Imperial College London
Portrait Picture

ProfessorAndreaRockall

Faculty of Medicine, Department of Surgery & Cancer

Clinical Chair in Radiology
 
 
 
//

Contact

 

a.rockall

 
 
//

Location

 

ICTEM buildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Doran:2024:10.1186/s13244-023-01591-7,
author = {Doran, SJ and Barfoot, T and Wedlake, L and Winfield, JM and Petts, J and Glocker, B and Li, X and Leach, M and Kaiser, M and Barwick, TD and Chaidos, A and Satchwell, L and Soneji, N and Elgendy, K and Sheeka, A and Wallitt, K and Koh, D-M and Messiou, C and Rockall, A},
doi = {10.1186/s13244-023-01591-7},
journal = {Insights Imaging},
title = {Curation of myeloma observational study MALIMAR using XNAT: solving the challenges posed by real-world data.},
url = {http://dx.doi.org/10.1186/s13244-023-01591-7},
volume = {15},
year = {2024}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - OBJECTIVES: MAchine Learning In MyelomA Response (MALIMAR) is an observational clinical study combining "real-world" and clinical trial data, both retrospective and prospective. Images were acquired on three MRI scanners over a 10-year window at two institutions, leading to a need for extensive curation. METHODS: Curation involved image aggregation, pseudonymisation, allocation between project phases, data cleaning, upload to an XNAT repository visible from multiple sites, annotation, incorporation of machine learning research outputs and quality assurance using programmatic methods. RESULTS: A total of 796 whole-body MR imaging sessions from 462 subjects were curated. A major change in scan protocol part way through the retrospective window meant that approximately 30% of available imaging sessions had properties that differed significantly from the remainder of the data. Issues were found with a vendor-supplied clinical algorithm for "composing" whole-body images from multiple imaging stations. Historic weaknesses in a digital video disk (DVD) research archive (already addressed by the mid-2010s) were highlighted by incomplete datasets, some of which could not be completely recovered. The final dataset contained 736 imaging sessions for 432 subjects. Software was written to clean and harmonise data. Implications for the subsequent machine learning activity are considered. CONCLUSIONS: MALIMAR exemplifies the vital role that curation plays in machine learning studies that use real-world data. A research repository such as XNAT facilitates day-to-day management, ensures robustness and consistency and enhances the value of the final dataset. The types of process described here will be vital for future large-scale multi-institutional and multi-national imaging projects. CRITICAL RELEVANCE STATEMENT: This article showcases innovative data curation methods using a state-of-the-art image repository platform; such tools will be vital for managing the l
AU  - Doran,SJ
AU  - Barfoot,T
AU  - Wedlake,L
AU  - Winfield,JM
AU  - Petts,J
AU  - Glocker,B
AU  - Li,X
AU  - Leach,M
AU  - Kaiser,M
AU  - Barwick,TD
AU  - Chaidos,A
AU  - Satchwell,L
AU  - Soneji,N
AU  - Elgendy,K
AU  - Sheeka,A
AU  - Wallitt,K
AU  - Koh,D-M
AU  - Messiou,C
AU  - Rockall,A
DO  - 10.1186/s13244-023-01591-7
PY  - 2024///
SN  - 1869-4101
TI  - Curation of myeloma observational study MALIMAR using XNAT: solving the challenges posed by real-world data.
T2  - Insights Imaging
UR  - http://dx.doi.org/10.1186/s13244-023-01591-7
UR  - https://www.ncbi.nlm.nih.gov/pubmed/38361108
UR  - http://hdl.handle.net/10044/1/109352
VL  - 15
ER  -
Download