Vol2-2art1 AI Fungal Identification by Colony

J. Benjamin Stielow^1,2, Sarah A. Ahmed^2,3, G. Sybren de Hoog^2,4#

¹Helmholtz Institute for One Health, Bioinformatics, Greifswald, Germany; ²Foundation Atlas of Clinical Fungi, Hilversum, The Netherlands; ³Department of Microbiology, Faculty of Medicine, Kuwait University, Kuwait; ⁴Radboudumc-CWZ Center of Expertise for Mycology, Nijmegen, The Netherlands

Abstract

Objectives. We developed and tested multiple computer-vision image classifiers for their ability to identify a large set of opportunistic and pathogenic molds by their colony appearance. Aim of the study was to create a comprehensive global benchmark towards computer vision driven diagnostics of pathogenic microbes. If successfully implemented, high resource clinical settings could greatly benefit from this adjunct technique to supplement molecular sequencing and mass spectrometry diagnostic methods, while under low resource conditions in rural and remote geographies, it could provide rapid approximate pathogen identification.
Methods. We selected 114 clinically relevant fungi represented by 123 strains obtained from the images implemented within the ‘Atlas of Clinical Fungi’, to serve as core dataset. The image classifiers were designed with a rigorous testing and evaluation strategy, at a yet unprecedented level of detail. We designed the framework within the TensorFlow environment, testing multiple transfer-learning approaches, as well hybrid architectures comprising features of convolutional neural networks (CNN) and advanced vision transformers (ViT).
Results. We achieved a global identification accuracy of > 88 % for the validation partition with our best model (Test accu. 87 %, Train. accu. 96 %). Simulations indicated that extended training time would lead to further improvement of accuracy, particularly with greater data richness. Our results highlight complex de-black-boxing approaches in interpreting image classification, useful for validating computer-vision driven microbial identification.
Discussion. Besides quantitative limitations of representative strains per tested species, our approach reflects a significant scientific novelty, providing value to the technically simple culturing technique. The method was tested on filamentous molds and a small subset of common bacteria as a control set. The methodology can be universally applied to clinical microbes, rendering the technique attractive for rapid diagnostics and verification of identities from experimental approaches.

#Correspondence: sybren.dehoog@radboudumc.nl

Article info:
Received 14 July 2025
Revised 2 August 2025
Accepted 5 August 2025
Appeared online 14 August 2025
One Health Mycology 2(2): 94-111, 2025
doi.org/10.63049/OHM.25.22.1

Cite this article:
Stielow JB, Ahmed SA, de Hoog GS, 2025. Rapid artificial intelligence-assisted identification of pathogenic fungi by colony architecture. One Health Mycology 2(2), 94-111
This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/ licenses/by-nc-nd/4.0/)

Keywords:
Novel diagnostics, convolutional neural networks, computer vision, fungal pathogens, low-income countries

Article highlights:

• Dataset: 114 filamentous fungi were imaged front- and backside on several culture media to create a reference dataset for colony-based computer vision-based identification.
• Model performance: With targeted augmentation, a ConvNeXtTiny backbone reached 88 % validation and 87 % test accuracy; removing backgrounds reduced VGG16 and DenseNet-121 accuracy by over 20 percentage points. 
• Laboratory utility: The workflow can be adapted to additional fungi, yeasts or bacteria, and maybe an attractive future supplement for identity check and for laboratories where MALDI-ToF or sequencing are unavailable.