Deep learning approach to describe and classify fungi microscopic images
This addresses a critical issue for immunosuppressed patients by reducing delays in fungal infection diagnosis, though it appears incremental as it builds on existing deep learning and bag-of-words methods.
The paper tackles the problem of ambiguous identification of fungi species from microscopic images by microbiologists, which delays targeted therapy, by applying a deep learning and Fisher Vector approach to classify these images, potentially shortening the identification process by 2-3 days and reducing diagnosis costs.
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.