Article (Scientific journals)
Deep neural networks outperform human expert's capacity in characterizing bioleaching bacterial biofilm composition
Buetti-Dinh, Antoine; Galli, Vanni; Bellenberg, Sören et al.
2019In Biotechnology Reports
Peer Reviewed verified by ORBi
 

Files


Full Text
main.pdf
Publisher postprint (1.46 MB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Acidophiles; Bacterial biofilm; Biomining; Deep learning; Convolutional neural networks; Microscopy imaging
Abstract :
[en] Background Deep neural networks have been successfully applied to diverse fields of computer vision. However, they only outperform human capacities in a few cases. Methods The ability of deep neural networks versus human experts to classify microscopy images was tested on biofilm colonization patterns formed on sulfide minerals composed of up to three different bioleaching bacterial species attached to chalcopyrite sample particles. Results A low number of microscopy images per category (<600) was sufficient for highly efficient computational analysis of the biofilm's bacterial composition. The use of deep neural networks reached an accuracy of classification of ∼90% compared to ∼50% for human experts. Conclusions Deep neural networks outperform human experts’ capacity in characterizing bacterial biofilm composition involved in the degradation of chalcopyrite. This approach provides an alternative to standard, time-consuming biochemical methods.
Disciplines :
Biotechnology
Environmental sciences & ecology
Author, co-author :
Buetti-Dinh, Antoine;  Università della Svizzera italiana - USI > Institute of Computational Science, Faculty of Informatics ; Swiss Institute of Bioinformatics - SIB
Galli, Vanni;  University of Applied Sciences of Southern Switzerland > Institute for Information Systems and Networking
Bellenberg, Sören;  Universität Duisburg-Essen > Fakultät für Chemie, Biofilm Centre
Ilie, Olga;  Università della Svizzera italiana - USI > Institute of Computational Science, Faculty of Informatics ; Swiss Institute of Bioinformatics - SIB
Herold, Malte ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Christel, Stephan
Boretska, Mariia
Pivkin, Igor V.
Wilmes, Paul ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Sand, Wolfgang
Vera, Mario
Dopson, Mark
External co-authors :
yes
Language :
English
Title :
Deep neural networks outperform human expert's capacity in characterizing bioleaching bacterial biofilm composition
Publication date :
07 March 2019
Journal title :
Biotechnology Reports
ISSN :
2215-017X
Publisher :
Elsevier, Netherlands
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Systems Biomedicine
European Projects :
FP7 - 321567 - ERASYSAPP - ERASysAPP - Systems Biology Applications
Name of the research project :
SysMetEx
Funders :
FNR - Fonds National de la Recherche [LU]
CE - Commission Européenne [BE]
Available on ORBilu :
since 21 May 2019

Statistics


Number of views
187 (21 by Unilu)
Number of downloads
4 (4 by Unilu)

Scopus citations®
 
65
Scopus citations®
without self-citations
63
OpenCitations
 
42

Bibliography


Similar publications



Contact ORBilu