scholarly journals Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
Average Precision ◽  
True Negative ◽  
True Negative Rate ◽  
Ct Test ◽  
The Mean

In this paper we compare the models for the detection and segmentation of Ground Glass Opacity and Consolidation in chest CT scans. These lesion areas are often associated both with common pneumonia and COVID-19. We train a Mask R-CNN model to segment these areas with high accuracy using three approaches: merging masks for these lesions into one, deleting the mask for Consolidation, and using both masks separately. The best model achieves the mean average precision of 44.68% using MS COCO criterion for instance segmentation across all accuracy thresholds. The classification model, COVID-CT-Mask-Net, which learns to predict the presence of COVID-19 vs common pneumonia vs control, achieves the 93.88% COVID-19 sensitivity, 95.64% overall accuracy, 95.06% common pneumonia sensitivity and 96.91% true negative rate on the COVIDx-CT test split (21192 CT scans) using a small fraction of the training data. We also analyze the effect of Non-Maximum Suppression of overlapping object predictions, both on the segmentation and classification accuracy. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
Average Precision ◽  
True Negative ◽  
True Negative Rate ◽  
Ct Test ◽  
The Mean

Abstract In this paper we compare the models for the detection and segmentation of Ground Glass Opacity and Consolidation in chest CT scans. These lesion areas are often associated both with common pneumonia and COVID-19. We train a Mask R-CNN model to segment these areas with high accuracy using three approaches: merging masks for these lesions into one, deleting the mask for Consolidation, and using both masks separately. The best model achieves the mean average precision of 44.68% using MS COCO criterion for instance segmentation across all accuracy thresholds. The classification model, COVID-CT-Mask-Net, which learns to predict the presence of COVID-19 vs common pneumonia vs control, achieves the 93.88% COVID-19 sensitivity, 95.64% overall accuracy, 95.06% common pneumonia sensitivity and 96.91% true negative rate on the COVIDx-CT test split (21192 CT scans) using a small fraction of the training data. We also analyze the effect of Non-Maximum Suppression of overlapping object predictions, both on the segmentation and classification accuracy. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
Average Precision ◽  
True Negative ◽  
True Negative Rate ◽  
Ct Test ◽  
The Mean

Abstract In this paper we compare the models for the detection and segmentation of Ground Glass Opacity and Consolidation in chest CT scans. These lesion areas are often associated both with common pneumonia and COVID-19. We train a Mask R-CNN model to segment these areas with high accuracy using three approaches: merging masks for these lesions into one, deleting the mask for Consolidation, and using both masks separately. The best model achieves the mean average precision of 44.68% using MS COCO criterion for instance segmentation across all accuracy thresholds. The classification model, COVID-CT-Mask-Net, which learns to predict the presence of COVID-19 vs common pneumonia vs control, achieves the 93.88% COVID-19 sensitivity, 95.64% overall accuracy, 95.06% common pneumonia sensitivity and 96.91% true negative rate on the COVIDx-CT test split (21192 CT scans) using a small fraction of the training data. We also analyze the effect of Non-Maximum Suppression of overlapping object predictions, both on the segmentation and classification accuracy. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT Scans

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Single Layer ◽  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
True Negative ◽  
Training Time ◽  
Regional Features ◽  
Similar Solutions

Abstract We introduce a lightweight Mask R-CNN model that segments areas with the Ground Glass Opacity and Consolidation in chest CT scans. The model uses truncated ResNet18 and ResNet34 nets with a single layer of Feature Pyramid Network as a backbone net, thus substantially reducing the number of the parameters and the training time compared to similar solutions using deeper networks. Without any data balancing and manipulations, and using only a small fraction of the training data, COVID-CT-Mask-Net classification model with 6.12M total and 600K trainable parameters derived from Mask R-CNN, achieves 91.35% COVID-19 sensitivity, 91.63% Common Pneumonia sensitivity, 96.98% true negative rate and 93.95% overall accuracy on COVIDx-CT dataset (21191 images). We also present a thorough analysis of the regional features critical to the correct classification of the image. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT Scans

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Single Layer ◽  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
True Negative ◽  
Training Time ◽  
Regional Features ◽  
Similar Solutions

Abstract We introduce a lightweight Mask R-CNN model that segments areas with the Ground Glass Opacity and Consolidation in chest CT scans. The model uses truncated ResNet18 and ResNet34 nets with a single layer of Feature Pyramid Network as a backbone net, thus substantially reducing the number of the parameters and the training time compared to similar solutions using deeper networks. Without any data balancing and manipulations, and using only a small fraction of the training data, COVID-CT-Mask-Net classification model with 6.12M total and 600K trainable parameters derived from Mask R-CNN, achieves 91.35% COVID-19 sensitivity, 91.63% Common Pneumonia sensitivity, 96.98% true negative rate and 93.95% overall accuracy on COVIDx-CT dataset (21191 images). We also present a thorough analysis of the regional features critical to the correct classification of the image. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT Scans

2020 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Single Layer ◽  
Ground Glass Opacity ◽  
Chest Ct ◽  
Training Data ◽  
Classification Model ◽  
Ct Scans ◽  
True Negative ◽  
Training Time ◽  
Regional Features ◽  
Similar Solutions

AbstractWe introduce a lightweight Mask R-CNN model that segments areas with the Ground Glass Opacity and Consolidation in chest CT scans. The model uses truncated ResNet18 and ResNet34 nets with a single layer of Feature Pyramid Network as a backbone net, thus substantially reducing the number of the parameters and the training time compared to similar solutions using deeper networks. Without any data balancing and manipulations, and using only a small fraction of the training data, COVID-CT-Mask-Net classification model with 6.12M total and 600K trainable parameters derived from Mask R-CNN, achieves 91.35% COVID-19 sensitivity, 91.63% Common Pneumonia sensitivity, 96.98% true negative rate and 93.95% overall accuracy on COVIDx-CT dataset (21191 images). We also present a thorough analysis of the regional features critical to the correct classification of the image. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.

scholarly journals One Shot Model For The Prediction of COVID-19 and Lesions Segmentation In Chest CT Scans Through The Affinity Among Lesion Mask Features

2021 ◽  
Author(s):  
Aram Ter-Sarkisov
Keyword(s):  
Source Code ◽  
Chest Ct ◽  
Training Data ◽  
Ct Scans ◽  
Affinity Matrix ◽  
True Negative ◽  
Data Manipulation ◽  
True Negative Rate ◽  
Affinity Model ◽  
The Relationship

AbstractWe introduce a model that segments lesions and predicts COVID-19 from chest CT scans through the derivation of an affinity matrix between lesion masks. The novelty of the methodology is based on the computation of the affinity between the lesion masks’ features extracted from the image. First, a batch of vectorized lesion masks is constructed. Then, the model learns the parameters of the affinity matrix that captures the relationship between features in each vector. Finally, the affinity is expressed as a single vector of pre-defined length. Without any complicated data manipulation, class balancing tricks, and using only a fraction of the training data, we achieve a 91.74% COVID-19 sensitivity, 85.35% common pneumonia sensitivity, 97.26% true negative rate and 91.94% F1-score. Ablation studies show that the method can quickly generalize to new datasets. All source code, models and results are publicly available on https://github.com/AlexTS1980/COVID-Affinity-Model.

Abstract P105: Identification of Cardioembolic Sources and Myocardial Injury in Acute Ischemic Stroke With Delayed-Phase, Low-Dose Chest Ct by Means of a Dual-Layer Spectral Ct Scanner

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Gaston Rodriguez Granillo ◽  
Juan José Cirio ◽  
Ivan Lylyk ◽  
Nicolas Perez ◽  
Maria L Caballero ◽  
...  
Keyword(s):  
Myocardial Injury ◽  
Low Dose ◽  
Late Enhancement ◽  
Chest Ct ◽  
Ct Scans ◽  
Ct Scanner ◽  
Spectral Ct ◽  
Thrombotic Complications ◽  
The Mean ◽  
Delayed Phase

Background: The COVID-19 pandemic has promoted adaptations in diagnostic algorithms. We explored the feasibility and accuracy of delayed phase (DP) chest computed tomography (CT) performed immediately after brain CT perfusion (CTP) for the identification of thrombotic complications and myocardial fibrosis among patients admitted with acute ischemic stroke (AIS). Methods: Since July, we have incorporated the use of low dose chest CT scans using a spectral CT scanner in all patients admitted with AIS, encouraging acquisitions, five min after brain CTP. All scans were non gated and comprised low dose chest CT scans, without additional contrast. Using virtual monochromatic imaging and iodine maps, we evaluated the presence of thrombotic complications, myocardial late enhancement, and myocardial extracellular volume (ECV), as a surrogate of edema and interstitial fibrosis. Results: We included 22 patients. The mean age was 66.2±19.6 years. In 5 patients, a cardioembolic (CE) source was later identified by transesophageal echocardiogram (TEE), [left atrial appendage (LAA) thrombus, n=1], transthoracic echocardiogram with agitated saline injection (patent foramen ovale n=2), or by EKG (atrial fibrillation). Seven patients further underwent either TEE or cardiac CT to identify CE sources. DP non gated chest CT had a sensitivity and specificity of 100% to identify CE sources, 1 LAA thrombus correctly detected. Chest CT identified pulmonary thromboembolism (PE), later confirmed with CT angiography. Chest CT identified myocardial late enhancement in 16 patients (80% in CE vs. 71% in non CE, p=0.68), myocardial fat in 1, and coronary calcification in 77% [with 2.6±2.2 vs 3.8±3.6 coronary calcified segments in CE vs. non CE strokes, p=0.36). The mean ECV was 35±4% in CE vs 32±6% in non CE strokes (p=0.17). The 2 patients with a positive PCR test for COVID-19 showed evidence of myocardial late iodine enhancement, and incremented ECV of the septal wall (38% and 40%, respectively). Conclusions: In this pilot study, DP, non ECG gated, low dose chest CT scan performed 5 min after brain CTP with a spectral scanner; enabled straightforward identification of CE sources among patients with AIS. This approach allowed detection of PE and myocardial injury.

