scholarly journals Performance of a 3D convolutional neural network in the detection of hypoperfusion at CT pulmonary angiography in patients with chronic pulmonary embolism: a feasibility study

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Tuomas Vainio ◽  
Teemu Mäkelä ◽  
Sauli Savolainen ◽  
Marko Kangasniemi
Keyword(s):  
Neural Network ◽  
Computed Tomography ◽  
Pulmonary Embolism ◽  
Convolutional Neural Network ◽  
Strong Predictor ◽  
Pulmonary Angiography ◽  
Threshold Method ◽  
Disease Extent ◽  
Prediction Probability ◽  
Chronic Pulmonary Embolism

Abstract Background Chronic pulmonary embolism (CPE) is a life-threatening disease easily misdiagnosed on computed tomography. We investigated a three-dimensional convolutional neural network (CNN) algorithm for detecting hypoperfusion in CPE from computed tomography pulmonary angiography (CTPA). Methods Preoperative CTPA of 25 patients with CPE and 25 without pulmonary embolism were selected. We applied a 48%–12%–40% training-validation-testing split (12 positive and 12 negative CTPA volumes for training, 3 positives and 3 negatives for validation, 10 positives and 10 negatives for testing). The median number of axial images per CTPA was 335 (min–max, 111–570). Expert manual segmentations were used as training and testing targets. The CNN output was compared to a method in which a Hounsfield unit (HU) threshold was used to detect hypoperfusion. Receiver operating characteristic area under the curve (AUC) and Matthew correlation coefficient (MCC) were calculated with their 95% confidence interval (CI). Results The predicted segmentations of CNN showed AUC 0.87 (95% CI 0.82–0.91), those of HU-threshold method 0.79 (95% CI 0.74–0.84). The optimal global threshold values were CNN output probability ≥ 0.37 and ≤ -850 HU. Using these values, MCC was 0.46 (95% CI 0.29–0.59) for CNN and 0.35 (95% CI 0.18–0.48) for HU-threshold method (average difference in MCC in the bootstrap samples 0.11 (95% CI 0.05–0.16). A high CNN prediction probability was a strong predictor of CPE. Conclusions We proposed a deep learning method for detecting hypoperfusion in CPE from CTPA. This model may help evaluating disease extent and supporting treatment planning.

scholarly journals Deep Learning Algorithm Trained with COVID-19 Pneumonia Also Identifies Immune Checkpoint Inhibitor Therapy-Related Pneumonitis

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 652 ◽  
Author(s):  
Carlo Augusto Mallio ◽  
Andrea Napolitano ◽  
Gennaro Castiello ◽  
Francesco Maria Giordano ◽  
Pasquale D'Alessio ◽  
...  
Keyword(s):  
Neural Network ◽  
Computed Tomography ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitor ◽  
Learning Algorithm ◽  
Checkpoint Inhibitor ◽  
Deep Convolutional Neural Network ◽  
Deep Learning Algorithm

Background: Coronavirus disease 2019 (COVID-19) pneumonia and immune checkpoint inhibitor (ICI) therapy-related pneumonitis share common features. The aim of this study was to determine on chest computed tomography (CT) images whether a deep convolutional neural network algorithm is able to solve the challenge of differential diagnosis between COVID-19 pneumonia and ICI therapy-related pneumonitis. Methods: We enrolled three groups: a pneumonia-free group (n = 30), a COVID-19 group (n = 34), and a group of patients with ICI therapy-related pneumonitis (n = 21). Computed tomography images were analyzed with an artificial intelligence (AI) algorithm based on a deep convolutional neural network structure. Statistical analysis included the Mann–Whitney U test (significance threshold at p < 0.05) and the receiver operating characteristic curve (ROC curve). Results: The algorithm showed low specificity in distinguishing COVID-19 from ICI therapy-related pneumonitis (sensitivity 97.1%, specificity 14.3%, area under the curve (AUC) = 0.62). ICI therapy-related pneumonitis was identified by the AI when compared to pneumonia-free controls (sensitivity = 85.7%, specificity 100%, AUC = 0.97). Conclusions: The deep learning algorithm is not able to distinguish between COVID-19 pneumonia and ICI therapy-related pneumonitis. Awareness must be increased among clinicians about imaging similarities between COVID-19 and ICI therapy-related pneumonitis. ICI therapy-related pneumonitis can be applied as a challenge population for cross-validation to test the robustness of AI models used to analyze interstitial pneumonias of variable etiology.

scholarly journals CORRELATION OF D-DIMER LEVEL WITH THE PRESENCE AND SEVERITY OF PULMONARY EMBOLISM ON COMPUTED TOMOGRAPHY PULMONARY ANGIOGRAPHY

