ItemArticle

Novel Pooling-Based VGG-Lite for Pneumonia and Covid-19 Detection From Imbalanced Chest X-Ray Datasets

Title
Novel Pooling-Based VGG-Lite for Pneumonia and Covid-19 Detection From Imbalanced Chest X-Ray Datasets
Creator
Roy, Santanu; Suresh, Ashvath; Sahu, Palak; Roy, Achintya; Gupta, Tulika Rudra
Description
This paper proposes a novel pooling-based VGG-Lite model in order to mitigate class imbalance issues in Chest X-Ray (CXR) datasets. Automatic Pneumonia detection from CXR images by deep learning model has emerged as a prominent and dynamic area of research, since the inception of the new Covid-19 variant in 2020. However, the standard Convolutional Neural Network (CNN) models encounter challenges associated with class imbalance, a prevalent issue found in many medical datasets. The innovations introduced in the proposed model architecture include: (I) A very lightweight CNN model, VGG-Lite, is proposed as a base model, inspired by VGG-16 and MobileNet-V2 architecture. (II) On top of this base model, we leverage an Edge Enhanced Module (EEM) through a parallel branch, consisting of a negative image layer, and a novel custom pooling layer 2Max-Min Pooling. This 2Max-Min Pooling layer is entirely novel in this investigation, providing more attention to edge components within pneumonia CXR images. Thus, it works as an efficient spatial attention module (SAM). We have implemented the proposed framework on two separate CXR datasets. The first dataset is obtained from a readily available source on the internet, and the second dataset is a more challenging CXR dataset, assembled by our research team from three different sources. Experimental results reveal that our proposed framework has outperformed pre-trained CNN models, and three recent trend existing models Vision Transformer, Pooling-based Vision Transformer (PiT) and PneuNet, by substantial margins on both datasets. The proposed framework VGG-Lite with EEM, has achieved a macro average of 95% accuracy, 97.1% precision, 96.1% recall, and 96.6% F1 score on the Pneumonia Imbalance CXR dataset, without employing any pre-processing technique. 2017 IEEE.
Source
IEEE Transactions on Emerging Topics in Computational Intelligence;Volume;9;Issue;6;pp.4231-4242
Date
01-01-2025
Publisher
Institute of Electrical and Electronics Engineers Inc.
Subject
chest X-ray (CXR) images; class-imbalance problem; Complementary and edge enhanced module (CEEM); novel pooling technique; pneumonia and COVID-19 detection; spatial attention module (SAM); vision transformer (ViT)
Coverage
Roy S., Department of Computer Science and Engineering, Christ (Deemed to be University) Bangalore, Bangalore, 560029, India, Manipal Academy of Higher Education (MAHE), Manipal, 576104, India; Suresh A., NIIT University, Department of Computer Science and Engineering, Jaipur, 301705, India; Sahu P., National Institute of Technology Warangal, Department of Mathematics, Hanamkonda, 506004, India; Roy A., Indian Institute of Technology, Kharagpur, 721302, India, Harvard Medical School, Dana-Farber Cancer Institute, Boston, 02115, MA, United States; Gupta T.R., Harvard Medical School, Dana-Farber Cancer Institute, Boston, 02115, MA, United States
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 2471285X;
Format
online
Language
English
Type
Article

Citation

Roy, Santanu; Suresh, Ashvath; Sahu, Palak; Roy, Achintya; Gupta, Tulika Rudra, “Novel Pooling-Based VGG-Lite for Pneumonia and Covid-19 Detection From Imbalanced Chest X-Ray Datasets,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/22965.

Output Formats