Deep convolutional neural network: a novel approach for the detection of Aspergillus fungi via stereomicroscopy

Haozhong Ma; Jinshan Yang; Xiaolu Chen; Xinyu Jiang; Yimin Su; Shanlei Qiao; Guowei Zhong

doi:10.1007/s12275-021-1013-z

Articles

Page Path: HOME > J. Microbiol > Volume 59(6); 2021 > Article

Journal Article
Deep convolutional neural network: a novel approach for the detection of Aspergillus fungi via stereomicroscopy: Haozhong Ma , Jinshan Yang , Xiaolu Chen , Xinyu Jiang , Yimin Su , Shanlei Qiao , Guowei Zhong; Journal of Microbiology 2021;59(6):563-572.
DOI: https://doi.org/10.1007/s12275-021-1013-z
Published online: March 29, 2021

Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, P. R. ChinaCenter for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, P. R. China

Corresponding author: Shanlei Qiao ,
Guowei Zhong ,

Received: 11 January 2021 • Revised: 10 February 2021 • Accepted: 10 February 2021

prev next

52 Views
0 Download
11 Web of Science
12 Crossref
11 Scopus

Full Article

Abstract

Fungi of the genus Aspergillus are ubiquitously distributed in nature, and some cause invasive aspergillosis (IA) infections in immunosuppressed individuals and contamination in agricultural products. Because microscopic observation and molecular detection of Aspergillus species represent the most operator-dependent and time-intensive activities, automated and cost-effective approaches are needed. To address this challenge, a deep convolutional neural network (CNN) was used to investigate the ability to classify various Aspergillus species. Using a dissecting microscopy (DM)/stereomicroscopy platform, colonies on plates were scanned with a 35× objective, generating images of sufficient resolution for classification. A total of 8,995 original colony images from seven Aspergillus species cultured in enrichment medium were gathered and autocut to generate 17,142 image crops as training and test datasets containing the typical representative morphology of conidiophores or colonies of each strain. Encouragingly, the Xception model exhibited a classification accuracy of 99.8% on the training image set. After training, our CNN model achieved a classification accuracy of 99.7% on the test image set. Based on the Xception performance during training and testing, this classification algorithm was further applied to recognize and validate a new set of raw images of these strains, showing a detection accuracy of 98.2%. Thus, our study demonstrated a novel concept for an artificial-intelligence-based and cost-effective detection
method
ology for Aspergillus organisms, which also has the potential to improve the public’s understanding of the fungal kingdom.

Keywords: C. glycerinogenes;MVA pathway;acetyl coenzyme A;mevalonate;pinene;squalene

Figure & Data

References

Citations

Citations to this article as recorded by

Outlier classification for microbiological open set recognition
Yining Pan, Wei Ye, Dejin Xie, Jiaoyu Wang, Hongkai Wang, Haiping Qiu
Computers and Electronics in Agriculture.2024; 224: 109104. CrossRef
Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review
Buket Baddal, Ferdiye Taner, Dilber Uzun Ozsahin
Diagnostics.2024; 14(5): 484. CrossRef
Current status and new experimental diagnostic methods of invasive fungal infections after hematopoietic stem cell transplantation
Zhenhua Tang, HaiTao Wang, Yuankai Liu, Chen Wang, Xinye Li, Qiong Yang
Archives of Microbiology.2024;[Epub] CrossRef
Artificial Intelligence: Exploring utility in detection and typing of fungus with futuristic application in fungal cytology
Nidhi Singla, Reetu Kundu, Pranab Dey
Cytopathology.2024; 35(2): 226. CrossRef
Label-Free Optical Transmission Tomography for Direct Mycological Examination and Monitoring of Intracellular Dynamics
Eliott Teston, Marc Sautour, Léa Boulnois, Nicolas Augey, Abdellah Dighab, Christophe Guillet, Dea Garcia-Hermoso, Fanny Lanternier, Marie-Elisabeth Bougnoux, Frédéric Dalle, Louise Basmaciyan, Mathieu Blot, Pierre-Emmanuel Charles, Jean-Pierre Quenot, Bi
Journal of Fungi.2024; 10(11): 741. CrossRef
Artificial Intelligence and Microbiology
Mert Kandilci, Gülfer Yakıcı, Mediha Begüm Kayar
Experimental and Applied Medical Science.2024; 5(2): 119. CrossRef
Attention-Guided Transfer Learning for Identification of Filamentous Fungi Encountered in the Clinical Laboratory
Tsi-Shu Huang, Kevin Wang, Xiu-Yuan Ye, Chii-Shiang Chen, Fu-Chuen Chang, Paschalis Vergidis, Yang Zhang
Microbiology Spectrum.2023;[Epub] CrossRef
Artificial Intelligence Based Test Systems to Resist Waterborne Diseases by Early and Rapid Identification of Pathogens: A Review
Chethna Joy, G. Naveen Sundar, D. Narmadha
SN Computer Science.2023;[Epub] CrossRef
Plant and Animal Species Recognition Based on Dynamic Vision Transformer Architecture
Hang Pan, Lun Xie, Zhiliang Wang
Remote Sensing.2022; 14(20): 5242. CrossRef
Machine Learning and Deep Learning Based Computational Approaches in Automatic Microorganisms Image Recognition: Methodologies, Challenges, and Developments
Priya Rani, Shallu Kotwal, Jatinder Manhas, Vinod Sharma, Sparsh Sharma
Archives of Computational Methods in Engineering.2022; 29(3): 1801. CrossRef
A Small Sample Recognition Model for Poisonous and Edible Mushrooms based on Graph Convolutional Neural Network
Li Zhu, Xin Pan, Xinpeng Wang, Fu Haito, Abdul Rehman Javed
Computational Intelligence and Neuroscience.2022; 2022: 1. CrossRef
Morphologic identification of clinically encountered moulds using a residual neural network
Ran Jing, Xiang-Long Yin, Xiu-Li Xie, He-Qing Lian, Jin Li, Ge Zhang, Wen-Hang Yang, Tian-Shu Sun, Ying-Chun Xu
Frontiers in Microbiology.2022;[Epub] CrossRef

Cite this Article

Cite this Article: export Copy Download Format; Close

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

RIS — For EndNote, ProCite, RefWorks, and most other reference management software
BibTeX — For JabRef, BibDesk, and other BibTeX-specific software

Include:

Citation for the content below
Citation and abstract for the content below

Deep convolutional neural network: a novel approach for the detection of Aspergillus fungi via stereomicroscopy

J. Microbiol. 2021;59(6):563-572. Published online March 29, 2021

DOI: https://doi.org/10.1007/s12275-021-1013-z

Related articles