Purpose: The early and exact classification and identification is necessary for proper treatment which needs excessive time and effort of professionals. This examination is meant to foster a task to recognize Pneumonia and Coronavirus utilizing the idea of the Convolutional Neural Network (CNN) for picture grouping and is centered on building the profound learning model that aids in the characterization utilizing chest X-beam pictures in one of the quick and financially savvy ways.
Design/Methodology/Approach: This study uses a wide dataset comprising of chest X-beam pictures accumulated from the Mendeley dataset. Include extraction strategies like picture pre-handling and data augmentation are applied to improve the arrangement execution. The framework utilizes the ResNet-18, which is a sort of CNN model for order. The examination includes assessing the exactness, accuracy, review, F1 score, and area under the receiver working trademark bend (AUC-ROC) for every classification model.
Findings/Result: The dataset is separated into preparing and testing subsets to ensure unbiased performance evaluation. For the development and deployment of an accurate and reliable system, factors like data quality, model interpretability, and ethical considerations are considered. We successfully used the pre-trained ResNet-18 CNN model with chest X-ray image data that helped to build a robust classification system with a learning rate of 0.0001 and epoch size 10 having approx. 98.12% train accuracy and 97.70% test accuracy.
Since the start of the project, we researched several methodologies to build the system. The other models (e.g., ResNet-50) were too big algorithms for our problem which created a problem of overfitting. Hence performance was not very accurate. So, we planned to go with the ResNet-18 model. As per our plan, we developed a system that operates as expected.
Originality/Value: It helps medical professionals in diagnosing and managing these diseases.
Paper Type: Research paper