The application of Hybrid deep learning Approach to evaluate chest ray images for the diagnosis of pneumonia in children

  1. Mohammad Ali Abbasa
  2. Syed Usama Khalid Bukhari
  3. Syed Khuzaima Arssalan Bokhari
  4. manal niazi

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Background

Pneumonia is a leading cause of morbidity and mortality worldwide, particularly among the developing nations. Pneumonia is the most common cause of death in children due to infectious etiology. Early and accurate Pneumonia diagnosis could play a vital role in reducing morbidity and mortality associated with this ailment. In this regard, the application of a new hybrid machine learning vision-based model may be a useful adjunct tool that can predict Pneumonia from chest X-ray (CXR) images.

Aim & Objective

we aimed to assess the diagnostic accuracy of hybrid machine learning vision-based model for the diagnosis of Pneumonia by evaluating chest X-ray (CXR) images

Materials & Methods

A total of five thousand eight hundred and fifty-six digital X-ray images of children from ages one to five were obtained from the Chest X-Ray Pneumonia dataset using the Kaggle site. The dataset contains fifteen hundred and eighty-three digital X-ray images categorized as normal, where four thousand two hundred and seventy-three digital X-ray images are categorized as Pneumonia by an expert clinician. In this research project, a new hybrid machine learning vision-based model has been evaluated that can predict Pneumonia from chest X-ray (CXR) images. The proposed model is a hybrid of convolutional neural network and tree base algorithms (random forest and light gradient boosting machine). In this study, a hybrid architecture with four variations and two variations of ResNet architecture are employed, and a comparison is made between them.

Results

In the present study, the analysis of digital X-ray images by four variations of hybrid architecture RN-18 RF, RN-18 LGBM, RN-34 RF, and RN-34 LGBM, along with two variations of ResNet architecture, ResNet-18 and ResNet-30 have revealed the diagnostic accuracy of 97.78%, 96.42%, 97.1%,96.59%, 95.05%, and 95.05%, respectively.

Discussion

The analysis of the present study results revealed more than 95% diagnostic accuracy for the diagnosis of Pneumonia by evaluating chest x-ray images of children with the help of four variations of hybrid architectures and two variations of ResNet architectures. Our findings are in accordance with the other published study in which the author used the deep learning algorithm Chex-Net with 121 layers.

Conclusion

The hybrid machine learning vision-based model is a useful tool for the assessment of chest x rays of children for the diagnosis of Pneumonia.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.12.03.20243550: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.12.03.20243550v1 on medRxiv