<p>Deep Learning has recently been in trend when it comes to medical image analysis as it uses Convolution Neural Network (CNN), which utilizes multi-layer processing to extract intricate and complex features from the data. Similar to other research work, we used Chest X-ray (CXR) images as our dataset and classified them into five categories of lung disease, namely bacterial pneumonia, COVID-19, normal, pneumothorax, and tuberculosis. This study proposes a novel CNN, UCD_Net, which uses a convolutional upsampling layer featuring bicubic interpolation along with a stack of convolution layers before inputting the images into the fine-tuned Xception model and resorts to multiple dilated convolution layers before predicting output. This 2D CNN model is used to achieve optimal feature extraction within minimal time and space constraints. The dataset was divided into a ratio of 0.66 and 0.33 for the training set and testing set, respectively. The best performance is recorded by our proposed model, UCD_Net, with a training accuracy equal to 99.23%, a validation accuracy equal to 98.05%, a recall of 97.8%, a precision of 97.2%, and a fi-score equal to 97.6%. The model performance on the same dataset is also compared to four state-of-the-art architectures, namely ResNet 50, VGG16, Xception, and ResNet152. After our UCD_Net, the best performance was seen using ResNet 50, with accuracy, recall, and precision of 95.45%, 94.5%, and 95.2%, respectively. Training the model on a larger dataset and subsequent fine-tuning can lead to more research and model development.</p>