Efficient, high-performance semantic segmentation using multi-scale feature extraction.

The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving an...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Moritz Knolle, Georgios Kaissis, Friederike Jungmann, Sebastian Ziegelmayer, Daniel Sasse, Marcus Makowski, Daniel Rueckert, Rickmer Braren
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/795046935447453c9293c2f093d03ef3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:795046935447453c9293c2f093d03ef3
record_format	dspace
spelling	oai:doaj.org-article:795046935447453c9293c2f093d03ef32021-12-02T20:17:46ZEfficient, high-performance semantic segmentation using multi-scale feature extraction.1932-620310.1371/journal.pone.0255397https://doaj.org/article/795046935447453c9293c2f093d03ef32021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255397https://doaj.org/toc/1932-6203The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model's segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet's inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.Moritz KnolleGeorgios KaissisFriederike JungmannSebastian ZiegelmayerDaniel SasseMarcus MakowskiDaniel RueckertRickmer BrarenPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0255397 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Moritz Knolle Georgios Kaissis Friederike Jungmann Sebastian Ziegelmayer Daniel Sasse Marcus Makowski Daniel Rueckert Rickmer Braren Efficient, high-performance semantic segmentation using multi-scale feature extraction.
description	The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model's segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet's inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.
format	article
author	Moritz Knolle Georgios Kaissis Friederike Jungmann Sebastian Ziegelmayer Daniel Sasse Marcus Makowski Daniel Rueckert Rickmer Braren
author_facet	Moritz Knolle Georgios Kaissis Friederike Jungmann Sebastian Ziegelmayer Daniel Sasse Marcus Makowski Daniel Rueckert Rickmer Braren
author_sort	Moritz Knolle
title	Efficient, high-performance semantic segmentation using multi-scale feature extraction.
title_short	Efficient, high-performance semantic segmentation using multi-scale feature extraction.
title_full	Efficient, high-performance semantic segmentation using multi-scale feature extraction.
title_fullStr	Efficient, high-performance semantic segmentation using multi-scale feature extraction.
title_full_unstemmed	Efficient, high-performance semantic segmentation using multi-scale feature extraction.
title_sort	efficient, high-performance semantic segmentation using multi-scale feature extraction.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/795046935447453c9293c2f093d03ef3
work_keys_str_mv	AT moritzknolle efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT georgioskaissis efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT friederikejungmann efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT sebastianziegelmayer efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT danielsasse efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT marcusmakowski efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT danielrueckert efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction AT rickmerbraren efficienthighperformancesemanticsegmentationusingmultiscalefeatureextraction
_version_	1718374351770746880

Efficient, high-performance semantic segmentation using multi-scale feature extraction.

Ejemplares similares