Developing countries including Uganda face a major public health challenge from the lower respiratory tract Infections (LRTIs), mainly common within the vulnerable groups encircling children, elderly, and immunocompromised individuals. Pneumonia alone is said to account for 10% of under-five deaths in Uganda. Tuberculosis and bronchitis are also common LRTIs and are mainly caused by numerous pathogens like fungi, bacteria, and viruses; according to the World Health Organization (WHO), over 3 million deaths occur yearly on the globe and this is due to late diagnosis being a major contributor to this high mortality rate. However, even the existing deep learning approaches have limited performance arising from poor feature extraction on poor-quality images of LRTIs and the models often lack transparency in their decision-making process. Thus making it difficult for medical experts to understand and trust the AI results. This chapter presents a gradient weighting approach to provide visual explanations of the deep learning models based on the activation maps around the most important regions of medical images used to diagnose pneumonia. The models include vision transformers, MobileNet, VGG19, and ResNet50 with an 86.86%, 100%, 90.54%, and 93.22% validation accuracy, respectively. The activation maps are used as explainers to enhance the trustworthiness of the models for the experts and improve adoption of AI tools for medical imaging in constrained resource settings.