Search papers, labs, and topics across Lattice.
This paper investigates the performance limitations of MicrobiaNet, a cardinality classification model for bacterial colony counting, using explainable AI (XAI) techniques. XAI analysis reveals that high visual similarity between colony classes, particularly for counts of three or more, is the primary factor limiting performance, challenging previous assumptions about the model's inherent limitations. The study suggests that future research should focus on models that explicitly address visual similarity or explore density estimation methods to improve colony counting accuracy.
Turns out, the best colony counter struggles not because of the model, but because all those colonies look too darn similar.
Automatic bacterial colony counting is a highly sought-after technology in modern biological laboratories because it eliminates manual counting effort. Previous work has observed that MicrobiaNet, currently the best-performing cardinality classification model for colony counting, has difficulty distinguishing colonies of three or more individuals. However, it is unclear if this is due to properties of the data together with inherent characteristics of the MicrobiaNet model. By analysing MicrobiaNet with explainable artificial intelligence (XAI), we demonstrate that XAI can provide insights into how data properties constrain cardinality classification performance in colony counting. Our results show that high visual similarity across classes is the key issue hindering further performance improvement, revising prior assertions about MicrobiaNet. These findings suggest future work should focus on models that explicitly incorporate visual similarity or explore density estimation approaches, with broader implications for neural network classifiers trained on imbalanced datasets.
