Covid-19 Pneumonia Classification Using Deep Learning Technique

COVID-19 PNEUMONIA
CLASSIFICATION USING DEEP

LEARNING TECHNIQUE
Presented By
Xxxxxxx (962xxxxxxxxx)
Xxxxxxx (962xxxxxxxxx)
Xxxxxx (962xxxxxxxxx)
Xxxxxx (962xxxxxxxxx)
Final Year Biomedical Engineering
Udaya School of Engineering
ABSTRACT
• Covid-19 is a rapidly spreading viral disease that infects not only humans, but
animals are also infected because of this disease.
• The daily life of human beings, their health, and the economy of a country are
affected due to this deadly viral disease.
• Covid-19 is a common spreading disease, and till now, not a single country can
prepare a vaccine for COVID-19.
• A clinical study of COVID-19 infected patients has shown that these types of
patients are mostly infected from a lung infection after coming in contact with this
disease.
• Chest x-ray (i.e., radiography) and chest CT are a more effective imaging technique
for diagnosing lung related problems.
ABSTRACT(Continued)
• Still, a substantial chest x-ray is a lower cost process in comparison to chest CT.
• Deep learning is the most successful technique of machine learning, which
provides useful analysis to study a large amount of chest x-ray images that can
critically impact on screening of Covid-19.
• In this work, we have taken the posteroanterior (PA) view of chest x-ray scans for
covid-19 affected patients as well as healthy patients.
• After cleaning up the images and applying data augmentation, we have used deep
learning-based ResNeXt models and compared their performance.
INTRODUCTION
• Coronavirus disease (COVID-19) is an extremely contagious disease and it has been
declared as a pandemic by the World Health Organization (WHO).
• The pandemic declaration also stressed the deep concerns of the alarming rate of spread
and severity of COVID-19.
• While most of the people infected with the COVID-19 experienced mild to moderate
respiratory illness, some developed a deadly pneumonia.
• The other diagnosis methods of the COVID-19 include clinical symptoms analysis,
epidemiological history and positive radiographic images (computed tomography (CT)
/Chest radiograph (CXR)) as well as positive pathogenic testing.
• Although typical CXR images may help early screening of suspected cases, the images of
various viral pneumonias are similar and they overlap with other infectious and
inflammatory lung diseases.
LITERATURE SURVEY 1
TITLE OF THE PAPER CheXNet: Radiologist-Level Pneumonia Detection on Chest
X-Rays with Deep Learning
AUTHOR, JOURNAL Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel
AND YEAR OF Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie
PUBLICATION Shpanskaya, Matthew P. Lungren, Andrew Y. Ng;
PLoS Med, 2017.
METHOD Deep Learning &Framework classification algorithm used is the
Neural Network.
ADVANTAGE Automated detection of diseases from chest X-rays at the level of

expert radiologists.
DISADVANTAGE No comparison is made between the accuracies of several algorithm

LITERATURE SURVEY 2
TITLE OF THE PAPER An Efficient Deep Learning Approach to Pneumonia Classification
in Healthcare
AUTHOR, JOURNAL Okeke Stephen, Mangal Sain, Uchenna Joseph Maduh and Do-Un
AND YEAR OF Jeong;
PUBLICATION Hindaw, Journal of Healthcare Engineering 2019
METHOD Deep Learning Framework is used and the only classification
algorithm used is the Neural Network.
ADVANTAGE • Helps to extract best features from given chest X-ray image and
• Helps to classify whether if a person is infected by pneumonia or
not.
DISADVANTAGE No comparison is made between the accuracies of several algorithm.
LITERATURE SURVEY 3
TITLE OF THE PAPER Identifying medical diagnoses and treatable diseases by
image-based deep learning
AUTHOR, JOURNAL Kermany, Daniel S., Michael Goldbaum, Wenjia Cai, Carolina CS
AND YEAR OF Valentim, Huiying Liang, Sally L. Baxter, Alex McKeown et al.
PUBLICATION Cell 172, 2018.
METHOD Deep Learning Framework is used and the only classification
algorithm used is the Neural Network.
ADVANTAGE • Differentiates the X-rays presenting as pneumonia versus normal

