Open medicine: A comparative analysis of the binary and multiclass classified chest X-ray images of pneumonia and COVID-19 with ML and DL models

Pal, Madhumita; Mohapatra, Ranjan K.; Sarangi, Ashish K.; Sahu, Alok Ranjan; Mishra, Snehasish; Patel, Alok; Bhoi, Sushil Kumar; Elnaggar, Ashraf Y.; El Azab, Islam H.; Alissa, Mohammed; El-Bahy, Salah M.

Amtsblatt für den Landespolizeibezirk Berlin (Public Domain) Ausgabe 1932 (Public Domain)

Access restriction

There is no access restriction for this record.

Copyright

Public Domain Mark 1.0. You can find more information here.

Bibliographic data

Full text : Amtsblatt für den Landespolizeibezirk Berlin (Public Domain) Ausgabe 1932 (Public Domain)

Access restriction

There is no access restriction for this record.

Copyright

Public Domain Mark 1.0. You can find more information here.

Periodical

Title:: Open medicine

Publication:: Berlin: de Gruyter

Note:: Open Access; Namensnennung 4.0 International

Scope:: Online-Ressource

ISSN:: 2391-5463

ZDB-ID:: 2829380-0

VÖBB-Katalog:: 35318930

Keywords:: Zeitschrift

DDC Group:: 610 Medizin

Copyright:: Rights reserved

Accessibility:: Free Access

Title:: Open medicine

Publication:: Berlin: de Gruyter

Note:: Open Access; Namensnennung 4.0 International

Scope:: Online-Ressource

ISSN:: 2391-5463

ZDB-ID:: 2829380-0

VÖBB-Katalog:: 35318930

Keywords:: Zeitschrift

DDC Group:: 610 Medizin

Copyright:: Rights reserved

Accessibility:: Free Access

Article

Author:: Pal, Madhumita; Mohapatra, Ranjan K.; Sarangi, Ashish K.; Sahu, Alok Ranjan; Mishra, Snehasish; Patel, Alok; Bhoi, Sushil Kumar; Elnaggar, Ashraf Y.; El Azab, Islam H.; Alissa, Mohammed; El-Bahy, Salah M.

Title:: A comparative analysis of the binary and multiclass classified chest X-ray images of pneumonia and COVID-19 with ML and DL models

Publication:: Berlin: de Gruyter, 2025

Language:: English

Information:: Background: The highly infectious coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2, the seventh coronavirus. It is the longest pandemic in recorded history worldwide. Many countries are still reporting COVID-19 cases even in the fifth year of its emergence. Objective: The performance of various machine learning (ML) and deep learning (DL) models was studied for image-based classification of the lungs infected with COVID-19, pneumonia (viral and bacterial), and normal cases from the chest X-rays (CXRs). Methods: The K-nearest neighbour and logistics regression as the two ML models, and Visual Geometry Group-19, Vision transformer, and ConvMixer as the three DL models were included in the investigation to compare the brevity of the detection and classification of the cases. Results: Among the investigated models, ConvMixer returned the best result in terms of accuracy, recall, precision, F1-score and area under the curve for both binary as well as multiclass classification. The pre-trained ConvMixer model outperformed the other four models in classifying. As per the performance observations, there was 97.1% accuracy for normal and COVID-19 + pneumonia-infected lungs, 98% accuracy for normal and COVID-19 infected lungs, 82% accuracy for normal + bacterial + viral infected lungs, and 98% accuracy for normal + pneumonia infected lungs. The DL models performed better than the ML models for binary and multiclass classification. The performance of these studied models was tried on other CXR image databases. Conclusion: The suggested network effectively detected COVID-19 and different types of pneumonia by using CXR imagery. This could help medical sciences for timely and accurate diagnoses of the cases through bioimaging technology and the use of high-end bioinformatics tools.

Scope:: Online-Ressource

Note:: Open Access; Archivierung/Langzeitarchivierung gewährleistet

Keywords:: COVID-19 ; chest X-ray images ; ML and DL models ; binary and multiclass classification

Classification:: Sonstiges

URN:: urn:nbn:de:101:1-2502051659321.030708327425

Collection:: Sonstiges

Copyright:: CC BY

Accessibility:: Free Access

Author:: Pal, Madhumita; Mohapatra, Ranjan K.; Sarangi, Ashish K.; Sahu, Alok Ranjan; Mishra, Snehasish; Patel, Alok; Bhoi, Sushil Kumar; Elnaggar, Ashraf Y.; El Azab, Islam H.; Alissa, Mohammed; El-Bahy, Salah M.