2020 ◽  
pp. 33-34
Author(s):  
Mantavya Patel ◽  
Sanjay Paliwal ◽  
Rachit Saxena
Keyword(s):  
Computed Tomography ◽  
Pulmonary Embolism ◽  
Early Diagnosis ◽  
Pulmonary Angiography ◽  
Clinical Suspicion ◽  
Early Prediction ◽  
Computed Tomography Pulmonary Angiography ◽  
Negative Prediction ◽  
D Dimer

Introduction: Early diagnosis of pulmonary embolism can reduce morbidity and motility. D-dimer is well known parameter having high negative prediction value. This study focused on role of D-dimer in early prediction of presence and severity of pulmonary embolism. Material and Methods: Thirty patients with clinical suspicion of pulmonary embolism along with high D-dimer value were included in this study. All selected patients underwent computed tomography pulmonary angiography assessment. D-dimer value was correlated with presence and proximity of pulmonary embolism. Results: Out of thirty selected patients 50% had pulmonary embolism on computed tomography pulmonary angiography assessment. D-dimer value correlated well with presence and proximity of pulmonary embolism. Conclusion: D-dimer value more than 4000 ng/ml had high positive prediction value (79%) in suspected clinical cases. Value more than 8000 ng/ml further improve value to nearly 100% in suspected cases.

Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box

2015 ◽  
Vol 26 (1) ◽  
pp. 195-202 ◽  
Author(s):  
Francesco Ciompi ◽  
Bartjan de Hoop ◽  
Sarah J. van Riel ◽  
Kaman Chung ◽  
Ernst Th. Scholten ◽  
...  
Keyword(s):  
Neural Network ◽  
Computed Tomography ◽  
Convolutional Neural Network ◽  
Automatic Classification

Pulmonary arterial hypertension and acute and chronic thromboembolism

ESC CardioMed ◽  
2018 ◽  
pp. 406-409
Author(s):  
Thomas Henzler
Keyword(s):  
Computed Tomography ◽  
Pulmonary Embolism ◽  
Pulmonary Hypertension ◽  
Pulmonary Arterial Hypertension ◽  
Arterial Hypertension ◽  
Imaging Modality ◽  
Chronic Thromboembolic Pulmonary Hypertension ◽  
Right Ventricular Dysfunction ◽  
Chronic Pulmonary Embolism ◽  
Pulmonary Arterial

Pulmonary arterial hypertension (PAH) and acute and chronic pulmonary embolism represent severe cardiovascular diseases with a high mortality if left undiagnosed and untreated. Computed tomography of the chest plays a pivotal role in the diagnosis of all three disorders. In acute pulmonary embolism, computed tomography pulmonary angiography has become the gold-standard imaging modality due to its high diagnostic accuracy, cost-effectiveness, 24-hour availability at most institutions, as well as the ability to diagnose alternative chest pathologies and right ventricular dysfunction within a single examination. In PAH, computed tomography of the chest is also deeply embedded within the diagnostic algorithm in order to exclude other causes of pulmonary hypertension, such as structural lung disease and chronic thromboembolic pulmonary hypertension of left heart disease. This article intends to provide a short overview on imaging techniques and characteristic findings in PAH, as well as acute and chronic pulmonary embolism.

An artificial intelligence algorithm that identifies middle turbinate pneumatisation (concha bullosa) on sinus computed tomography scans

2020 ◽  
Vol 134 (4) ◽  
pp. 328-331 ◽  
Author(s):  
P Parmar ◽  
A-R Habib ◽  
D Mendis ◽  
A Daniel ◽  
M Duvnjak ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Computed Tomography ◽  
Diagnostic Accuracy ◽  
Convolutional Neural Network ◽  
Middle Turbinate ◽  
Concha Bullosa ◽  
Computed Tomography Images ◽  
Computed Tomography Scans ◽  
Neural Network Algorithm

AbstractObjectiveConvolutional neural networks are a subclass of deep learning or artificial intelligence that are predominantly used for image analysis and classification. This proof-of-concept study attempts to train a convolutional neural network algorithm that can reliably determine if the middle turbinate is pneumatised (concha bullosa) on coronal sinus computed tomography images.MethodConsecutive high-resolution computed tomography scans of the paranasal sinuses were retrospectively collected between January 2016 and December 2018 at a tertiary rhinology hospital in Australia. The classification layer of Inception-V3 was retrained in Python using a transfer learning method to interpret the computed tomography images. Segmentation analysis was also performed in an attempt to increase diagnostic accuracy.ResultsThe trained convolutional neural network was found to have diagnostic accuracy of 81 per cent (95 per cent confidence interval: 73.0–89.0 per cent) with an area under the curve of 0.93.ConclusionA trained convolutional neural network algorithm appears to successfully identify pneumatisation of the middle turbinate with high accuracy. Further studies can be pursued to test its ability in other clinically important anatomical variants in otolaryngology and rhinology.

Sign in / Sign up

Export Citation Format

Share Document