Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies
Abstract Large epidemiological studies such as the UK Biobank (UKBB) or German National Cohort (NAKO) provide unprecedented health-related data of the general population aiming to better understand determinants of health and disease. As part of these studies, Magnetic Resonance Imaging (MRI) is perf...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-23632-9 |
| _version_ | 1828094914089451520 |
|---|---|
| author | Turkay Kart Marc Fischer Stefan Winzeck Ben Glocker Wenjia Bai Robin Bülow Carina Emmel Lena Friedrich Hans-Ulrich Kauczor Thomas Keil Thomas Kröncke Philipp Mayer Thoralf Niendorf Annette Peters Tobias Pischon Benedikt M. Schaarschmidt Börge Schmidt Matthias B. Schulze Lale Umutle Henry Völzke Thomas Küstner Fabian Bamberg Bernhard Schölkopf Daniel Rueckert Sergios Gatidis |
| author_facet | Turkay Kart Marc Fischer Stefan Winzeck Ben Glocker Wenjia Bai Robin Bülow Carina Emmel Lena Friedrich Hans-Ulrich Kauczor Thomas Keil Thomas Kröncke Philipp Mayer Thoralf Niendorf Annette Peters Tobias Pischon Benedikt M. Schaarschmidt Börge Schmidt Matthias B. Schulze Lale Umutle Henry Völzke Thomas Küstner Fabian Bamberg Bernhard Schölkopf Daniel Rueckert Sergios Gatidis |
| author_sort | Turkay Kart |
| collection | DOAJ |
| description | Abstract Large epidemiological studies such as the UK Biobank (UKBB) or German National Cohort (NAKO) provide unprecedented health-related data of the general population aiming to better understand determinants of health and disease. As part of these studies, Magnetic Resonance Imaging (MRI) is performed in a subset of participants allowing for phenotypical and functional characterization of different organ systems. Due to the large amount of imaging data, automated image analysis is required, which can be performed using deep learning methods, e. g. for automated organ segmentation. In this paper we describe a computational pipeline for automated segmentation of abdominal organs on MRI data from 20,000 participants of UKBB and NAKO and provide results of the quality control process. We found that approx. 90% of data sets showed no relevant segmentation errors while relevant errors occurred in a varying proportion of data sets depending on the organ of interest. Image-derived features based on automated organ segmentations showed relevant deviations of varying degree in the presence of segmentation errors. These results show that large-scale, deep learning-based abdominal organ segmentation on MRI data is feasible with overall high accuracy, but visual quality control remains an important step ensuring the validity of down-stream analyses in large epidemiological imaging studies. |
| first_indexed | 2024-04-11T07:05:39Z |
| format | Article |
| id | doaj.art-6031c84e5aae40338dbc1cf216cc0791 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T07:05:39Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6031c84e5aae40338dbc1cf216cc07912022-12-22T04:38:25ZengNature PortfolioScientific Reports2045-23222022-11-0112111110.1038/s41598-022-23632-9Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort StudiesTurkay Kart0Marc Fischer1Stefan Winzeck2Ben Glocker3Wenjia Bai4Robin Bülow5Carina Emmel6Lena Friedrich7Hans-Ulrich Kauczor8Thomas Keil9Thomas Kröncke10Philipp Mayer11Thoralf Niendorf12Annette Peters13Tobias Pischon14Benedikt M. Schaarschmidt15Börge Schmidt16Matthias B. Schulze17Lale Umutle18Henry Völzke19Thomas Küstner20Fabian Bamberg21Bernhard Schölkopf22Daniel Rueckert23Sergios Gatidis24Biomedical Image Analysis Group, Department of Computing, Imperial College LondonInstitute of Signal Processing and System Theory, University of StuttgartBiomedical Image Analysis Group, Department of Computing, Imperial College LondonBiomedical Image Analysis Group, Department of Computing, Imperial College LondonBiomedical Image Analysis Group, Department of Computing, Imperial College LondonInstitute of Diagnostic Radiology and Neuroradiology, Greifswald University HospitalInstitute for Medical Informatics, Biometry and Epidemiology, University Hospital EssenDepartment of Diagnostic and Interventional Radiology, University Hospital AugsburgClinic for Diagnostic and Interventional Radiology, University Hospital HeidelbergInstitute of Social Medicine, Epidemiology and Health Economics, Charité – University Medicine BerlinDepartment of Diagnostic and Interventional Radiology, University Hospital AugsburgClinic for Diagnostic and Interventional Radiology, University Hospital HeidelbergBerlin Ultrahigh Field Facility (B.U.F.F.), Max-Delbrueck-Center for Molecular MedicineInstitute of Epidemiology, German Research Center for Environmental Health, Helmholtz Zentrum MünchenMax-Delbrueck-Center for Molecular Medicine, Molecular Epidemiology Research GroupInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute for Medical Informatics, Biometry and Epidemiology, University Hospital EssenDepartment of Molecular