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


Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Jan 2024
Historique:
received: 11 05 2023
revised: 28 09 2023
accepted: 06 11 2023
medline: 4 12 2023
pubmed: 19 11 2023
entrez: 18 11 2023
Statut: ppublish

Résumé

The classification of bone marrow (BM) cells by light microscopy 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. We aim to improve the automatic classification performance of hematological cell types. Therefore, we evaluate four state-of-the-art Convolutional Neural Network (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 hematological 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 explanations for the models' predictions. The best performing pre-trained model (Regnet_y_32gf) yields a mean precision, recall, and F1 scores of 0.787±0.060, 0.755±0.061, and 0.762±0.050, respectively. 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 apply 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. Our study provides data that can help hematology laboratories to choose the optimal training strategy for blood cell classification deep learning models 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.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
The classification of bone marrow (BM) cells by light microscopy 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 METHODS
We aim to improve the automatic classification performance of hematological cell types. Therefore, we evaluate four state-of-the-art Convolutional Neural Network (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 hematological 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 explanations for the models' predictions.
RESULTS RESULTS
The best performing pre-trained model (Regnet_y_32gf) yields a mean precision, recall, and F1 scores of 0.787±0.060, 0.755±0.061, and 0.762±0.050, respectively. 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 apply 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 CONCLUSIONS
Our study provides data that can help hematology laboratories to choose the optimal training strategy for blood cell classification deep learning models 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.

Identifiants

pubmed: 37979517
pii: S0169-2607(23)00590-4
doi: 10.1016/j.cmpb.2023.107924
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

107924

Informations de copyright

Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Stefan Balabanov reports a relationship with Alexion that includes: board membership. Stefan Balabanov reports a relationship with Amgen Europe GmbH that includes: board membership. Stefan Balabanov reports a relationship with Blueprint Medicines (Switzerland) GmbH that includes: speaking and lecture fees. Stefan Balabanov reports a relationship with Incyte Biosciences Germany GmbH that includes: speaking and lecture fees. Stefan Balabanov reports a relationship with Novartis that includes: speaking and lecture fees. Stefan Balabanov reports a relationship with Takeda Oncology that includes: speaking and lecture fees. Viktor Hendrik Koelzer reports a relationship with Indica Labs that includes: invited speaker. Viktor Hendrik Koelzer reports a relationship with Image Analysis Group that includes: funding grants. Viktor Hendrik Koelzer reports a relationship with SPCC that includes: speaker fees. Viktor Hendrik Koelzer reports a relationship with Roche that includes: funding grants; advisory board. Viktor Hendrik Koelzer reports a relationship with Takeda that includes: advisory board.

Auteurs

Stefan Glüge (S)

Institute of Computational Life Sciences, Zurich University of Applied Sciences, Schloss 1, 8820 Wädenswil, Switzerland. Electronic address: stefan.gluege@zhaw.ch.

Stefan Balabanov (S)

Department of Medical Oncology and Haematology, University Hospital Zurich and University of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland.

Viktor Hendrik Koelzer (VH)

Department of Pathology and Molecular Pathology, University Hospital Zurich and University of Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland.

Thomas Ott (T)

Institute of Computational Life Sciences, Zurich University of Applied Sciences, Schloss 1, 8820 Wädenswil, Switzerland.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH