scholarly journals COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing

2021 ◽  
pp. 100709
Author(s):  
Md. Kamrul Hasan ◽  
Md. Tasnim Jawad ◽  
Kazi Nasim Imtiaz Hasan ◽  
Sajal Basak Partha ◽  
Md. Masum Al Masba ◽  
...  
Keyword(s):  
Chest Ct ◽  
Ct Scans ◽  
3D Cnn

scholarly journals Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans

2020 ◽  
Author(s):  
Xin He ◽  
Shihao Wang ◽  
Shaohuai Shi ◽  
Xiaowen Chu ◽  
Jiangping Tang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Health Care Professionals ◽  
Data Augmentation ◽  
Model Performance ◽  
Chest Ct ◽  
Ct Scans ◽  
Data Sets ◽  
Learning Models ◽  
3D Cnn ◽  
Novel Coronavirus

AbstractCOVID-19 pandemic has spread all over the world for months. As its transmissibility and high pathogenicity seriously threaten people’s lives, the accurate and fast detection of the COVID-19 infection is crucial. Although many recent studies have shown that deep learning based solutions can help detect COVID-19 based on chest CT scans, there lacks a consistent and systematic comparison and evaluation on these techniques. In this paper, we first build a clean and segmented CT dataset called Clean-CC-CCII by fixing the errors and removing some noises in a large CT scan dataset CC-CCII with three classes: novel coronavirus pneumonia (NCP), common pneumonia (CP), and normal controls (Normal). After cleaning, our dataset consists of a total of 340,190 slices of 3,993 scans from 2,698 patients. Then we benchmark and compare the performance of a series of state-of-the-art (SOTA) 3D and 2D convolutional neural networks (CNNs). The results show that 3D CNNs outperform 2D CNNs in general. With extensive effort of hyperparameter tuning, we find that the 3D CNN model DenseNet3D121 achieves the highest accuracy of 88.63% (F1-score is 88.14% and AUC is 0.940), and another 3D CNN model ResNet3D34 achieves the best AUC of 0.959 (accuracy is 87.83% and F1-score is 86.04%). We further demonstrate that the mixup data augmentation technique can largely improve the model performance. At last, we design an automated deep learning methodology to generate a lightweight deep learning model MNas3DNet41 that achieves an accuracy of 87.14%, F1-score of 87.25%, and AUC of 0.957, which are on par with the best models made by AI experts. The automated deep learning design is a promising methodology that can help health-care professionals develop effective deep learning models using their private data sets. Our Clean-CC-CCII dataset and source code are available at:https://github.com/arthursdays/HKBU HPML COVID-19.

scholarly journals Cross-sectional analysis of follow-up chest MRI and chest CT scans in patients previously affected by COVID-19

2021 ◽  
Author(s):  
Martina Pecoraro ◽  
Stefano Cipollari ◽  
Livia Marchitelli ◽  
Emanuele Messina ◽  
Maurizio Del Monte ◽  
...  
Keyword(s):  
Chest Ct ◽  
Ct Scans ◽  
Imaging Biomarker ◽  
Cross Sectional ◽  
Mri Scans ◽  
Magnetic Resonance Imaging Mri ◽  
Sectional Analysis ◽  
Ct And Mri ◽  
Interlobular Septal Thickening

Abstract Purpose The aim of the study was to prospectively evaluate the agreement between chest magnetic resonance imaging (MRI) and computed tomography (CT) and to assess the diagnostic performance of chest MRI relative to that of CT during the follow-up of patients recovered from coronavirus disease 2019. Materials and methods Fifty-two patients underwent both follow-up chest CT and MRI scans, evaluated for ground-glass opacities (GGOs), consolidation, interlobular septal thickening, fibrosis, pleural indentation, vessel enlargement, bronchiolar ectasia, and changes compared to prior CT scans. DWI/ADC was evaluated for signal abnormalities suspicious for inflammation. Agreement between CT and MRI was assessed with Cohen’s k and weighted k. Measures of diagnostic accuracy of MRI were calculated. Results The agreement between CT and MRI was almost perfect for consolidation (k = 1.00) and change from prior CT (k = 0.857); substantial for predominant pattern (k = 0.764) and interlobular septal thickening (k = 0.734); and poor for GGOs (k = 0.339), fibrosis (k = 0.224), pleural indentation (k = 0.231), and vessel enlargement (k = 0.339). Meanwhile, the sensitivity of MRI was high for GGOs (1.00), interlobular septal thickening (1.00), and consolidation (1.00) but poor for fibrotic changes (0.18), pleural indentation (0.23), and vessel enlargement (0.50) and the specificity was overall high. DWI was positive in 46.0% of cases. Conclusions The agreement between MRI and CT was overall good. MRI was very sensitive for GGOs, consolidation and interlobular septal thickening and overall specific for most findings. DWI could be a reputable imaging biomarker of inflammatory activity.

