Cargando…

Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis

BACKGROUND: Obtaining ground truth for pathological images is essential for various experiments, especially for training and testing image analysis algorithms. However, obtaining pathologist input is often difficult, time consuming and expensive. This leads to algorithms being over-fitted to small d...

Descripción completa

Detalles Bibliográficos
Autores principales: Wright, Alexander I., Magee, Derek R., Quirke, Philip, Treanor, Darren E.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Medknow Publications & Media Pvt Ltd 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4466790/
https://www.ncbi.nlm.nih.gov/pubmed/26110089
http://dx.doi.org/10.4103/2153-3539.157785
_version_ 1782376286519296000
author Wright, Alexander I.
Magee, Derek R.
Quirke, Philip
Treanor, Darren E.
author_facet Wright, Alexander I.
Magee, Derek R.
Quirke, Philip
Treanor, Darren E.
author_sort Wright, Alexander I.
collection PubMed
description BACKGROUND: Obtaining ground truth for pathological images is essential for various experiments, especially for training and testing image analysis algorithms. However, obtaining pathologist input is often difficult, time consuming and expensive. This leads to algorithms being over-fitted to small datasets, and inappropriate validation, which causes poor performance on real world data. There is a great need to gather data from pathologists in a simple and efficient manner, in order to maximise the amount of data obtained. METHODS: We present a lightweight, web-based HTML5 system for administering and participating in data collection experiments. The system is designed for rapid input with minimal effort, and can be accessed from anywhere in the world with a reliable internet connection. RESULTS: We present two case studies that use the system to assess how limitations on fields of view affect pathologist agreement, and to what extent poorly stained slides affect judgement. In both cases, the system collects pathologist scores at a rate of less than two seconds per image. CONCLUSIONS: The system has multiple potential applications in pathology and other domains.
format Online
Article
Text
id pubmed-4466790
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Medknow Publications & Media Pvt Ltd
record_format MEDLINE/PubMed
spelling pubmed-44667902015-06-24 Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis Wright, Alexander I. Magee, Derek R. Quirke, Philip Treanor, Darren E. J Pathol Inform Original Article BACKGROUND: Obtaining ground truth for pathological images is essential for various experiments, especially for training and testing image analysis algorithms. However, obtaining pathologist input is often difficult, time consuming and expensive. This leads to algorithms being over-fitted to small datasets, and inappropriate validation, which causes poor performance on real world data. There is a great need to gather data from pathologists in a simple and efficient manner, in order to maximise the amount of data obtained. METHODS: We present a lightweight, web-based HTML5 system for administering and participating in data collection experiments. The system is designed for rapid input with minimal effort, and can be accessed from anywhere in the world with a reliable internet connection. RESULTS: We present two case studies that use the system to assess how limitations on fields of view affect pathologist agreement, and to what extent poorly stained slides affect judgement. In both cases, the system collects pathologist scores at a rate of less than two seconds per image. CONCLUSIONS: The system has multiple potential applications in pathology and other domains. Medknow Publications & Media Pvt Ltd 2015-05-28 /pmc/articles/PMC4466790/ /pubmed/26110089 http://dx.doi.org/10.4103/2153-3539.157785 Text en Copyright: © 2015 Wright AI. http://creativecommons.org/licenses/by-nc-sa/3.0 This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Original Article
Wright, Alexander I.
Magee, Derek R.
Quirke, Philip
Treanor, Darren E.
Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title_full Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title_fullStr Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title_full_unstemmed Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title_short Prospector: A web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
title_sort prospector: a web-based tool for rapid acquisition of gold standard data for pathology research and image analysis
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4466790/
https://www.ncbi.nlm.nih.gov/pubmed/26110089
http://dx.doi.org/10.4103/2153-3539.157785
work_keys_str_mv AT wrightalexanderi prospectorawebbasedtoolforrapidacquisitionofgoldstandarddataforpathologyresearchandimageanalysis
AT mageederekr prospectorawebbasedtoolforrapidacquisitionofgoldstandarddataforpathologyresearchandimageanalysis
AT quirkephilip prospectorawebbasedtoolforrapidacquisitionofgoldstandarddataforpathologyresearchandimageanalysis
AT treanordarrene prospectorawebbasedtoolforrapidacquisitionofgoldstandarddataforpathologyresearchandimageanalysis