Evaluation of deep learning training strategies for the classification of bone marrow cell images

Glüge, Stefan; Balabanov, Stefan; Koelzer, Viktor Hendrik; Ott, Thomas

doi:10.1016/j.cmpb.2023.107924

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-29212

Full metadata record

DC Field	Value	Language
dc.contributor.author	Glüge, Stefan	-
dc.contributor.author	Balabanov, Stefan	-
dc.contributor.author	Koelzer, Viktor Hendrik	-
dc.contributor.author	Ott, Thomas	-
dc.date.accessioned	2023-11-24T15:19:39Z	-
dc.date.available	2023-11-24T15:19:39Z	-
dc.date.issued	2023	-
dc.identifier.issn	0169-2607	de_CH
dc.identifier.issn	1872-7565	de_CH
dc.identifier.uri	https://digitalcollection.zhaw.ch/handle/11475/29212	-
dc.description.abstract	Background and Objective: The classification of bone marrow (BM) cells by light mi- croscopy is an important cornerstone of hematological diagnosis, performed thousands of times a day by highly trained specialists in laboratories worldwide. As the manual evaluation of blood or BM smears is very time-consuming and prone to inter-observer variation, new reliable automated systems are needed. Methods: We aim to improve the automatic classification performance of hematolog- ical cell types. Therefore, we evaluate four state-of-the-art Convolutional Neural Net- work (CNN) architectures on a dataset of 171, 374 microscopic cytological single-cell images obtained from BM smears from 945 patients diagnosed with a variety of hema- tological diseases. We further evaluate the effect of an in-domain vs. out-of-domain pre-training, and assess whether class activation maps provide human-interpretable ex- planations for the models’ predictions. Results: The best performing pre-trained model (Regnet y 32gf) yields a mean pre- cision, recall, and F1 scores of 0.787 ± 0.060, 0.755 ± 0.061, and 0.762 ± 0.050, re- spectively. This is a 53.5% improvement in precision and 7.3% improvement in recall over previous results with CNNs (ResNeXt-50) that were trained from scratch. The out-of-domain pre-training apparently yields general feature extractors/filters that ap- ply very well to the BM cell classification use case. The class activation maps on cell types with characteristic morphological features were found to be consistent with the explanations of a human domain expert. For example, the Auer rods in the cytoplasm were the predictive cellular feature for correctly classified images of faggot cells. Conclusions: Our study provides data that can help hematology laboratories to choose the optimal training strategy for blood cell classification deep learning mod- els to improve computer-assisted blood and bone marrow cell identification. It also highlights the need for more specific training data, i.e. images of difficult-to-classify classes, including cells labeled with disease information.	de_CH
dc.language.iso	en	de_CH
dc.publisher	Elsevier	de_CH
dc.relation.ispartof	Computer Methods and Programs in Biomedicine	de_CH
dc.rights	http://creativecommons.org/licenses/by/4.0/	de_CH
dc.subject	Hematopoiesis	de_CH
dc.subject	In-domain pre-training	de_CH
dc.subject	Deep learning	de_CH
dc.subject	Hematopathology	de_CH
dc.subject.ddc	006: Spezielle Computerverfahren	de_CH
dc.subject.ddc	610.28: Biomedizin, Biomedizinische Technik	de_CH
dc.title	Evaluation of deep learning training strategies for the classification of bone marrow cell images	de_CH
dc.type	Beitrag in wissenschaftlicher Zeitschrift	de_CH
dcterms.type	Text	de_CH
zhaw.departement	Life Sciences und Facility Management	de_CH
zhaw.organisationalunit	Institut für Computational Life Sciences (ICLS)	de_CH
dc.identifier.doi	10.1016/j.cmpb.2023.107924	de_CH
dc.identifier.doi	10.21256/zhaw-29212	-
zhaw.funding.eu	No	de_CH
zhaw.issue	243	de_CH
zhaw.originated.zhaw	Yes	de_CH
zhaw.pages.start	107924	de_CH
zhaw.publication.status	publishedVersion	de_CH
zhaw.publication.review	Peer review (Publikation)	de_CH
zhaw.webfeed	Predictive Analytics	de_CH
zhaw.author.additional	No	de_CH
zhaw.display.portrait	Yes	de_CH
Appears in collections:	Publikationen Life Sciences und Facility Management

Files in This Item:

File	Description	Size	Format
2023_Gluege-etal_Deep-learning-training-strategies-classification-bone-marrow-cell-images.pdf	Article	3.02 MB	Adobe PDF	View/Open
2023_Gluege-etal_Blood-cell-classification_Suppl.pdf	Supplementary material	4.41 MB	Adobe PDF	View/Open

Show simple item record

Glüge, S., Balabanov, S., Koelzer, V. H., & Ott, T. (2023). Evaluation of deep learning training strategies for the classification of bone marrow cell images. Computer Methods and Programs in Biomedicine, 243, 107924. https://doi.org/10.1016/j.cmpb.2023.107924

Glüge, S. et al. (2023) ‘Evaluation of deep learning training strategies for the classification of bone marrow cell images’, Computer Methods and Programs in Biomedicine, (243), p. 107924. Available at: https://doi.org/10.1016/j.cmpb.2023.107924.

S. Glüge, S. Balabanov, V. H. Koelzer, and T. Ott, “Evaluation of deep learning training strategies for the classification of bone marrow cell images,” Computer Methods and Programs in Biomedicine, no. 243, p. 107924, 2023, doi: 10.1016/j.cmpb.2023.107924.

GLÜGE, Stefan, Stefan BALABANOV, Viktor Hendrik KOELZER und Thomas OTT, 2023. Evaluation of deep learning training strategies for the classification of bone marrow cell images. Computer Methods and Programs in Biomedicine. 2023. Nr. 243, S. 107924. DOI 10.1016/j.cmpb.2023.107924

Glüge, Stefan, Stefan Balabanov, Viktor Hendrik Koelzer, and Thomas Ott. 2023. “Evaluation of Deep Learning Training Strategies for the Classification of Bone Marrow Cell Images.” Computer Methods and Programs in Biomedicine, no. 243: 107924. https://doi.org/10.1016/j.cmpb.2023.107924.

Glüge, Stefan, et al. “Evaluation of Deep Learning Training Strategies for the Classification of Bone Marrow Cell Images.” Computer Methods and Programs in Biomedicine, no. 243, 2023, p. 107924, https://doi.org/10.1016/j.cmpb.2023.107924.