scholarly journals Deep CNN-Based CAD System for COVID-19 Detection Using Multiple Lung CT Scans (Preprint)

10.2196/27468 ◽  
2021 ◽  
Author(s):  
Mustafa Ghaderzadeh ◽  
Farkhondeh Asadi ◽  
Ramezan Jafari ◽  
Davood Bashash ◽  
Hassan Abolghasemi ◽  
...  
Keyword(s):  
Ct Scans ◽  
Cad System ◽  
Deep Cnn ◽  
Lung Ct

scholarly journals Deep CNN-Based CAD System for COVID-19 Detection Using Multiple Lung CT Scans (Preprint)

2021 ◽  
Author(s):  
Mustafa Ghaderzadeh ◽  
Farkhondeh Asadi ◽  
Ramezan Jafari ◽  
Davood Bashash ◽  
Hassan Abolghasemi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Feature ◽  
Detection Sensitivity ◽  
World Health ◽  
Detection Methods ◽  
Ct Scans ◽  
Cad System ◽  
Early Stages ◽  
The World ◽  
Lung Ct

BACKGROUND Due to the COVID-19 pandemic and the imminent collapse of healthcare systems following the excessive consumption of financial, hospital, and medicinal resources, the World Health Organization (WHO) changed the alert level on the COVID-19 pandemic from high to very high. Meanwhile, the world began to favor less expensive and more precise COVID-19 detection methods. Machine vision-based COVID-19 detection methods especially Deep learning as a diagnostic technique in the early stages of the disease have found great importance during the pandemic. OBJECTIVE This study aimed to design a highly efficient Computer-Aided Detection (CAD) system for COVID-19 by using a NASNet-based algorithm. n images of 190 persons suspected of COVID-19, was used. METHODS A state-of-the-art pre-trained CNN network for image feature extraction, called NASNet, was adopted to identify patients with COVID-19 in the first stages of the disease. A local dataset, comprising 10153 CT scan images of 190 persons suspected of COVID-19, was used. RESULTS After fitting on the training dataset, hyper-parameter tuning and finally topological alterations of the classifier block, the proposed NASNet-based model was evaluated on the test dataset and yielded remarkable results. The proposed model's performance achieved a detection sensitivity, specificity, and accuracy of 0.999, 0.986, and 0.996, respectively. CONCLUSIONS The proposed model achieved acceptable results in the categorization of two data classes. Therefore, a CAD system was designed based on this model for COVID-19 detection using multiple lung CT scans. The system managed to differentiate all the COVID-19 cases from non-COVID-19 ones without any error in the application phase. Overall, the proposed deep learning-based CAD system can greatly aid radiologists in the detection of COVID-19 in its early stages. During the COVID-19 pandemic, the use of CAD system as a screening tool accelerates the process of disease detection and prevents the loss of healthcare resources.

scholarly journals Motion correction for routine X-ray lung CT imaging

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Doil Kim ◽  
Jiyoung Choi ◽  
Duhgoon Lee ◽  
Hyesun Kim ◽  
Jiyoung Jung ◽  
...  
Keyword(s):  
Motion Estimation ◽  
Motion Correction ◽  
Ct Imaging ◽  
Motion Artifacts ◽  
Ct Scans ◽  
Breath Hold ◽  
X Ray ◽  
Wide Range ◽  
Thorax Ct ◽  
Lung Ct

AbstractA novel motion correction algorithm for X-ray lung CT imaging has been developed recently. It was designed to perform for routine chest or thorax CT scans without gating, namely axial or helical scans with pitch around 1.0. The algorithm makes use of two conjugate partial angle reconstruction images for motion estimation via non-rigid registration which is followed by a motion compensated reconstruction. Differently from other conventional approaches, no segmentation is adopted in motion estimation. This makes motion estimation of various fine lung structures possible. The aim of this study is to explore the performance of the proposed method in correcting the lung motion artifacts which arise even under routine CT scans with breath-hold. The artifacts are known to mimic various lung diseases, so it is of great interest to address the problem. For that purpose, a moving phantom experiment and clinical study (seven cases) were conducted. We selected the entropy and positivity as figure of merits to compare the reconstructed images before and after the motion correction. Results of both phantom and clinical studies showed a statistically significant improvement by the proposed method, namely up to 53.6% (p < 0.05) and up to 35.5% (p < 0.05) improvement by means of the positivity measure, respectively. Images of the proposed method show significantly reduced motion artifacts of various lung structures such as lung parenchyma, pulmonary vessels, and airways which are prominent in FBP images. Results of two exemplary cases also showed great potential of the proposed method in correcting motion artifacts of the aorta which is known to mimic aortic dissection. Compared to other approaches, the proposed method provides an excellent performance and a fully automatic workflow. In addition, it has a great potential to handle motions in wide range of organs such as lung structures and the aorta. We expect that this would pave a way toward innovations in chest and thorax CT imaging.