Epidemiology, German Institute of Human NutritionInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital EssenInstitute for Community Medicine, Greifswald University HospitalMedical Image and Data Analysis Lab, Department of Radiology, University of TübingenDepartment of Radiology, University of FreiburgEmpirical Inference Department, Max-Planck Institute for Intelligent SystemsBiomedical Image Analysis Group, Department of Computing, Imperial College LondonBiomedical Image Analysis Group, Department of Computing, Imperial College LondonAbstract Large epidemiological studies such as the UK Biobank (UKBB) or German National Cohort (NAKO) provide unprecedented health-related data of the general population aiming to better understand determinants of health and disease. As part of these studies, Magnetic Resonance Imaging (MRI) is performed in a subset of participants allowing for phenotypical and functional characterization of different organ systems. Due to the large amount of imaging data, automated image analysis is required, which can be performed using deep learning methods, e. g. for automated organ segmentation. In this paper we describe a computational pipeline for automated segmentation of abdominal organs on MRI data from 20,000 participants of UKBB and NAKO and provide results of the quality control process. We found that approx. 90% of data sets showed no relevant segmentation errors while relevant errors occurred in a varying proportion of data sets depending on the organ of interest. Image-derived features based on automated organ segmentations showed relevant deviations of varying degree in the presence of segmentation errors. These results show that large-scale, deep learning-based abdominal organ segmentation on MRI data is feasible with overall high accuracy, but visual quality control remains an important step ensuring the validity of down-stream analyses in large epidemiological imaging studies.https://doi.org/10.1038/s41598-022-23632-9 |
| spellingShingle | Turkay Kart Marc Fischer Stefan Winzeck Ben Glocker Wenjia Bai Robin Bülow Carina Emmel Lena Friedrich Hans-Ulrich Kauczor Thomas Keil Thomas Kröncke Philipp Mayer Thoralf Niendorf Annette Peters Tobias Pischon Benedikt M. Schaarschmidt Börge Schmidt Matthias B. Schulze Lale Umutle Henry Völzke Thomas Küstner Fabian Bamberg Bernhard Schölkopf Daniel Rueckert Sergios Gatidis Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies Scientific Reports |
| title | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| title_full | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| title_fullStr | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| title_full_unstemmed | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| title_short | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| title_sort | automated imaging based abdominal organ segmentation and quality control in 20 000 participants of the uk biobank and german national cohort studies |
| url | https://doi.org/10.1038/s41598-022-23632-9 |
| work_keys_str_mv | AT turkaykart automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT marcfischer automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT stefanwinzeck automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT benglocker automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT wenjiabai automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT robinbulow automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT carinaemmel automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT lenafriedrich automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT hansulrichkauczor automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT thomaskeil automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT thomaskroncke automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT philippmayer automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT thoralfniendorf automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT annettepeters automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT tobiaspischon automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT benediktmschaarschmidt automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT borgeschmidt automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT matthiasbschulze automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT laleumutle automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT henryvolzke automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT thomaskustner automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT fabianbamberg automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT bernhardscholkopf automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT danielrueckert automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies AT sergiosgatidis automatedimagingbasedabdominalorgansegmentationandqualitycontrolin20000participantsoftheukbiobankandgermannationalcohortstudies |