• Achieved high accuracy of 92.8% with sensitivity of 93.2% and
specificity of 90.1%.
DISADVANTAGE • No comparison is made between the accuracies of several algorithm

LITERATURE SURVEY 4
TITLE OF THE PAPER Deep Learning Approach For Prediction Of Pneumonia
Kalyani Kadam, Dr.Swati Ahirrao, Harbir Kaur ,Dr.Shraddha

AUTHOR, JOURNAL
Phansalkar , Dr. Ambika Pawar
AND YEAR OF
INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY
PUBLICATION RESEARCH VOLUME 8, 2019.
Deep Learning Framework is used and the classification algorithm
METHOD
used is the Convolutional Neural Network
• An efficient and highly accurate network

ADVANTAGE • Predicts Pneumonia in minimal time,
• High efficiency with 92.9% accuracy
• Processing building the model requires fast and efficient processors

DISADVANTAGE
which is cost consuming
LITERATURE SURVEY 5
TITLE OF THE PAPER Automatic detection of acute bacterial pneumonia from
chest X-ray reports
AUTHOR, JOURNAL Fiszman, Marcelo, Wendy W. Chapman, Dominik Aronsky, R. Scott
AND YEAR OF Evans, and Peter J. Haug.
PUBLICATION Journal of the American Medical Informatics Association 7, 2000.
METHOD Natural language processing (NLP) is a methodology for automatically
encoding clinical data from narrative report.
ADVANTAGE • The performance of an NLP system was similar to the performance
of physicians.
DISADVANTAGE • The small number of clinical conditions that were evaluated.
• Study did not compare the NLP performance with the average
physician performance.
LITERATURE SURVEY 6
TITLE OF THE PAPER Reading and interpretation of chest X-ray in adults with
community-acquired pneumonia
AUTHOR, JOURNAL Moncada, Diana Carolina, Zulma Vanessa Rueda, Antonio Macías,
AND YEAR OF Tatiana Suárez, Héctor Ortega, and Lázaro Agustín Vélez.
PUBLICATION The Brazilian Journal of Infectious Diseases, 2011
METHOD
ADVANTAGE
DISADVANTAGE
LITERATURE SURVEY 7
TITLE OF THE PAPER Detection and Classification of Lung Abnormalities by Use
of Convolutional Neural Network (CNN) and Regions with
CNN Features (R-CNN)
AUTHOR, JOURNAL
Shoji Kido
AND YEAR OF
IEEE 2018
PUBLICATION
METHOD
ADVANTAGE
DISADVANTAGE
LITERATURE SURVEY 8
TITLE OF THE PAPER
On The Use of Deep Learning Methods On Medical Images
AUTHOR, JOURNAL
Zulfikar Aslan
AND YEAR OF
IEEE 2018
PUBLICATION
METHOD
ADVANTAGE
DISADVANTAGE
LITERATURE SURVEY 9
TITLE OF THE PAPER
Diagnosis of Pneumonia from Chest X-Ray Images using
Deep Learning
AUTHOR, JOURNAL
Enes Ayan
AND YEAR OF
IEEE 2019
PUBLICATION
METHOD
ADVANTAGE
DISADVANTAGE
LITERATURE SURVEY 10
TITLE OF THE PAPER
An Efficient Deep Learning Approach to Pneumonia
Classification in Healthcare
AUTHOR, JOURNAL
Okele Stephen
AND YEAR OF
Journal of Healthcare Engineering, Hindawi, Vol 2019
PUBLICATION
METHOD
ADVANTAGE
DISADVANTAGE
PROPOSED SYSTEM
• The proposed work is based on chest X-ray radiographic images
• The dataset are downloaded from the online dataset.
• The Chest X-ray images were only resized and normalized before applying as
input to the networks.
• The preprocessing techniques includes noise filtering , RGB to gray conversion
processes.
• The image augmentation techniques such as rotation, and translation are
implemented to generate COVID-19 training images.
• The ResNeXt – deep learning network is implemented in this proposed work, it
will extract the texture features and classifying the test image into three classes
such as, Normal, COVID-19 and Viral pneumonia.
PROPOSED SYSTEM
ADVANTAGES
• High accuracy and Precision
• High recognition rate
• Consumption of less time comparatively to other networks.