scholarly journals Reducing False-Positives in Lung Nodules Detection Using Balanced Datasets

2021 ◽  
Vol 9 ◽  
Author(s):  
Jinglun Liang ◽  
Guoliang Ye ◽  
Jianwen Guo ◽  
Qifan Huang ◽  
Shaohui Zhang
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
False Positives ◽  
Classification Systems ◽  
Cad System ◽  
Nodule Detection ◽  
Diagnosis Of Lung Cancer ◽  
Lung Ct

Malignant pulmonary nodules are one of the main manifestations of lung cancer in early CT image screening. Since lung cancer may have no early obvious symptoms, it is important to develop a computer-aided detection (CAD) system to assist doctors to detect the malignant pulmonary nodules in the early stage of lung cancer CT diagnosis. Due to the recent successful applications of deep learning in image processing, more and more researchers have been trying to apply it to the diagnosis of pulmonary nodules. However, due to the ratio of nodules and non-nodules samples used in the training and testing datasets usually being different from the practical ratio of lung cancer, the CAD classification systems may easily produce higher false-positives while using this imbalanced dataset. This work introduces a filtering step to remove the irrelevant images from the dataset, and the results show that the false-positives can be reduced and the accuracy can be above 98%. There are two steps in nodule detection. Firstly, the images with pulmonary nodules are screened from the whole lung CT images of the patients. Secondly, the exact locations of pulmonary nodules will be detected using Faster R-CNN. Final results show that this method can effectively detect the pulmonary nodules in the CT images and hence potentially assist doctors in the early diagnosis of lung cancer.

Automated Detection of Small Pulmonary Nodules in Whole Lung CT Scans

2007 ◽  
Vol 14 (5) ◽  
pp. 579-593 ◽  
Author(s):  
Andinet A. Enquobahrie ◽  
Anthony P. Reeves ◽  
David F. Yankelevitz ◽  
Claudia I. Henschke
Keyword(s):  
Pulmonary Nodules ◽  
Automated Detection ◽  
Ct Scans ◽  
Small Pulmonary Nodules ◽  
Lung Ct

scholarly journals Contribution of CAD to the Sensitivity for Detecting Lung Metastases on Thin-Section CT – A Prospective Study with Surgical and Histopathological Correlation

2019 ◽  
Vol 192 (01) ◽  
pp. 65-73 ◽  
Author(s):  
Christian Meybaum ◽  
Mareike Graff ◽  
Eva Maria Fallenberg ◽  
Gunda Leschber ◽  
Dag Wormanns
Keyword(s):  
Thin Section ◽  
Lung Metastases ◽  
Ct Scans ◽  
Pulmonary Metastasectomy ◽  
Computed Tomographic ◽  
Cad System ◽  
Histopathological Correlation ◽  
Experienced Radiologist ◽  
Key Points ◽  
A Prospective Study

Purpose To assess the sensitivity of radiologists and a CAD system for the detection of lung metastases on thin-section computed tomographic (CT) scans prior to pulmonary metastasectomy. Materials and Methods All patients scheduled for resection of lung metastases were eligible for this prospective single-center trial. 95 patients with 115 surgical procedures (pulmonary metastasectomy using thoracotomy) were included. An experienced radiologist examined the CT scans for pulmonary metastases and documented his findings. A commercial CAD system was used as a second reader; additional CAD findings were recorded. A comparison of the sensitivity of the radiologist alone and with CAD was performed. Intraoperatively surgeons tried to identify the documented lesions and resected them as well as additionally palpable lesions. The standard of reference consisted of surgery and histopathology. Follow-up information for radiologically detected lesions missed during surgery was sought. Results 693 lesions (262 metastases) were detected radiologically or surgically, 646 of them were resected. The sensitivity of radiologists without CAD was 67.5 % for all lesions (87.4 % for metastases). CAD highly significantly (p < 0.001) increased the sensitivity to 77.9 % (92.7 %). During surgery, 143 additional lesions (19 metastases) were detected. 49 radiologically detected lesions were not palpable during surgery: 4 metastases, 5 benign lesions, and 40 lesions of an unknown nature. Conclusion CAD provides significant additional sensitivity for detecting lung metastases using MDCT compared to the performance of a radiologist alone. CT reveals a relevant number of non-palpable pulmonary lesions. Key Points:  Citation Format

scholarly journals Quantitative Computerized Two-Point Correlation Analysis of Lung CT Scans Correlates With Pulmonary Function in Pulmonary Sarcoidosis

