Clin Radiol. 2019 Feb 22. pii: S0009-9260(19)30074-1. doi: 10.1016/j.crad.2019.01.012. [Epub ahead of print]

Machine learning in whole-body MRI: experiences and challenges from an applied study using multicentre data.

Lavdas I1, Glocker B2, Rueckert D2, Taylor SA3, Aboagye EO4, Rockall AG5.

Author information

1

Imperial College Comprehensive Cancer Imaging Centre (C.C.I.C.), Hammersmith Campus, Commonwealth Building Main Office, Ground Floor, Du Cane Road, London W12 0NN, UK. Electronic address: ilavdas@imperial.ac.uk.

2

Biomedical Image Analysis Group, Department of Computing, Huxley Building, 180 Queen's Gate, Imperial College London, London SW7 2AZ, UK.

3

Department of Imaging, University College London Hospitals NHS Foundation Trust, Euston Road, London NW1 2BU, UK.

4

Imperial College Comprehensive Cancer Imaging Centre (C.C.I.C.), Hammersmith Campus, Commonwealth Building Main Office, Ground Floor, Du Cane Road, London W12 0NN, UK.

5

Imperial College Comprehensive Cancer Imaging Centre (C.C.I.C.), Hammersmith Campus, Commonwealth Building Main Office, Ground Floor, Du Cane Road, London W12 0NN, UK; Department of Radiology Hammersmith Hospital, Imperial College Healthcare NHS Trust, Du Cane Road, London W12 0NN, UK.

Abstract

Machine learning is now being increasingly employed in radiology to assist with tasks such as automatic lesion detection, segmentation, and characterisation. We are currently involved in an National Institute of Health Research (NIHR)-funded project, which aims to develop machine learning methods to improve the diagnostic performance and reduce the radiology reading time of whole-body magnetic resonance imaging (MRI) scans, in patients being staged for cancer (MALIBO study). We describe here the main challenges we have encountered during the course of this project. Data quality and uniformity are the two most important data traits to be considered in clinical trials incorporating machine learning. Robust data pre-processing and machine learning pipelines have been employed in MALIBO, a task facilitated by the now freely available machine learning libraries and toolboxes. Another important consideration for achieving the desired clinical outcome in MALIBO, was to effectively host the resulting machine learning output, along with the clinical images, for reading in a clinical environment. Finally, a range of legal, ethical, and clinical acceptance issues should be considered when attempting to incorporate computer-assisting tools into clinical practice. The road from translating computational methods into potentially useful clinical tools involves an analytical, stepwise adaptation approach, as well as engagement of a multidisciplinary team.