PROPOSED BLOCK DIAGRAM
Training images
Input X- Pre- Image Feature Classification

ray image processing augmentation extraction
COVID-19 Viral
Normal Pneumonia Pneumonia
ResNeXt – Deep learning network

REFERENCES
1. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
―Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan,
Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, Matthew P. Lungren, Andrew
Y. Ng PLoS Med 15(11): e1002686.
2. Okeke Stephen , Mangal Sain , Uchenna Joseph Maduh, and Do-Un Jeong ‘An Efficient
Deep Learning Approach to Pneumonia Classification in Healthcare’ Hindawi Journal of
Healthcare Engineering Volume 2019, ID 4180949.
3. Kermany, Daniel S., Michael Goldbaum, Wenjia Cai, Carolina CS Valentim, Huiying
Liang, Sally L. Baxter, Alex McKeown et al. "Identifying medical diagnoses and treatable
diseases by image-based deep learning." Cell 172, no. 5 (2018): 1122-1131.
4. Kalyani Kadam, Dr.Swati Ahirrao, Harbir Kaur ,Dr.Shraddha Phansalkar , Dr. Ambika
Pawar’ Deep Learning Approach For Prediction Of Pneumonia’ INTERNATIONAL
JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 8, ISSUE 10,
ISSN 2277-8616, 2019.
5. Fiszman, Marcelo, Wendy W. Chapman, Dominik Aronsky, R. Scott Evans, and Peter J.
Haug. "Automatic detection of acute bacterial pneumonia from chest X-ray reports."
Journal of the American Medical Informatics Association 7, no. 6 (2000): 593-604.
REFERENCES
6. Moncada, Diana Carolina, Zulma Vanessa Rueda, Antonio Macías, Tatiana Suárez, Héctor
Ortega, and Lázaro Agustín Vélez. "Reading and interpretation of chest X-ray in adults with
community-acquired pneumonia." The Brazilian Journal of Infectious Diseases 15, no. 6 (2011):
540-546.
7. Shoji Kido, “Detection and Classification of Lung Abnormalities by Use of Convolutional
Neural Network (CNN) and Regions with CNN Features (R-CNN), IEEE 2018.
8. Zulfikar Aslan, “On The Use of Deep Learning Methods On Medical Images”, International
Journal on Energu & Engineering Science, Vol 3,, 12, 2018.ages”, IEEE 2018.
9. Enes Ayan, “Diagnosis of Pneumonia from Chest X-Ray Images using Deep Learning”, IEEE
2019.
10. Okele Stephen, “An Efficient Deep Learning Approach to Pneumonia Classification in
Healthcare” , Journal of Healthcare Engineering, Hindawi, Vol 2019.
THANK YoU..

Covid-19 Pneumonia Classification Using Deep Learning Technique

Uploaded by

Copyright:

Available Formats

Covid-19 Pneumonia Classification Using Deep Learning Technique

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Covid-19 Pneumonia Classification Using Deep Learning Technique

Uploaded by

Copyright:

Available Formats

COVID-19 PNEUMONIA

CLASSIFICATION USING DEEP

ADVANTAGE Automated detection of diseases from chest X-rays at the level of

DISADVANTAGE No comparison is made between the accuracies of several algorithm

ADVANTAGE • Differentiates the X-rays presenting as pneumonia versus normal

DISADVANTAGE • No comparison is made between the accuracies of several algorithm

Kalyani Kadam, Dr.Swati Ahirrao, Harbir Kaur ,Dr.Shraddha

• An efficient and highly accurate network

• Processing building the model requires fast and efficient processors

• High accuracy and Precision

• High recognition rate

• Consumption of less time comparatively to other networks.

Input X- Pre- Image Feature Classification

ResNeXt – Deep learning network

You might also like