Deep learning classification of bacteria clones explained by persistence homology

In this work, we automatically distinguish between different clones of the same bacteria species (Klebsiella pneumoniae) based only on microscopic images. It is a challenging task, previously seemed unreachable due to the high clones' similarity. For this purpose, we apply a multi-step algorithm with attention-based deep multiple instance learning, which returns parts of the image crucial to the prediction. Except for obtaining high accuracy, we introduce extensive explainability based on persistence homology, increasing the understandability and trust in the model. Our work opens a plethora of research pathways towards cheaper and faster epidemiological management.