Performance Enhancement of Convolution Neural Network for COVID-19 Classification
Year: 2024
Type: dissertation
Abstract: This Master’s thesis investigates a deep learning–based approach for accurate detection of COVID-19 from chest X-ray (CXR) images using Convolutional Neural Networks (CNNs). Accurate and timely identification of COVID-19 cases from radiographic images is essential for effective clinical decision-making, particularly in situations where laboratory testing resources are limited. The study focuses on improving CNN performance through systematic hyperparameter optimization and transfer learning techniques. A VGG16 architecture pretrained on ImageNet was used as the base model, enabling effective feature extraction from medical images while reducing training complexity. A large-scale dataset of approximately 15,000 chest X-ray images was utilized. Comprehensive preprocessing steps including normalization, resizing, and data augmentation were applied to improve model robustness and generalization. Key hyperparameters — including batch size, learning rate, dropout rate, and dataset size — were systematically tuned through extensive experimentation. Model performance was evaluated using standard classification metrics such as accuracy, precision, recall (sensitivity), F1-score, ROC-AUC, and confusion matrices. The models were implemented using Python with TensorFlow/Keras and trained on Google Colaboratory to leverage high-performance computational resources. The optimized VGG16 model achieved a classification accuracy of 98.5% and sensitivity of 97.8%, significantly reducing false negatives — a critical factor in medical diagnosis. Experimental results demonstrate that appropriate hyperparameter selection, particularly a learning rate of 0.001 and batch size of 64, provides the best balance between performance and stability. This research confirms that systematic hyperparameter tuning can substantially enhance CNN performance for medical image classification and supports the development of reliable AI-assisted diagnostic systems for real-time COVID-19 screening. The methodology can be extended to other medical imaging applications and disease detection tasks.
Authors: Ghimirey, Bikash, Chitrakar, Roshan
Institution: Pokhara University
Language: English
Topic: COVID-19 diagnosis using AI
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7131246595