scholarly journals COVID-19 Lung Radiography Segmentation by Means of Multiphase Transfer Learning

2021 ◽  
Vol 7 (1) ◽  
pp. 5
Author(s):  
Plácido L. Vidal ◽  
Joaquim de Moura ◽  
Jorge Novo ◽  
Marcos Ortega
Keyword(s):  
Image Quality ◽  
Transfer Learning ◽  
Respiratory System ◽  
Region Of Interest ◽  
Limited Data ◽  
Target Domain ◽  
X Ray ◽  
Computer Aided ◽  
Portable Chest ◽  
Aided Diagnosis

COVID-19 is characterized by its impact on the respiratory system and, during the global outbreak of 2020, specific protocols had to be designed to contain its spread within hospitals. This required the use of portable X-ray devices that allow for a greater flexibility in terms of their arrangement in rooms not specifically designed for such purpose. However, their poor image quality, together with the subjectivity of the expert, can hinder the diagnosis process. Therefore, the use of automatic methodologies is advised. Even so, their development is challenging due to the scarcity of available samples. For this reason, we present a COVID-19-specific methodology able to segment these portable chest radiographs with a reduced number of samples via multiple transfer learning phases. This allows us to extract knowledge from two related fields and obtain a robust methodology with limited data from the target domain. Our proposal aims to help both experts and other computer-aided diagnosis systems to focus their attention on the region of interest, ignoring unrelated information.

Computer-aided diagnosis system for Covid-19 by using deep transfer learning through X-ray images

2021 ◽  
Author(s):  
K. Akhil Trinayan ◽  
B. Prema Sai ◽  
P. Sai Akhilesh ◽  
Matta Aditya Reddy ◽  
J Neetha
Keyword(s):  
Transfer Learning ◽  
Computer Aided Diagnosis ◽  
Diagnosis System ◽  
X Ray ◽  
Computer Aided ◽  
Aided Diagnosis

Deep Learning Enabled Deblurring of Computed Tomography Images of Porous Media

2021 ◽  
Author(s):  
Khalid Labib Alsamadony ◽  
Ertugrul Umut Yildirim ◽  
Guenther Glatz ◽  
Umair bin Waheed ◽  
Sherif M. Hanafy
Keyword(s):  
Computed Tomography ◽  
Image Quality ◽  
Transfer Learning ◽  
Temporal Resolution ◽  
Exposure Time ◽  
Ct Images ◽  
Loss Functions ◽  
High Quality ◽  
X Ray ◽  
Training Images

Abstract Computed tomography (CT) is an important tool to characterize rock samples allowing quantification of physical properties in 3D and 4D. The accuracy of a property delineated from CT data is strongly correlated with the CT image quality. In general, high-quality, lower noise CT Images mandate greater exposure times. With increasing exposure time, however, more wear is put on the X-Ray tube and longer cooldown periods are required, inevitably limiting the temporal resolution of the particular phenomena under investigation. In this work, we propose a deep convolutional neural network (DCNN) based approach to improve the quality of images collected during reduced exposure time scans. First, we convolve long exposure time images from medical CT scanner with a blur kernel to mimic the degradation caused because of reduced exposure time scanning. Subsequently, utilizing the high- and low-quality scan stacks, we train a DCNN. The trained network enables us to restore any low-quality scan for which high-quality reference is not available. Furthermore, we investigate several factors affecting the DCNN performance such as the number of training images, transfer learning strategies, and loss functions. The results indicate that the number of training images is an important factor since the predictive capability of the DCNN improves as the number of training images increases. We illustrate, however, that the requirement for a large training dataset can be reduced by exploiting transfer learning. In addition, training the DCNN on mean squared error (MSE) as a loss function outperforms both mean absolute error (MAE) and Peak signal-to-noise ratio (PSNR) loss functions with respect to image quality metrics. The presented approach enables the prediction of high-quality images from low exposure CT images. Consequently, this allows for continued scanning without the need for X-Ray tube to cool down, thereby maximizing the temporal resolution. This is of particular value for any core flood experiment seeking to capture the underlying dynamics.

scholarly journals A quality enhanced preprocessing method for mammogram ROI extraction

2018 ◽  
Vol 7 (2.25) ◽  
pp. 133
Author(s):  
T R. Thamizhvani ◽  
Bincy Babu ◽  
A Josephin Arockia Dhivya ◽  
R J. Hemalatha ◽  
Josline Elsa Joseph ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Early Detection ◽  
Screening Test ◽  
Region Of Interest ◽  
Quality Enhancement ◽  
Cancer Death ◽  
Cad System ◽  
Computer Aided ◽  
Roi Extraction ◽  
Aided Diagnosis

Early detection of breast cancer is necessary because it is considered as one of the most common reason of cancer death among women. Nowadays, the basic screening test for detection of breast cancer is Mammography which con-sists of various artifacts. These artifacts leads to wrong results in detection of breast cancer. Therefore, Computer Aided Diagnosis (CAD) system mainly focus in removal of artifacts and mammogram quality enhancement. By this procedure, exact Region of Interest (ROI) can be obtained. This is a challenging procedure because detection of pecto-ral muscle and cancer region is difficult. Here a comparative study of different preprocessing and enhancement tech-niques are done by testing proposed system on mammogram mini-MIAS database. Result obtained shows that sug-gested system is efficient for CAD system.  