Title:: A comparative analysis of the binary and multiclass classified chest X-ray images of pneumonia and COVID-19 with ML and DL models

Publication:: Berlin: de Gruyter, 2025

Language:: English

Information:: Background: The highly infectious coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2, the seventh coronavirus. It is the longest pandemic in recorded history worldwide. Many countries are still reporting COVID-19 cases even in the fifth year of its emergence. Objective: The performance of various machine learning (ML) and deep learning (DL) models was studied for image-based classification of the lungs infected with COVID-19, pneumonia (viral and bacterial), and normal cases from the chest X-rays (CXRs). Methods: The K-nearest neighbour and logistics regression as the two ML models, and Visual Geometry Group-19, Vision transformer, and ConvMixer as the three DL models were included in the investigation to compare the brevity of the detection and classification of the cases. Results: Among the investigated models, ConvMixer returned the best result in terms of accuracy, recall, precision, F1-score and area under the curve for both binary as well as multiclass classification. The pre-trained ConvMixer model outperformed the other four models in classifying. As per the performance observations, there was 97.1% accuracy for normal and COVID-19 + pneumonia-infected lungs, 98% accuracy for normal and COVID-19 infected lungs, 82% accuracy for normal + bacterial + viral infected lungs, and 98% accuracy for normal + pneumonia infected lungs. The DL models performed better than the ML models for binary and multiclass classification. The performance of these studied models was tried on other CXR image databases. Conclusion: The suggested network effectively detected COVID-19 and different types of pneumonia by using CXR imagery. This could help medical sciences for timely and accurate diagnoses of the cases through bioimaging technology and the use of high-end bioinformatics tools.

Scope:: Online-Ressource

Note:: Open Access; Archivierung/Langzeitarchivierung gewährleistet

Keywords:: COVID-19 ; chest X-ray images ; ML and DL models ; binary and multiclass classification

Classification:: Sonstiges

URN:: urn:nbn:de:101:1-2502051659321.030708327425

Collection:: Sonstiges

Copyright:: CC BY

Accessibility:: Free Access

1086 der Geschäftsstelle des Amtsgerichts Berlin-Mitte, | 16 646,90 bestritten. Der nach Sicherstellung der Abteilung 453, niedergelegten Verzeichnis sind Masseschulden und Massekosten zur Verteilung ver-RM 7237,53 bevorrechtigte Forderungen und | fügbare Bestand beträgt X H 12 361,96. KRM 48 536,98 nichtbevorrechtigte Forderungen zu Berlin C€ 2, Burgstr. 28, den 28. September 1932. berücksichtigen. Der zur Begleichung der noch aus- Hans Zettelmeyer, Konkursverwalter. stehenden Massekosten, Masseschulden, bevorrechtigten 8088 Konkursverfahren. und nichtbevorrechtigten Forderungen verfügbare In dem Konkursverfahren über das Vermögen Bestand beträgt 2-4 1315,17. der Firma Georg Leisegang, Photohaus, Berlin C 2, Burgstr. 28, den 28. September 1932. Berlin, Pot8damer Str. 138, Aktenzeichen 153. N. Hans Zettelmeyer, Konkursverwalter. 300. 31, soll eine Abschlagsverteilung von % % 8087 Konkursverfahren. erfolgen. Nach dem auf der Geschäftsstelle des Amts-In dem Konkursverfahren über das Vermögen gerichts Berlin-Mitte niedergelegten Verzeichnis sind des Kaufmanns (Georg Leisegang, Allein- nichtbevorrechtigte Forderungen in Höhe von insinhabers3 : der -Firma Sporthaus A. Steidel, gesamt XA 182 356,12 zu berücsichtigen. Von Berlin, Rosenthaler Str. 34, Aktenzeichen 153. N. diesen Forderungen sind bisher "2X 134 412,47 301. 31, soll eine Abschlagöverteilung von 3 % er- festgestellt und 2 XA 47 943,65 bestritten. Der nach folgen. Nach dem auf der Geschäftsstelle des Amts- Sicherstellung der Masseschulden und Massekosten zur gerichts Berlin-Mitte niedergelegten Verzeihnis Verteilung verfügbare Bestand beträgt Reichsmark sind nichtbevorrechtigte Forderungen in Höhe von 2373,30. insSgesamt :2 4 80 668,16 zu berüdfichtigen. Davon Berlin C 2, Burgstr. 28, den 28. September 1932. sind biSher ZH 64 021,26 festgestellt und Reichsmark . Hans Zettelmeyer, Konkursverwalter. Preußische Druderei- und Verlags-Äktiengesells<haft Berlin.

Full text : Amtsblatt für den Landespolizeibezirk Berlin (Public Domain) Ausgabe 1932 (Public Domain)

Access restriction

There is no access restriction for this record.

Copyright

Public Domain Mark 1.0. You can find more information here.

Access restriction

Copyright

Periodical

Article

Table of contents

Downloads

Full record

Image fragment

Formats and links

Formats

Links

Cite

Full record

This page

Citation recommendation

Full text : Amtsblatt für den Landespolizeibezirk Berlin (Public Domain) Ausgabe 1932 (Public Domain) Access restriction There is no access restriction for this record. Copyright Public Domain Mark 1.0. You can find more information here.

Access restriction

Copyright

Table of contents

Image fragment

Full text : Amtsblatt für den Landespolizeibezirk Berlin (Public Domain) Ausgabe 1932 (Public Domain)

Access restriction

There is no access restriction for this record.

Copyright

Public Domain Mark 1.0. You can find more information here.