Antigen Ki67 is a nuclear protein that serves as a helpful immunohistochemistry marker in cancer diagnosis. In the current clinical practice, the Ki67 proliferation index is either estimated visually from the stained tissue under an optical microscope or tediously counted in the small region of digitalized tissue scans using specialized vision software. The thesis aims to design, train, and evaluate a convolutional neural network architecture capable of predicting the Ki67 proliferation index from histopathological breast tissue images based on clinical data provided by Masaryk Memorial Cancer Institute. The student will familiarise themself and present the basics of digital histopathology, emphasizing the Ki67 cellular marker. They collect and preprocess the input data, design, train, and evaluate the model in the cloud infrastructure of the RationAI group. The student will optionally contribute the code to HistoPipe, the RationAI open-source library for digital histopathology.