CHEST Journal ◽  
2012 ◽  
Vol 142 (6) ◽  
pp. 1589-1597 ◽  
Author(s):  
Barbaros Selnur Erdal ◽  
Elliott D. Crouser ◽  
Vedat Yildiz ◽  
Mark A. King ◽  
Andrew T. Patterson ◽  
...  
Keyword(s):  
Correlation Analysis ◽  
Pulmonary Function ◽  
Pulmonary Sarcoidosis ◽  
Ct Scans ◽  
Point Correlation ◽  
Lung Ct

scholarly journals DIAG a Diagnostic Web Application Based on Lung CT Scan Images and Deep Learning

2021 ◽  
Author(s):  
Amel Imene Hadj Bouzid ◽  
Said Yahiaoui ◽  
Anis Lounis ◽  
Sid-Ahmed Berrani ◽  
Hacène Belbachir ◽  
...  
Keyword(s):  
Deep Learning ◽  
Web Application ◽  
Patient Management ◽  
Image Interpretation ◽  
Ct Scans ◽  
Diagnostic Tools ◽  
The World ◽  
Aided Diagnosis ◽  
Lung Ct ◽  
Lung Ct Scan

Coronavirus disease is a pandemic that has infected millions of people around the world. Lung CT-scans are effective diagnostic tools, but radiologists can quickly become overwhelmed by the flow of infected patients. Therefore, automated image interpretation needs to be achieved. Deep learning (DL) can support critical medical tasks including diagnostics, and DL algorithms have successfully been applied to the classification and detection of many diseases. This work aims to use deep learning methods that can classify patients between Covid-19 positive and healthy patient. We collected 4 available datasets, and tested our convolutional neural networks (CNNs) on different distributions to investigate the generalizability of our models. In order to clearly explain the predictions, Grad-CAM and Fast-CAM visualization methods were used. Our approach reaches more than 92% accuracy on 2 different distributions. In addition, we propose a computer aided diagnosis web application for Covid-19 diagnosis. The results suggest that our proposed deep learning tool can be integrated to the Covid-19 detection process and be useful for a rapid patient management.

scholarly journals CoronaNet: A Novel Deep Learning Model for COVID-19 Detection in CT Scans

2020 ◽  
Vol 9 (2) ◽  
Author(s):  
Rohan Bhansali ◽  
Rahul Kumar ◽  
Duke Writer
Keyword(s):  
Deep Learning ◽  
Ct Scan ◽  
Biomedical Applications ◽  
Feature Detection ◽  
Ct Scans ◽  
Affine Transformations ◽  
Global Pandemic ◽  
Deep Cnn ◽  
High Degree ◽  
Ct Scan Analysis

Coronavirus disease (COVID-19) is currently the cause of a global pandemic that is affecting millions of people around the world. Inadequate testing resources have resulted in several people going undiagnosed and consequently untreated; however, using computerized tomography (CT) scans for diagnosis is an alternative to bypass this limitation. Unfortunately, CT scan analysis is time-consuming and labor intensive and rendering is generally infeasible in most diagnosis situations. In order to alleviate this problem, previous studies have utilized multiple deep learning techniques to analyze biomedical images such as CT scans. Specifically, convolutional neural networks (CNNs) have been shown to provide medical diagnosis with a high degree of accuracy. A common issue in the training of CNNs for biomedical applications is the requirement of large datasets. In this paper, we propose the use of affine transformations to artificially magnify the size of our dataset. Additionally, we propose the use of the Laplace filter to increase feature detection in CT scan analysis. We then feed the preprocessed images to a novel deep CNN structure: CoronaNet. We find that the use of the Laplace filter significantly increases the performance of CoronaNet across all metrics. Additionally, we find that affine transformations successfully magnify the dataset without resulting in high degrees of overfitting. Specifically, we achieved an accuracy of 92% and an F1 of 0.8735. Our novel research describes the potential of the Laplace filter to significantly increase deep CNN performance in biomedical applications such as COVID-19 diagnosis.

Sign in / Sign up

Export Citation Format

Share Document