AIDeveloper: Deep Learning Image Classification in Life Science and Beyond.
artificial intelligence
deep neural networks
graphical user interface
image processing
software
Journal
Advanced science (Weinheim, Baden-Wurttemberg, Germany)
ISSN: 2198-3844
Titre abrégé: Adv Sci (Weinh)
Pays: Germany
ID NLM: 101664569
Informations de publication
Date de publication:
06 2021
06 2021
Historique:
revised:
08
02
2021
received:
30
09
2020
entrez:
9
6
2021
pubmed:
10
6
2021
medline:
15
12
2021
Statut:
ppublish
Résumé
Artificial intelligence (AI)-based image analysis has increased drastically in recent years. However, all applications use individual solutions, highly specialized for a particular task. Here, an easy-to-use, adaptable, and open source software, called AIDeveloper (AID) to train neural nets (NN) for image classification without the need for programming is presented. AID provides a variety of NN-architectures, allowing to apply trained models on new data, obtain performance metrics, and export final models to different formats. AID is benchmarked on large image datasets (CIFAR-10 and Fashion-MNIST). Furthermore, models are trained to distinguish areas of differentiated stem cells in images of cell culture. A conventional blood cell count and a blood count obtained using an NN are compared, trained on >1.2 million images, and demonstrated how AID can be used for label-free classification of B- and T-cells. All models are generated by non-programmers on generic computers, allowing for an interdisciplinary use.
Identifiants
pubmed: 34105281
doi: 10.1002/advs.202003743
pmc: PMC8188199
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e2003743Subventions
Organisme : Deutsche Forschungsgemeinschaft
ID : 399422891
Organisme : Marie Sklodowska-Curie Actions
ID : 641639
Organisme : Mechthild Harf Research Grant
ID : DKMS-SLS-MHG-2016-02
Organisme : H2020 Marie Skłodowska-Curie Actions
ID : 641639
Informations de copyright
© 2021 The Authors. Advanced Science published by Wiley-VCH GmbH.
Références
Cell. 2018 Sep 20;175(1):266-276.e13
pubmed: 30166209
Cytotherapy. 2020 Jan;22(1):21-26
pubmed: 31883948
Stem Cells. 2004;22(3):377-84
pubmed: 15153614
Sci Rep. 2017 Jul 27;7(1):6654
pubmed: 28751719
Elife. 2018 Jan 13;7:
pubmed: 29331015
Nat Rev Clin Oncol. 2019 Nov;16(11):703-715
pubmed: 31399699
PLoS Biol. 2018 Jul 3;16(7):e2005970
pubmed: 29969450
Nat Methods. 2015 Mar;12(3):199-202, 4 p following 202
pubmed: 25643151
J Immunol Res. 2017;2017:1254792
pubmed: 29164154
Nat Methods. 2017 Apr;14(4):403-406
pubmed: 28218899
Nat Methods. 2012 Jul;9(7):671-5
pubmed: 22930834
Tissue Antigens. 1974;4(4):269-74
pubmed: 4415728
Cytometry A. 2019 Aug;95(8):836-842
pubmed: 31081599
J Cell Physiol. 1998 Jul;176(1):57-66
pubmed: 9618145
Med Image Comput Comput Assist Interv. 2013;16(Pt 2):411-8
pubmed: 24579167
Nat Methods. 2019 Dec;16(12):1226-1232
pubmed: 31570887
Nature. 2017 Jun 28;546(7660):686
pubmed: 28658222
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
BMC Bioinformatics. 2008 Nov 15;9:482
pubmed: 19014601
Nat Methods. 2012 Jun 28;9(7):676-82
pubmed: 22743772
QJM. 2003 Oct;96(10):711-29
pubmed: 14500858
J Vis Exp. 2018 Nov 19;(141):
pubmed: 30507910
Nat Methods. 2018 May;15(5):355-358
pubmed: 29608556
Adv Sci (Weinh). 2021 Jun;8(11):e2003743
pubmed: 34105281
Nat Methods. 2021 Oct;18(10):1192-1195
pubmed: 34594030
Sci Rep. 2014 Mar 11;4:4348
pubmed: 24614613
Nat Methods. 2020 Jun;17(6):595-599
pubmed: 32451476
Science. 1975 May 16;188(4189):732-4
pubmed: 1079095
Cell Stem Cell. 2018 Jun 01;22(6):824-833
pubmed: 29859173
Genome Biol. 2006;7(10):R100
pubmed: 17076895
Nat Mater. 2019 May;18(5):414-418
pubmed: 31000804