scholarly journals Amiodarone-induced pulmonary toxicity

2011 ◽  
Vol 1 (1) ◽  
pp. 6
Author(s):  
Junichi Ochi ◽  
Minoru Ohkouchi ◽  
Yoshikazu Tsukada ◽  
Shinichiro Tominaga ◽  
Satoshi Takayama ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Medical Records ◽  
Lung Biopsy ◽  
Pulmonary Toxicity ◽  
Ground Glass Opacity ◽  
Chest Ct ◽  
Chest Computed Tomography ◽  
Ct Findings ◽  
The Mean ◽  
Foamy Macrophages

Amiodarone-induced pulmonary toxicity is a critical and potentially fatal side effect of amiodarone. Our study was designed to reveal its clinical features, including KL-6, as an interstitial marker. The medical records of eight patients (five men and three women) with amiodarone-induced pulmonary toxicity, who had been referred to our hospital, were examined. The mean age at the initiation of amiodarone was 48 years (range, 54-87 years) and mean duration of medication prior to the development of pulmonary toxicity was 18 months (range, 7-33 months). Serum KL-6 was elevated in six of the eight patients with a range of 525-2915 U/mL. Chest computed tomography (CT) findings showed non-segmental consolidation and/or ground glass opacity. Foamy macrophages were found in bronchoalveolar lavage (BAL) fluids of all examined patients and in transbronchial lung biopsy (TBLB) specimens in half of the examined patients. We concluded that serum KL-6, chest CT findings, and foamy macrophages in BAL fluids and TBLB specimens will be helpful for the diagnosis of amiodarone-induced pulmonary toxicity.

scholarly journals The halo sign: HRCT findings in 85 patients

2016 ◽  
Vol 42 (6) ◽  
pp. 435-439 ◽  
Author(s):  
Giordano Rafael Tronco Alves ◽  
◽  
Edson Marchiori ◽  
Klaus Irion ◽  
Carlos Schuler Nin ◽  
...  
Keyword(s):  
Immune Status ◽  
Ground Glass Opacity ◽  
Diagnostic Value ◽  
Chest Ct ◽  
Ct Scans ◽  
Pulmonary Lesions ◽  
Halo Sign ◽  
Immunosuppressed Patients ◽  
Primary Neoplasm ◽  
Immunocompetent Patients

ABSTRACT Objective: The halo sign consists of an area of ground-glass opacity surrounding pulmonary lesions on chest CT scans. We compared immunocompetent and immunosuppressed patients in terms of halo sign features and sought to identify those of greatest diagnostic value. Methods: This was a retrospective study of CT scans performed at any of seven centers between January of 2011 and May of 2015. Patients were classified according to their immune status. Two thoracic radiologists reviewed the scans in order to determine the number of lesions, as well as their distribution, size, and contour, together with halo thickness and any other associated findings. Results: Of the 85 patients evaluated, 53 were immunocompetent and 32 were immunosuppressed. Of the 53 immunocompetent patients, 34 (64%) were diagnosed with primary neoplasm. Of the 32 immunosuppressed patients, 25 (78%) were diagnosed with aspergillosis. Multiple and randomly distributed lesions were more common in the immunosuppressed patients than in the immunocompetent patients (p < 0.001 for both). Halo thickness was found to be greater in the immunosuppressed patients (p < 0.05). Conclusions: Etiologies of the halo sign differ markedly between immunocompetent and immunosuppressed patients. Although thicker halos are more likely to occur in patients with infectious diseases, the number and distribution of lesions should also be taken into account when evaluating patients presenting with the halo sign.

Sign in / Sign up

Export Citation Format

Share Document