Deep Learning-Based Pneumonia Diagnosis: A Comparative Review of Models and Metrics

Year : 2024 | Volume : 13 | 03 | Page :
    By

    Dr. Purushotam naidu K,

  • Harshitha Kasarapu,

  • Keerthi Mogilipuri,

  • Chinmayi Sista,

  • Uppalpati Prapadhya,

  • Dhanishya Vadlamudi,

  1. Assistant Professor, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women,, Visakhapatnam, India
  2. Student, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women, Visakhapatnam, India
  3. Student, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women, Visakhapatnam, India
  4. Student, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women, Visakhapatnam, India
  5. Student, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women, Visakhapatnam, India
  6. Student, Dept. of Computer Science and Engineering (AI&ML), GVP College of Engineering for Women, Visakhapatnam, India

Abstract

Pneumonia is a common viral infection that affects a large percentage of people worldwide. It is more common in developing and impoverished areas because of factors like poor sanitation, crowded living quarters, pollution in the environment, and restricted access to medical facilities. In order to improve survival chances and gain access to therapeutic therapies, pneumonia must be diagnosed as soon as possible. A type of artificial intelligence called deep learning has shown promise in the creation of predictive models to support the diagnosis of pneumonia. In order to train deep learning models, such as VGG16, for pneumonia detection and classification, this study uses a single CXR picture dataset. Accuracy measures are used for the evaluation, with a special emphasis on DenseNet121. The results show that the VGG16 model trained on the dataset has an accuracy of 92.15%. Additionally, a thorough analysis using multiple deep learning models is carried out on a heterogeneous CXR dataset that includes pneumonia, normal cases. The DenseNet121 model performs better than the others, as evidenced by its accuracy of 95.4%. Our method improves accuracy and efficiency in diagnosing pneumonia from CXR pictures by utilizing deep learning models, specifically DenseNet121, to solve the urgent problem of pneumonia diagnosis. Our technology helps with early detection and timely intervention, which improves patient outcomes and lessens the strain on healthcare systems. It does this by offering dependable and quick diagnostic assistance.

Keywords: Pneumonia Diagnosis, Chest X-ray imaging, DenseNet121, VGG16, Xception, Diagnostic Accuracy, Predictive Modelling, Disease Classification

How to cite this article:
Dr. Purushotam naidu K, Harshitha Kasarapu, Keerthi Mogilipuri, Chinmayi Sista, Uppalpati Prapadhya, Dhanishya Vadlamudi. Deep Learning-Based Pneumonia Diagnosis: A Comparative Review of Models and Metrics. Research and Reviews : A Journal of Medical Science and Technology. 2024; 13(03):-.
How to cite this URL:
Dr. Purushotam naidu K, Harshitha Kasarapu, Keerthi Mogilipuri, Chinmayi Sista, Uppalpati Prapadhya, Dhanishya Vadlamudi. Deep Learning-Based Pneumonia Diagnosis: A Comparative Review of Models and Metrics. Research and Reviews : A Journal of Medical Science and Technology. 2024; 13(03):-. Available from: https://journals.stmjournals.com/rrjomst/article=2024/view=184846


References

  1. Almaslukh B. A lightweight deep learning-based pneumonia detection approach for energy-efficient medical systems. Published April 22, 2021.
  2. Cohen J, Dao L, Roth K, et al. Predicting COVID-19 pneumonia severity on chest X-ray with deep learning. Cureus. 2020 Jul 28;12(7) doi: 10.7759/cureus.9448.
  3. Panwar H, Gupta PK, Siddiqui MK, et al. Application of deep learning for fast detection of COVID-19 in X-rays using nCOVnet. Chaos Solitons Fractals. 2020 May;138:109944.
  4. Sharma S, Gupta PK, Sidiqui MK, et al. A deep learning based model for the detection of pneumonia from chest X-ray images using VGG-16 and neural networks. Procedia Comput Sci. 2023;218:357-66.
  5. Panwar H, Gupta PK, Siddiqui MK, et al. Application of deep learning for fast detection of COVID-19 in X-rays using nCOVnet. Chaos Solitons Fractals. 2020 May;138:109944.
  6. Sarker L, Islam MM, Hannan T, Ahmed Z. A deep learning architecture to detect COVID-19 from chest radiology images. 2020 May 9.
  7. Alapat DJ, Menon MV, Ashok S. A review on detection of pneumonia in chest X-ray images using neural networks. J Biomed Phys Eng. 2022 Dec;12(6):1035-46.
  8. Varshni D, Thakral K, Agarwal L, Nijhawan R, Mittal A. Pneumonia detection using CNN based feature extraction. IEEE. 2019 Feb 22. Available from: https://ieeexplore.ieee.org/document/8869364
  9. Ayan E, Ünver HM. Diagnosis of pneumonia from chest X-ray images using deep learning. IEEE. 2019 Apr 26. Available from: https://ieeexplore.ieee.org/document/8741582
  10. Tang YX, Tang YB, Peng Y, Yan K, Bagheri M, Redd BA, Brandon CJ, Lu Z, Han M, Xiao J, Summers RM. Automated abnormality classification of chest radiographs using deep convolutional neural networks. Nat Biomed Eng. 2020 May 14;4(5):409-20. doi: 10.1038/s41746-020-0273-z.
  11. Chouhan V, Singh SK, Khamparia A, Gupta D, Tiwari P, Moreira C, Damaševičius R, De Albuquerque VH. A novel transfer learning based approach for pneumonia detection in chest X-ray images. Appl Sci. 2020;10(2):559. Available from: https://www.mdpi.com/2076-3417/10/2/559
  12. Abiyev RH, Ma’aitah MKS. Deep convolutional neural networks for chest diseases detection. J Healthc Eng. 2018;2018:6415973. doi: 10.1155/2018/6415973.
  13. Rahmat T, Ismail A, Aliman S. Chest X-ray image classification using faster R-CNN. Malaysian J Comput. 2019;4(1):225-36.
  14. Jain R, Nagrath P, Kataria G, Kaushik VS, Hemanth DJ. Pneumonia detection in chest X-ray images using convolutional neural networks and transfer learning. Measurement. 2020;165:108046. doi: 10.1016/j.measurement.2020.108046.
  15. Nandi R, Mulimani M. Detection of COVID-19 from X-rays using hybrid deep learning models. Res Biomed Eng. 2021;37(4):687-95. doi: 10.1007/s42600-021-00121-2.
Ahead of Print Subscription Review Article
Volume 13
03
Received 18/10/2024
Accepted 29/10/2024
Published 13/11/2024
Publication Time 26 Days
360

Login


My IP

PlumX Metrics