. CTPA images were retrieved from the Radiology Information System (RIS) and Picture Archiving and Communication System (PACS). They were double-reviewed by the authors, with the initial reports redacted from reporting radiologists to prevent reporting bias. The predictive factors were determined using simple logistic regression and multiple logistic regression. Results A total of 351 CTPAs were reviewed, of which 93 were found to be positive for PE, giving rise to an overall CTPA yield of 26.5%. Upon simple logistic regression, factors such as gender, discipline, history of trauma, presence of COVID-19 infection, and pneumonia were found to be associated with positive CTPA. Upon multiple logistic regression, male patients were found to have a higher chance of positive CTPA results. On the other hand, patients with COVID-19 infection and pneumonia have a lower chance of positive results in CTPA. Conclusion The yield of CTPA in diagnosing PE at our institution was acceptable at 26.5%. Upon multiple logistic regression, patients with COVID-19 infection and pneumonia were more likely to have a negative CTPA result, highlighting the need for clinicians to be more prudent in requesting CTPAs in these patients.

Detection and quantification of pulmonary embolism with artificial intelligence: The SFR 2022 artificial intelligence data challenge

PurposeIn 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence. Materials and methodsThe data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks. ResultsA total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784. ConclusionThis multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.

Comparison of Dual-Energy Computed Tomography Pulmonary Angiography-Derived Contrast Enhancement with Standard Dual-Energy Pulmonary Angiography in Diagnosing Subsegmental Pulmonary Embolism: A Prospective Study.

Objective In this study, we compare the diagnostic accuracy of dual-energy (DE) computed tomography pulmonary angiography (CTPA) derived contrast enhancement (DECTPA, CTPA images with iodine maps) with standard dual-energy pulmonary angiography (SCTPA) for diagnosis of subsegmental pulmonary embolism in the cases with clinical suspicion of acute pulmonary embolism (APE). Materials and Methods We included 50 cases with clinical suspicion of APE that were referred for CTPA. All the patients underwent CTPA in the dual-energy protocol. Two radiologists evaluated the images. The first radiologist interpreted the SCTPA images (vascular images) and the second radiologist interpreted the DECTPA (CTPA images with iodine maps) for findings of APE. We calculated the sensitivity, specificity, and negative predictive value of DECTPA vis-à-vis SCTPA images. Results The DECTPA with the advantage of iodine map utilization yielded higher detection of thrombi in peripheral subsegmental arteries (72 vs. 99; p = - 0.001) as compared to the SCTPA images by identification of 18 new perfusion defects (interquartile range [IQR]: 0-1) that were consistent with APE. Filling defects were identified in 27 (IQR: 0-4) more subsegmental arteries supplying these 18 areas, which were not detected on SCTPA alone. These 18 perfusion defects were identified in 13 cases. In these 13 cases, 4 new cases were diagnosed that were negative on CTPA ( p = -0.125). In the evaluation of the APE, sensitivity and specificity were calculated and it was found that DECTPA showed 100% sensitivity and 86% specificity with 100% negative predictive value in the detection of thrombi as compared to the routine CTPA. Conclusion DECTPA has higher sensitivity and negative predictive value in the detection of the subsegmental perfusion defect identification as compared to SCTPA.

Capnography derived breath variability analysis feasibility and its importance for pulmonary embolism prediction

Capnography is a method that monitors the concentration of Carbon Dioxide (CO2) in patients’ respiratory gases. Its outcome, i.e., the capnographic curve shows CO2 levels plotted against time. The measurement of the carbon dioxide that is released at the end of an exhaled breath is called end-tidal carbon dioxide (etCO2). Such monitoring provides information about CO2 production and clearance. This paper hypothesizes that the capnographic curve could be useful in everyday clinical practice for differential diagnosis. Specifically, a computational analysis method was developed and a pilot study was conducted to determine if capnography can be used as a predictive indicator for Pulmonary Embolism (PE). To verify whether the respiratory pattern may have clinical significance, an assessment was carried out in patients in whom PE was diagnosed and those in whom PE was suspected but ultimately excluded. The age, gender, end-tidal-CO2 (etCO2), respiratory rate, and symptoms at the admission of patients who had a chest CT angiography were noted. Classification and regression tree analysis were designed and used to identify variables predictive for PE. A total of 120 patients (60 female, 60 males) aged 64.3 +/- 18.0 admitted to the Emergency Department had the computed tomography pulmonary angiography imaging study: 60 with positive PE and 60 with negative PE results. In patients with etCO2>=32 mmHg was a negative predictor for PE. In those with the etCO2 < 32 mmHg was predictive for PE. The developed model indicates that it could assist in predicting PE based on the etCO2 values.

