Investigation of cardinality classification for bacterial colony counting using explainable artificial intelligence

TL;DR

This paper uses explainable AI to analyze why bacterial colony counting models struggle with similar-looking colonies, revealing that visual similarity limits classification accuracy.

Contribution

It demonstrates how XAI can uncover data property constraints on model performance, challenging prior assumptions about MicrobiaNet.

Findings

High visual similarity across classes hampers classification accuracy.

XAI provides insights into data-model interaction in colony counting.

Future models should address visual similarity or use density estimation.

Abstract

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.