Hematologist-Level Classification of Mature B-Cell Neoplasm Using Deep Learning on Multiparameter Flow Cytometry Data.
deep learning
non-Hodgkin lymphoma
self-organizing maps
Journal
Cytometry. Part A : the journal of the International Society for Analytical Cytology
ISSN: 1552-4930
Titre abrégé: Cytometry A
Pays: United States
ID NLM: 101235694
Informations de publication
Date de publication:
10 2020
10 2020
Historique:
received:
06
04
2020
revised:
18
05
2020
accepted:
19
05
2020
pubmed:
11
6
2020
medline:
30
7
2021
entrez:
11
6
2020
Statut:
ppublish
Résumé
The wealth of information captured by multiparameter flow cytometry (MFC) can be analyzed by recent methods of computer vision when represented as a single image file. We therefore transformed MFC raw data into a multicolor 2D image by a self-organizing map and classified this representation using a convolutional neural network. By this means, we built an artificial intelligence that is not only able to distinguish diseased from healthy samples, but it can also differentiate seven subtypes of mature B-cell neoplasm. We trained our model with 18,274 cases including chronic lymphocytic leukemia and its precursor monoclonal B-cell lymphocytosis, marginal zone lymphoma, mantle cell lymphoma, prolymphocytic leukemia, follicular lymphoma, hairy cell leukemia, lymphoplasmacytic lymphoma and achieved a weighted F1 score of 0.94 on a separate test set of 2,348 cases. Furthermore, we estimated the trustworthiness of a classification and could classify 70% of all cases with a confidence of 0.95 and higher. Our performance analyses indicate that particularly for rare subtypes further improvement can be expected when even more samples are available for training. © 2020 The Authors. Cytometry Part A published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry.
Identifiants
pubmed: 32519455
doi: 10.1002/cyto.a.24159
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1073-1080Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2020 The Authors. Cytometry Part A published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry.
Références
Weber LM, Robinson MD. Comparison of clustering methods for high-dimensional single-cell flow and mass cytometry data. Cytometry Part A 2016;89A:1084-1096.
Aghaeepour N, Finak G, Consortium TF, Consortium TD, Hoos H, Mosmann TR, Brinkman R, Gottardo R, Scheuermann RH. Critical assessment of automated flow cytometry data analysis techniques. Nat Methods 2013;10:228-238.
Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique. IEEE Trans Med Imaging 2016;35:1153-1159.
Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017;19:221-248.
Van Gassen S, Callebaut B, Van Helden MJ, Lambrecht BN, Demeester P, Dhaene T, Saeys Y. FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data. Cytometry Part A 2015;87A:636-645.
Kohonen T. The self-organizing map. Proc IEEE 1990;78:1464-1480.
Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D, Basel-Salmon L, Krawitz PM, Kamphausen SB, Zenker M, et al. Identifying facial phenotypes of genetic disorders using deep learning. Nat Med 2019;25:60-64.
Goodfellow I, Bengio Y, Courville A. Deep Learning. Vol 801, Cambridge, MA: MIT Press, 2016.
Rawat W, Wang Z. Deep convolutional neural networks for image classification: A comprehensive review. Neural Comput 2017;29:2352-2449.
Dean PN, Bagwell CB, Lindmo T, Murphy RF, Salzman GC. Data file standard for flow cytometry. Cytometry 1990;11:323-332.
Gorman C. A Multi-Gpu Implementation of the Self-Organizing Map in TensorFlow: Cgorman/Tensorflow-Som. 2019. Available at: https://github.com/cgorman/tensorflow-som. Accessed May 5, 2019.
Fort J-C, Cottrell M, Letremy P. Stochastic on-line algorithm versus batch algorithm for quantization and self organizing maps. In: Proceedings of the 2001 IEEE Signal Processing Society Workshop, 2001; pp. 43-52.
Kiviluoto K. Topology preservation in self-organizing maps. In: Proceedings of International Conference on Neural Networks (ICNN'96); Vol 1, 1996; pp. 294-299.
Mount NJ, Weaver D. Self-organizing maps and boundary effects: Quantifying the benefits of torus wrapping for mapping SOM trajectories. Pattern Anal Applic 2011;14:139-148.
Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980 [cs] 2014. Available at: http://arxiv.org/abs/1412.6980. Accessed October 19, 2019.
Chollet F. Keras. 2015. Available at: https://keras.io.
Zeiler MD, Fergus R. Visualizing Understanding Convolutional Networks. arXiv:1311.2901 [cs] 2013. Available at: http://arxiv.org/abs/1311.2901. Accessed October 22, 2019.
Simonyan K, Vedaldi A, Zisserman A. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv:1312.6034 [cs] 2013. Available at: http://arxiv.org/abs/1312.6034. Accessed June 12, 2019.
Kotikalapudi R. Neural Network Visualization Toolkit for Keras. 2019. Available at: https://github.com/raghakot/keras-vis. Accessed May 5, 2019.
Bassarova A, Trøen G, Spetalen S, Micci F, Tierens A, Delabie J. Lymphoplasmacytic lymphoma and marginal zone lymphoma in the bone marrow: Paratrabecular involvement as an important distinguishing feature. Am J Clin Pathol 2015;143:797-806.
van der Velden VHJ, Hoogeveen PG, de Ridder D, Schindler-van der Struijk M, van Zelm MC, Sanders M, Karsch D, Beverloo HB, Lam K, Orfao A, et al. van Lom K. B-cell prolymphocytic leukemia: A specific subgroup of mantle cell lymphoma. Blood 2014;124:412-419.
Topol EJ. High-performance medicine: The convergence of human and artificial intelligence. Nat Med 2019;25:44-56.
Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, Cui C, Corrado G, Thrun S, Dean J. A guide to deep learning in healthcare. Nat Med 2019;25:24-29.