PuSH - Publikationsserver des Helmholtz Zentrums München

Matek, C. ; Krappe, S.* ; Münzenmayer, C.* ; Haferlach, T.* ; Marr, C.

Highly accurate differentiation of bone marrow cell morphologies using deep neuralnetworks on a large image dataset

Blood 138, 1917-1927 (2021)
Verlagsversion Forschungsdaten DOI
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.

Biomedical applications of deep learning algorithms rely on large, expert annotated data sets. The classification of bone marrow cell cytomorphology, an important cornerstone of hematological diagnosis, is still done manually thousands of times every day, due to a lack of datasets and trained models.

We apply convolutional neural networks (CNNs) to a large dataset of 171,374 microscopic cytological images taken from bone marrow smears of 945 patients diagnosed with a variety of hematological diseases. The dataset is the largest expert-annotated pool of bone marrow cytology images available in the literature so far. It allows us to train high-quality classifiers of leukocyte cytomorphology that identify a wide range of diagnostically relevant cell species at high precision and recall.Our CNNs outcompete previous feature-based approaches and provide a proof-of-concept to the classification problem of single bone marrow cells.

This work is a step towards automated evaluation of bone marrow cell morphology using state-of-the-art image classification algorithms. The underlying dataset represents both an educational resource as well as a reference for future AI-based approaches to bone marrow cytomorphology.

Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Classification; Cancer
ISSN (print) / ISBN 0006-4971
e-ISSN 1528-0020
Zeitschrift Blood
Quellenangaben Band: 138, Heft: 20, Seiten: 1917-1927 Artikelnummer: , Supplement: ,
Verlag American Society of Hematology
Verlagsort 2021 L St Nw, Suite 900, Washington, Dc 20036 Usa
Begutachtungsstatus Peer reviewed
Förderungen European Research Council under the European Union's Horizon 2020 Research and Innovation Programme
German National Research foundation