EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Fungal Identification with Deep Learning on Time-Lapse Images

Marjan Mansourvar, Karol Rafal Charylo, Rasmus John Normand Frandsen, Steen Smidth Brewer, Jakob Blæsbjerg Hoof

Information · 05.02.2025 · 16 (2) · 109

DOI: 10.3390/info16020109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 05.02.2025. Verfasst von Marjan Mansourvar und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The identification of species within filamentous fungi is crucial in various fields such as agriculture, environmental monitoring, and medical mycology. Traditional identification methods based on morphology have a low demand for advanced equipment usage and heavily depend on manual observation and expertise. However, this approach may struggle to differentiate between species in a genus due to their potential visual similarities, making the process time-consuming and subjective. In this study, we present an AI-based fungal species recognition model that utilizes deep learning techniques applied to time-lapse images. The training dataset, derived from fungi strains in the IBT Culture Collection, comprised 26,451 high-resolution images representing 110 species from 35 genera. The dataset was divided into a training set and validation subsets. We implemented three advanced deep learning architectures—ResNet50, DenseNet-121, and Vision Transformer (ViT)—to assess their effectiveness in accurately classifying fungal species. By utilizing images from early growth stages (days 2–3.5) for training and testing and later stages (days 4–7) for validation, our approach shortens the fungal identification process by 2–3 days, significantly reducing the associated workload and costs. Among the models, the Vision Transformer achieved the highest accuracy of 92.6%, demonstrating the effectiveness of our method. This work contributes to the automation of fungal identification, providing a reliable and efficient solution for monitoring fungal growth and diversity over time, which would be useful for culture collections or other institutions that handle a large number of new isolates in their daily work.

Zitieren

APA

Mansourvar, M., Charylo, K. R., Frandsen, R. J. N., Brewer, S. S., & Hoof, J. B. (2025). Automated Fungal Identification with Deep Learning on Time-Lapse Images. Information, 16(2), 109. https://doi.org/10.3390/info16020109

Vancouver

Mansourvar M, Charylo KR, Frandsen RJN, Brewer SS, Hoof JB. Automated Fungal Identification with Deep Learning on Time-Lapse Images. Information. 2025;16(2):109. doi:10.3390/info16020109

BibTeX
@article{Mansourvar2025,
  author = {Mansourvar, Marjan and Charylo, Karol Rafal and Frandsen, Rasmus John Normand and Brewer, Steen Smidth and Hoof, Jakob Blæsbjerg},
  title = {Automated Fungal Identification with Deep Learning on Time-Lapse Images},
  journal = {Information},
  year = {2025},
  volume = {16},
  number = {2},
  pages = {109},
  doi = {10.3390/info16020109}
}
Kostenlos starten →