scholarly journals A Deep Convolutional Neural Network Based Lung Disorder Diagnosis

2019 ◽  
pp. 102-112
Author(s):  
J. Juditha Mercina ◽  
J. Madhumathi ◽  
V. Priyanga ◽  
M. Deva Priya
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Lung Disease ◽  
Lung Diseases ◽  
Intelligent System ◽  
Lung Disorder ◽  
X Ray ◽  
Cad System ◽  
Computer Aided ◽  
Aided Diagnosis

Lungs play an important role in human respiratory system. There are diseases that affect the functioning of lungs. To analyse lung diseases in the chest region using X-ray based Computer-Aided Diagnosis (CAD) system, it is necessary to determine the lung regions subject to analysis. In this paper, an intelligent system is proposed for lung disease detection. In this paper, Interstitial Lung Disease (ILD) patterns are classified using Convolutional Neural Networks (CNN). The proposed system involves five convolutional layers and three dense layers. The performance of the classification demonstrates the potential of CNN in analysing lung patterns.

scholarly journals Deep-learning convolutional neural networks with transfer learning accurately classify COVID-19 lung infection on portable chest radiographs

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e10309
Author(s):  
Shreeja Kikkisetti ◽  
Jocelyn Zhu ◽  
Beiyi Shen ◽  
Haifang Li ◽  
Tim Q. Duong
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Bacterial Pneumonia ◽  
Lung Infection ◽  
Accurate Diagnosis ◽  
Viral Pneumonia ◽  
X Ray ◽  
Portable Chest ◽  
Chest X Ray ◽  
Lung Infections

Portable chest X-ray (pCXR) has become an indispensable tool in the management of Coronavirus Disease 2019 (COVID-19) lung infection. This study employed deep-learning convolutional neural networks to classify COVID-19 lung infections on pCXR from normal and related lung infections to potentially enable more timely and accurate diagnosis. This retrospect study employed deep-learning convolutional neural network (CNN) with transfer learning to classify based on pCXRs COVID-19 pneumonia (N = 455) on pCXR from normal (N = 532), bacterial pneumonia (N = 492), and non-COVID viral pneumonia (N = 552). The data was randomly split into 75% training and 25% testing, randomly. A five-fold cross-validation was used for the testing set separately. Performance was evaluated using receiver-operating curve analysis. Comparison was made with CNN operated on the whole pCXR and segmented lungs. CNN accurately classified COVID-19 pCXR from those of normal, bacterial pneumonia, and non-COVID-19 viral pneumonia patients in a multiclass model. The overall sensitivity, specificity, accuracy, and AUC were 0.79, 0.93, and 0.79, 0.85 respectively (whole pCXR), and were 0.91, 0.93, 0.88, and 0.89 (CXR of segmented lung). The performance was generally better using segmented lungs. Heatmaps showed that CNN accurately localized areas of hazy appearance, ground glass opacity and/or consolidation on the pCXR. Deep-learning convolutional neural network with transfer learning accurately classifies COVID-19 on portable chest X-ray against normal, bacterial pneumonia or non-COVID viral pneumonia. This approach has the potential to help radiologists and frontline physicians by providing more timely and accurate diagnosis.

scholarly journals Computer aided diagnosis for breast cancer based on the gabor filter technique

2020 ◽  
Vol 10 (5) ◽  
pp. 5235 ◽  
Author(s):  
Mohammed Y. Kamil
Keyword(s):  
Breast Cancer ◽  
Gabor Filter ◽  
Diagnostic System ◽  
Region Of Interest ◽  
Histogram Equalization ◽  
Support Vector ◽  
Cancer Early Detection ◽  
False Positive Reduction ◽  
Computer Aided ◽  
Aided Diagnosis

The most prominent reason for the death of women all over the world is breast cancer. Early detection of cancer helps to lower the death rate. Mammography scans determine breast tumors in the first stage. As the mammograms have slight contrast, thus, it is a blur to the radiologist to recognize micro growths. A computer-aided diagnostic system is a powerful tool for understanding mammograms. Also, the specialist helps determine the presence of the breast lesion and distinguish between the normal area and the mass. In this paper, the Gabor filter is presented as a key step in building a diagnostic system. It is considered a sufficient method to extract the features. That helps us to avoid tumor classification difficulties and false-positive reduction. The linear support vector machine technique is used in this system for results classification. To improve the results, adaptive histogram equalization pre-processing procedure is employed. Mini-MIAS database utilized to evaluate this method. The highest accuracy, sensitivity, and specificity achieved are 98.7%, 98%, 99%, respectively, at the region of interest (30×30). The results have demonstrated the efficacy and accuracy of the proposed method of helping the radiologist on diagnosing breast cancer.

Sign in / Sign up

Export Citation Format

Share Document