Cargando…
An efficient magnetic resonance image data quality screening dashboard
PURPOSE: Complex data processing and curation for artificial intelligence applications rely on high‐quality data sets for training and analysis. Manually reviewing images and their associated annotations is a very laborious task and existing quality control tools for data review are generally limite...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8992954/ https://www.ncbi.nlm.nih.gov/pubmed/35148034 http://dx.doi.org/10.1002/acm2.13557 |
_version_ | 1784683811671375872 |
---|---|
author | Gates, Evan D. H. Celaya, Adrian Suki, Dima Schellingerhout, Dawid Fuentes, David |
author_facet | Gates, Evan D. H. Celaya, Adrian Suki, Dima Schellingerhout, Dawid Fuentes, David |
author_sort | Gates, Evan D. H. |
collection | PubMed |
description | PURPOSE: Complex data processing and curation for artificial intelligence applications rely on high‐quality data sets for training and analysis. Manually reviewing images and their associated annotations is a very laborious task and existing quality control tools for data review are generally limited to raw images only. The purpose of this work was to develop an imaging informatics dashboard for the easy and fast review of processed magnetic resonance (MR) imaging data sets; we demonstrated its ability in a large‐scale data review. METHODS: We developed a custom R Shiny dashboard that displays key static snapshots of each imaging study and its annotations. A graphical interface allows the structured entry of review data and download of tabulated review results. We evaluated the dashboard using two large data sets: 1380 processed MR imaging studies from our institution and 285 studies from the 2018 MICCAI Brain Tumor Segmentation Challenge (BraTS). RESULTS: Studies were reviewed at an average rate of 100/h using the dashboard, 10 times faster than using existing data viewers. For data from our institution, 1181 of the 1380 (86%) studies were of acceptable quality. The most commonly identified failure modes were tumor segmentation (9.6% of cases) and image registration (4.6% of cases). Tumor segmentation without visible errors on the dashboard had much better agreement with reference tumor volume measurements (root‐mean‐square error 12.2 cm(3)) than did segmentations with minor errors (20.5 cm(3)) or failed segmentations (27.4 cm(3)). In the BraTS data, 242 of 285 (85%) studies were acceptable quality after processing. Among the 43 cases that failed review, 14 had unacceptable raw image quality. CONCLUSION: Our dashboard provides a fast, effective tool for reviewing complex processed MR imaging data sets. It is freely available for download at https://github.com/EGates1/MRDQED. |
format | Online Article Text |
id | pubmed-8992954 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-89929542022-04-13 An efficient magnetic resonance image data quality screening dashboard Gates, Evan D. H. Celaya, Adrian Suki, Dima Schellingerhout, Dawid Fuentes, David J Appl Clin Med Phys Technical Notes PURPOSE: Complex data processing and curation for artificial intelligence applications rely on high‐quality data sets for training and analysis. Manually reviewing images and their associated annotations is a very laborious task and existing quality control tools for data review are generally limited to raw images only. The purpose of this work was to develop an imaging informatics dashboard for the easy and fast review of processed magnetic resonance (MR) imaging data sets; we demonstrated its ability in a large‐scale data review. METHODS: We developed a custom R Shiny dashboard that displays key static snapshots of each imaging study and its annotations. A graphical interface allows the structured entry of review data and download of tabulated review results. We evaluated the dashboard using two large data sets: 1380 processed MR imaging studies from our institution and 285 studies from the 2018 MICCAI Brain Tumor Segmentation Challenge (BraTS). RESULTS: Studies were reviewed at an average rate of 100/h using the dashboard, 10 times faster than using existing data viewers. For data from our institution, 1181 of the 1380 (86%) studies were of acceptable quality. The most commonly identified failure modes were tumor segmentation (9.6% of cases) and image registration (4.6% of cases). Tumor segmentation without visible errors on the dashboard had much better agreement with reference tumor volume measurements (root‐mean‐square error 12.2 cm(3)) than did segmentations with minor errors (20.5 cm(3)) or failed segmentations (27.4 cm(3)). In the BraTS data, 242 of 285 (85%) studies were acceptable quality after processing. Among the 43 cases that failed review, 14 had unacceptable raw image quality. CONCLUSION: Our dashboard provides a fast, effective tool for reviewing complex processed MR imaging data sets. It is freely available for download at https://github.com/EGates1/MRDQED. John Wiley and Sons Inc. 2022-02-11 /pmc/articles/PMC8992954/ /pubmed/35148034 http://dx.doi.org/10.1002/acm2.13557 Text en © 2022 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, LLC on behalf of The American Association of Physicists in Medicine https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Technical Notes Gates, Evan D. H. Celaya, Adrian Suki, Dima Schellingerhout, Dawid Fuentes, David An efficient magnetic resonance image data quality screening dashboard |
title | An efficient magnetic resonance image data quality screening dashboard |
title_full | An efficient magnetic resonance image data quality screening dashboard |
title_fullStr | An efficient magnetic resonance image data quality screening dashboard |
title_full_unstemmed | An efficient magnetic resonance image data quality screening dashboard |
title_short | An efficient magnetic resonance image data quality screening dashboard |
title_sort | efficient magnetic resonance image data quality screening dashboard |
topic | Technical Notes |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8992954/ https://www.ncbi.nlm.nih.gov/pubmed/35148034 http://dx.doi.org/10.1002/acm2.13557 |
work_keys_str_mv | AT gatesevandh anefficientmagneticresonanceimagedataqualityscreeningdashboard AT celayaadrian anefficientmagneticresonanceimagedataqualityscreeningdashboard AT sukidima anefficientmagneticresonanceimagedataqualityscreeningdashboard AT schellingerhoutdawid anefficientmagneticresonanceimagedataqualityscreeningdashboard AT fuentesdavid anefficientmagneticresonanceimagedataqualityscreeningdashboard AT gatesevandh efficientmagneticresonanceimagedataqualityscreeningdashboard AT celayaadrian efficientmagneticresonanceimagedataqualityscreeningdashboard AT sukidima efficientmagneticresonanceimagedataqualityscreeningdashboard AT schellingerhoutdawid efficientmagneticresonanceimagedataqualityscreeningdashboard AT fuentesdavid efficientmagneticresonanceimagedataqualityscreeningdashboard |