Agriculture is essential for sustaining the global population and is a crucial element in economic returns and food supply. However, plant leaf diseases are a major threat to agriculture and economy since they retard yield and increase cost of production. Because of high demand for broccoli, a wonderful and profitable crop, in the market, it has tremendous business opportunities for farmers. Nevertheless, similar to many other food crops, it is vulnerable to diseases which may affect its production and quality. Prevent losses from these diseases requires early detection of the disease affecting the leaves and with further enhancement of the technology, especially deep learning. In this research, an application of a new, specifically designed CNN model for the differentiation of healthy and diseased broccoli leaves is proposed. Data were collected directly from the field using mobile cameras and the images were sorted under healthy and unhealthy classes respectively. A new CNN model with an architecture specific to this dataset was designed and trained in this project using Keras. As evaluated from the result, the model proved efficient providing an accurate prediction on the health status of the leaf. The use of deep learning in disease diagnosis in crops enables farmers to make timely interventions thus protecting their crops, their potential economic value and nutritional value. This research acknowledges the possibilities of applying advanced technological improvement on the practice of agriculture.