![[feed]](/style/images/feed-icon-14x14.png){kind=icon}
|
PDF (Original Article)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB |
| Item Type: | Article |
|---|---|
| Title: | Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies |
| Creators Name: | Kart, T. and Fischer, M. and Winzeck, S. and Glocker, B. and Bai, W. and Bülow, R. and Emmel, C. and Friedrich, L. and Kauczor, H.U. and Keil, T. and Kröncke, T. and Mayer, P. and Niendorf, T. and Peters, A. and Pischon, T. and Schaarschmidt, B.M. and Schmidt, B. and Schulze, M.B. and Umutle, L. and Völzke, H. and Küstner, T. and Bamberg, F. and Schölkopf, B. and Rueckert, D. and Gatidis, S. |
| 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. |
| Keywords: | Epidemiology, Magnetic Resonance Imaging, Whole Body Imaging |
| Source: | Scientific Reports |
| ISSN: | 2045-2322 |
| Publisher: | Nature Publishing Group |
| Volume: | 12 |
| Number: | 1 |
| Page Range: | 18733 |
| Date: | 4 November 2022 |
| Official Publication: | https://doi.org/10.1038/s41598-022-23632-9 |
| PubMed: | View item in PubMed |
Repository Staff Only: item control page
Download Statistics
Download Statistics
