Deep learning approach to describe and classify fungi microscopic images

TL;DR

This paper presents a deep learning method using neural networks and Fisher Vector encoding to classify fungi microscopic images, aiming to speed up diagnosis and reduce costs by potentially replacing biochemical tests.

Contribution

The study introduces a novel deep neural network approach combined with Fisher Vector encoding for fungi species classification from microscopic images, improving diagnosis speed and cost-efficiency.

Findings

Potential to reduce diagnosis time by 2-3 days

Significant cost reduction in fungal identification

Effective classification accuracy demonstrated

Abstract

Preliminary diagnosis of fungal infections can rely on microscopic examination. However, in many cases, it does not allow unambiguous identification of the species by microbiologist due to their visual similarity. Therefore, it is usually necessary to use additional biochemical tests. That involves additional costs and extends the identification process up to 10 days. Such a delay in the implementation of targeted therapy may be grave in consequence as the mortality rate for immunosuppressed patients is high. In this paper, we apply a machine learning approach based on deep neural networks and Fisher Vector (advanced bag-of-words method) to classify microscopic images of various fungi species. Our approach has the potential to make the last stage of biochemical identification redundant, shortening the identification process by 2-3 days, and reducing the cost of the diagnosis.