Radiographic Pneumonia Detection and Multiclass Classification Using Deep Learning Models

The high prevalence of pneumonia in Ethiopia, where diagnostic tools are scarce and access to healthcare is uneven, particularly in rural areas, is addressed in this paper by presenting an advanced method for automating pneumonia detection and classification using deep learning and image processing techniques. Rapid, precise and automated diagnoses are provided by the suggested method, which enhances healthcare delivery and lowers mortality. The method starts with systematic preprocessing of chest X-ray images, which includes contrast enhancement, noise reduction and normalization to guarantee high-quality inputs for analysis. To increase the performance of Convolutional Neural Networks (CNNs), the study uses Gabor filters for feature extraction, which enhances textural information. The images are categorized into three classes using a three-way SoftMax classifier normal, viral and bacterial pneumonia. The best-performing CNN model out of the four that were tested was DenseNet201 with a testing accuracy of 97.39% and a training accuracy of 99.40%. This high level of accuracy indicates that the proposed system is highly effective in distinguishing between normal and pathological lung conditions, suggesting its potential for enhancing diagnostic precision and efficiency in clinical settings.