FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology
Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9399433/ |
_version_ | 1798024879285469184 |
---|---|
author | Andre Pedersen Marit Valla Anna M. Bofin Javier Perez De Frutos Ingerid Reinertsen Erik Smistad |
author_facet | Andre Pedersen Marit Valla Anna M. Bofin Javier Perez De Frutos Ingerid Reinertsen Erik Smistad |
author_sort | Andre Pedersen |
collection | DOAJ |
description | Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of CNN models. These applications use third-party solutions for inference, making them less user-friendly and unsuitable for high-performance image analysis. To make deployment of CNNs user-friendly and feasible on low-end machines, we have developed a new platform, <italic>FastPathology</italic>, using the FAST framework and C++. It minimizes memory usage for reading and processing WSIs, deployment of CNN models, and real-time interactive visualization of results. Runtime experiments were conducted on four different use cases, using different architectures, inference engines, hardware configurations and operating systems. Memory usage for reading, visualizing, zooming and panning a WSI were measured, using FastPathology and three existing platforms. FastPathology performed similarly in terms of memory to the other C++-based application, while using considerably less than the two Java-based platforms. The choice of neural network model, inference engine, hardware and processors influenced runtime considerably. Thus, FastPathology includes all steps needed for efficient visualization and processing of WSIs in a single application, including inference of CNNs with real-time display of the results. Source code, binary releases, video demonstrations and test data can be found online on GitHub at <uri>https://github.com/SINTEFMedtek/FAST-Pathology/</uri>. |
first_indexed | 2024-04-11T18:09:43Z |
format | Article |
id | doaj.art-6b55acd56f8b437bab8792e18289a594 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-11T18:09:43Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-6b55acd56f8b437bab8792e18289a5942022-12-22T04:10:11ZengIEEEIEEE Access2169-35362021-01-019582165822910.1109/ACCESS.2021.30722319399433FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital PathologyAndre Pedersen0https://orcid.org/0000-0002-3637-953XMarit Valla1https://orcid.org/0000-0001-7336-8779Anna M. Bofin2Javier Perez De Frutos3Ingerid Reinertsen4https://orcid.org/0000-0003-0999-3849Erik Smistad5https://orcid.org/0000-0002-7258-4709Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, NorwaySINTEF Medical Technology, Trondheim, NorwaySINTEF Medical Technology, Trondheim, NorwaySINTEF Medical Technology, Trondheim, NorwayDeep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of CNN models. These applications use third-party solutions for inference, making them less user-friendly and unsuitable for high-performance image analysis. To make deployment of CNNs user-friendly and feasible on low-end machines, we have developed a new platform, <italic>FastPathology</italic>, using the FAST framework and C++. It minimizes memory usage for reading and processing WSIs, deployment of CNN models, and real-time interactive visualization of results. Runtime experiments were conducted on four different use cases, using different architectures, inference engines, hardware configurations and operating systems. Memory usage for reading, visualizing, zooming and panning a WSI were measured, using FastPathology and three existing platforms. FastPathology performed similarly in terms of memory to the other C++-based application, while using considerably less than the two Java-based platforms. The choice of neural network model, inference engine, hardware and processors influenced runtime considerably. Thus, FastPathology includes all steps needed for efficient visualization and processing of WSIs in a single application, including inference of CNNs with real-time display of the results. Source code, binary releases, video demonstrations and test data can be found online on GitHub at <uri>https://github.com/SINTEFMedtek/FAST-Pathology/</uri>.https://ieeexplore.ieee.org/document/9399433/Deep learningneural networkshigh performancedigital pathologydecision support |
spellingShingle | Andre Pedersen Marit Valla Anna M. Bofin Javier Perez De Frutos Ingerid Reinertsen Erik Smistad FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology IEEE Access Deep learning neural networks high performance digital pathology decision support |
title | FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology |
title_full | FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology |
title_fullStr | FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology |
title_full_unstemmed | FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology |
title_short | FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology |
title_sort | fastpathology an open source platform for deep learning based research and decision support in digital pathology |
topic | Deep learning neural networks high performance digital pathology decision support |
url | https://ieeexplore.ieee.org/document/9399433/ |
work_keys_str_mv | AT andrepedersen fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology AT maritvalla fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology AT annambofin fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology AT javierperezdefrutos fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology AT ingeridreinertsen fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology AT eriksmistad fastpathologyanopensourceplatformfordeeplearningbasedresearchanddecisionsupportindigitalpathology |