MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI

UK Biobank (UKB) conducts large-scale examinations of more than half a million volunteers, collecting healthrelated information on genetics, lifestyle, blood biochemistry, and more. Medical imaging of 100,000 subjects, with 70,000 followup sessions, enables measurements of organs, muscle, and body composition. With up to 170,000 mounting MR images, various methodologies are accordingly engaged in large-scale image analysis. This work presents an experimental inference engine that can automatically predict a comprehensive profile of subject metadata from UKB neck-to-knee body MRI. It was evaluated in cross-validation for baseline characteristics such as age, height, weight, and sex, but also measurements of body composition, organ volumes, and abstract properties like grip strength, pulse rate, and type 2 diabetic status. It predicted subsequently released test data covering twelve body composition metrics with a 3% median error. The proposed system can automatically analyze one thousand subjects within ten minutes, providing individual confidence intervals. The underlying methodology utilizes convolutional neural networks for image-based mean-variance regression on two-dimensional representations of the MRI data. This work aims to make the proposed system available for free to researchers, who can use it to obtain fast and fully-automated estimates of 72 different measurements immediately upon release of new UKB image data.

[1]  Andreas Wallin,et al.  Kidney segmentation in neck-to-knee body MRI of 40,000 UK Biobank participants , 2020, Scientific Reports.

[2]  D. Rueckert,et al.  Deep Learning‐Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies , 2021, Investigative radiology.

[3]  Magnus Borga,et al.  Body Composition Profiling in the UK Biobank Imaging Study , 2018, Obesity.

[4]  Joel Kullberg,et al.  Large-scale biometry with interpretable neural network regression on UK Biobank body MRI , 2020, Scientific reports.

[5]  Michael Brady,et al.  Deep Quantitative Liver Segmentation and Vessel Exclusion to Assist in Liver Assessment , 2017, MIUA.

[6]  M. Cule,et al.  Genetic architecture of 11 organ traits derived from abdominal MRI using deep learning , 2021, eLife.

[7]  Magnus Borga,et al.  Feasibility of MR-Based Body Composition Analysis in Large Scale Population Studies , 2016, PloS one.

[8]  Cathie Sudlow,et al.  Algorithms for the Capture and Adjudication of Prevalent and Incident Diabetes in UK Biobank , 2016, PloS one.

[9]  Terry K Koo,et al.  A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. , 2016, Journal of chiropractic medicine.

[10]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[11]  Alejandro F. Frangi,et al.  The UK Biobank imaging enhancement of 100,000 participants: rationale, data collection, management and future directions , 2020, Nature Communications.

[12]  Robin Strand,et al.  Deep regression for uncertainty-aware and interpretable analysis of large-scale body MRI , 2021, ArXiv.

[13]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[14]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[15]  Robin Strand,et al.  Uncertainty-Aware Body Composition Analysis with Deep Regression Ensembles on UK Biobank MRI , 2021, Comput. Medical Imaging Graph..

[16]  Yi Liu,et al.  Automated Measurement of Pancreatic Fat and Iron Concentration Using Multi-Echo and T1-Weighted MRI Data , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[17]  H. Stefánsson,et al.  Brain age prediction using deep learning uncovers associated sequence variants , 2019, Nature Communications.

[18]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Michael Brady,et al.  Pancreas Segmentation-Derived Biomarkers: Volume and Shape Metrics in the UK Biobank Imaging Study , 2020, MIUA.

[20]  Stefan Neubauer,et al.  Characterisation of liver fat in the UK Biobank cohort , 2017, PloS one.