Classifying bacteria clones using attention-based deep multiple instance learning interpreted by persistence homology
This work tackles the problem of classifying highly similar bacteria clones, previously considered impossible, which could benefit medical diagnostics and research.
This paper addresses the challenging problem of distinguishing between highly similar clones of the same bacteria species (Klebsiella pneumoniae) using only microscopic images. The authors achieved an accuracy of 0.9 in classifying these bacteria clones.
In this work, we analyze if it is possible to distinguish between different clones of the same bacteria species (Klebsiella pneumoniae) based only on microscopic images. It is a challenging task, previously considered impossible due to the high clones similarity. For this purpose, we apply a multi-step algorithm with attention-based multiple instance learning. Except for obtaining accuracy at the level of 0.9, we introduce extensive interpretability based on CellProfiler and persistence homology, increasing the understandability and trust in the model.