scholarly journals CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans

2021 ◽  
pp. 1-1
Author(s):  
Tanvir Mahmud ◽  
Md Awsafur Rahman ◽  
Shaikh Anowarul Anowarul Fattah ◽  
Sun-Yuan Kung
Keyword(s):  
Chest Ct ◽  
Ct Scans ◽  
Lesion Segmentation ◽  
Decoder Architecture

scholarly journals Hierarchical Prediction of Registration Misalignment using a Convolutional LSTM: Application to Chest CT Scans

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Hessam Sokooti ◽  
Sahar Yousefi ◽  
Mohamed S. Elmahdy ◽  
Boudewijn P.F. Lelieveldt ◽  
Marius Staring
Keyword(s):  
Chest Ct ◽  
Ct Scans ◽  
Convolutional Lstm

scholarly journals A Deep Learning Approach For Improved Segmentation Of Lesions Related To Covid-19 Chest CT Scans

2021 ◽  
Author(s):  
Vlad Vasilescu ◽  
Ana Neacsu ◽  
Emilie Chouzenoux ◽  
Jean-Christophe Pesquet ◽  
Corneliu Burileanu
Keyword(s):  
Deep Learning ◽  
Chest Ct ◽  
Ct Scans ◽  
Learning Approach

Radiation Exposure in Standard and High-Resolution Chest CT Scans

CHEST Journal ◽  
1995 ◽  
Vol 107 (1) ◽  
pp. 113-115 ◽  
Author(s):  
Brigitte A.H.A. Van der Bruggen-Bogaarts ◽  
Johan J. Broerse ◽  
Jan-Willem J. Lammers ◽  
Paul F.G.M. Van Waes ◽  
Jacob Geleijns
Keyword(s):  
High Resolution ◽  
Radiation Exposure ◽  
Chest Ct ◽  
Ct Scans

Using chest CT scan and unsupervised machine learning for predicting and evaluating response to lumacaftor-ivacaftor in people with cystic fibrosis

2021 ◽  
pp. 2101344
Author(s):  
Alienor Campredon ◽  
Enzo Battistella ◽  
Clémence Martin ◽  
Isabelle Durieu ◽  
Laurent Mely ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cystic Fibrosis ◽  
Ct Scan ◽  
Structural Changes ◽  
Clinical Status ◽  
Chest Ct ◽  
Ct Scans ◽  
Wall Thickening ◽  
Unsupervised Machine Learning ◽  
One Year

ObjectivesLumacaftor-ivacaftor is a cystic fibrosis transmembrane conductance regulator (CFTR) modulator known to improve clinical status in people with cystic fibrosis (CF). This study aimed to assess lung structural changes after one year of lumacaftor-ivacaftor treatment, and to use unsupervised machine learning to identify morphological phenotypes of lung disease that are associated with response to lumacaftor-ivacaftor.MethodsAdolescents and adults with CF from the French multicenter real-world prospective observational study evaluating the first year of treatment with lumacaftor-ivacaftor were included if they had pretherapeutic and follow-up chest computed tomography (CT)-scans available. CT scans were visually scored using a modified Bhalla score. A k-mean clustering method was performed based on 120 radiomics features extracted from unenhanced pretherapeutic chest CT scans.ResultsA total of 283 patients were included. The Bhalla score significantly decreased after 1 year of lumacaftor-ivacaftor (−1.40±1.53 points compared with pretherapeutic CT; p<0.001). This finding was related to a significant decrease in mucus plugging (−0.35±0.62 points; p<0.001), bronchial wall thickening (−0.24±0.52 points; p<0.001) and parenchymal consolidations (−0.23±0.51 points; p<0.001). Cluster analysis identified 3 morphological clusters. Patients from cluster C were more likely to experience an increase in percent predicted forced expiratory volume in 1 sec (ppFEV1) ≥5 under lumacaftor–ivacaftor than those in the other clusters (54% of responders versus 32% and 33%; p=0.01).ConclusionOne year treatment with lumacaftor-ivacaftor was associated with a significant visual improvement of bronchial disease on chest CT. Radiomics features on pretherapeutic CT scan may help in predicting lung function response under lumacaftor-ivacaftor.

Sign in / Sign up

Export Citation Format

Share Document