Auto-Detection of Motion Artifacts on CT Pulmonary Angiograms with a Physician-Trained AI Algorithm.

Purpose: Motion-impaired CT images can result in limited or suboptimal diagnostic interpretation (with missed or miscalled lesions) and patient recall. We trained and tested an artificial intelligence (AI) model for identifying substantial motion artifacts on CT pulmonary angiography (CTPA) that have a negative impact on diagnostic interpretation. Methods: With IRB approval and HIPAA compliance, we queried our multicenter radiology report database (mPower, Nuance) for CTPA reports between July 2015 and March 2022 for the following terms: "motion artifacts", "respiratory motion", "technically inadequate", and "suboptimal" or "limited exam". All CTPA reports were from two quaternary (Site A, n = 335; B, n = 259) and a community (C, n = 199) healthcare sites. A thoracic radiologist reviewed CT images of all positive hits for motion artifacts (present or absent) and their severity (no diagnostic effect or major diagnostic impairment). Coronal multiplanar images from 793 CTPA exams were de-identified and exported offline into an AI model building prototype (Cognex Vision Pro, Cognex Corporation) to train an AI model to perform two-class classification ("motion" or "no motion") with data from the three sites (70% training dataset, n = 554; 30% validation dataset, n = 239). Separately, data from Site A and Site C were used for training and validating; testing was performed on the Site B CTPA exams. A five-fold repeated cross-validation was performed to evaluate the model performance with accuracy and receiver operating characteristics analysis (ROC). Results: Among the CTPA images from 793 patients (mean age 63 ± 17 years; 391 males, 402 females), 372 had no motion artifacts, and 421 had substantial motion artifacts. The statistics for the average performance of the AI model after five-fold repeated cross-validation for the two-class classification included 94% sensitivity, 91% specificity, 93% accuracy, and 0.93 area under the ROC curve (AUC: 95% CI 0.89-0.97). Conclusion: The AI model used in this study can successfully identify CTPA exams with diagnostic interpretation limiting motion artifacts in multicenter training and test datasets. Clinical relevance: The AI model used in the study can help alert technologists about the presence of substantial motion artifacts on CTPA, where a repeat image acquisition can help salvage diagnostic information.

Radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation after pulmonary endarterectomy.

This study aimed to construct a radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation (POAF) after pulmonary endarterectomy (PEA) in patients with chronic thromboembolic pulmonary hypertension (CTEPH). We reviewed the preoperative computed tomography pulmonary angiography images of CTEPH patients who underwent PEA at our institution between December 2016 and May 2022. Patients were divided into training/validation and testing cohorts by stratified random sampling in a ratio of 7:3. Radiomics features were selected by using intra- and inter-class correlation coefficient, redundancy analysis, and Least Absolute Shrinkage and Selection Operator algorithm to construct the radiomics signature. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical practicability of the radiomics signature. Two hundred-times stratified five-fold cross-validation was applied to assess the reliability and robustness of the radiomics signature. A total of 93 patients with CTEPH were included in this study, including 23 patients with POAF and 70 patients without POAF. Five of the 1,218 radiomics features were finally selected to construct the radiomics signature. The radiomics signature showed good discrimination with an AUC of 0.804 (95%CI: 0.664-0.943) in the training/validation cohort and 0.728 (95% CI: 0.503-0.953) in the testing cohorts. The average AUC of 200 times stratified five-fold cross-validation was 0.804 (95%CI: 0.801-0.806) and 0.807 (95%CI: 0.798-0.816) in the training and validation cohorts, respectively. The calibration curve showed good agreement between the predicted and actual observations. Based on the DCA, the radiomics signature was found to be clinically significant and useful. The radiomics signature achieved good discrimination, calibration, and clinical practicability. As a potential imaging biomarker, the radiomics signature of epicardial adipose tissue (EAT) may provide a reference for the risk assessment and individualized treatment of CTEPH patients at high risk of developing POAF after PEA.