{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T21:36:54Z","timestamp":1791063414914,"version":"4.1.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["16\/68\/34"],"award-info":[{"award-number":["16\/68\/34"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014461","name":"NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust\/Institute of Cancer Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014461","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C7273\/A28677"],"award-info":[{"award-number":["C7273\/A28677"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Objectives<\/jats:title>\n                <jats:p>MAchine Learning In MyelomA Response (MALIMAR) is an observational clinical study combining \u201creal-world\u201d 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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>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 \u201ccomposing\u201d 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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Critical relevance statement<\/jats:title>\n                <jats:p>This article showcases innovative data curation methods using a state-of-the-art image repository platform; such tools will be vital for managing the large multi-institutional datasets required to train and validate generalisable ML algorithms and future foundation models in medical imaging.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Key points<\/jats:title>\n                <jats:p>\u2022 Heterogeneous data in the MALIMAR study required the development of novel curation strategies.<\/jats:p>\n                <jats:p>\u2022 Correction of multiple problems affecting the real-world data was successful, but implications for machine learning are still being evaluated.<\/jats:p>\n                <jats:p>\u2022 Modern image repositories have rich application programming interfaces enabling data enrichment and programmatic QA, making them much more than simple \u201cimage marts\u201d.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Graphical Abstract<\/jats:title>\n                \n              <\/jats:sec>","DOI":"10.1186\/s13244-023-01591-7","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T03:02:01Z","timestamp":1708052521000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Curation of myeloma observational study MALIMAR using XNAT: solving the challenges posed by real-world data"],"prefix":"10.1186","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8569-9188","authenticated-orcid":false,"given":"Simon J.","family":"Doran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theo","family":"Barfoot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda","family":"Wedlake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica M.","family":"Winfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Petts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Glocker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingfeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Leach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Kaiser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara D.","family":"Barwick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aristeidis","family":"Chaidos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Satchwell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Soneji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalil","family":"Elgendy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Sheeka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn","family":"Wallitt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dow-Mu","family":"Koh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Messiou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8270-5597","authenticated-orcid":false,"given":"Andrea","family":"Rockall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"1591_CR1","first-page":"e210048","volume":"3","author":"C Messiou","year":"2021","unstructured":"Messiou C, Porta N, Sharma B et al (2021) Prospective evaluation of whole-body MRI versus FDG PET\/CT for lesion detection in participants with myeloma. Radiology 3:e210048","journal-title":"Radiology"},{"key":"1591_CR2","volume-title":"NICE guideline: myeloma: diagnosis and management","author":"National Institute for Health and Care Excellence","year":"2016","unstructured":"National Institute for Health and Care Excellence (2016) NICE guideline: myeloma: diagnosis and management"},{"key":"1591_CR3","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1200\/JCO.2014.57.9961","volume":"33","author":"MA Dimopoulos","year":"2015","unstructured":"Dimopoulos MA, Hillengass J, Usmani S et al (2015) Role of magnetic resonance imaging in the management of patients with multiple myeloma: a consensus statement. J Clin Oncol 33:657\u2013664","journal-title":"J Clin Oncol"},{"key":"1591_CR4","doi-asserted-by":"publisher","first-page":"e538","DOI":"10.1016\/S1470-2045(14)70442-5","volume":"15","author":"SV Rajkumar","year":"2014","unstructured":"Rajkumar SV, Dimopoulos MA, Palumbo A et al (2014) International Myeloma Working Group updated criteria for the diagnosis of multiple myeloma. Lancet Oncol 15:e538\u2013e548","journal-title":"Lancet Oncol"},{"key":"1591_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1148\/radiol.2019181949","volume":"291","author":"C Messiou","year":"2019","unstructured":"Messiou C, Hillengass J, Delorme S et al (2019) Guidelines for acquisition, interpretation, and reporting of whole-body MRI in myeloma: myeloma response assessment and diagnosis system (MY-RADS). Radiology 291:5\u201313","journal-title":"Radiology"},{"key":"1591_CR6","doi-asserted-by":"publisher","first-page":"e067140","DOI":"10.1136\/bmjopen-2022-067140","volume":"12","author":"L Satchwell","year":"2022","unstructured":"Satchwell L, Wedlake L, Greenlay E et al (2022) Development of machine learning support for reading whole body diffusion-weighted MRI (WB-MRI) in myeloma for the detection and quantification of the extent of disease before and after treatment (MALIMAR): protocol for a cross-sectional diagnostic test accuracy study. BMJ Open 12:e067140","journal-title":"BMJ Open"},{"key":"1591_CR7","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518","volume-title":"\u201cEveryone wants to do the model work, not the data work\u201d: data cascades in high-stakes AI","author":"N Sambasivan","year":"2021","unstructured":"Sambasivan N, Kapania S, Highfill H, Akrong D, Paritosh P, Aroyo LM (2021) \u201cEveryone wants to do the model work, not the data work\u201d: data cascades in high-stakes AI. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. https:\/\/doi.org\/10.1145\/3411764.3445518"},{"key":"1591_CR8","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1097\/RLI.0000000000000891","volume":"57","author":"M Wennmann","year":"2022","unstructured":"Wennmann M, Klein A, Bauer F et al (2022) Combining deep learning and radiomics for automated, objective, comprehensive bone marrow characterization from whole-body MRI: a multicentric feasibility study. Invest Radiol 57:752\u2013763","journal-title":"Invest Radiol"},{"key":"1591_CR9","unstructured":"Gu R, Antonelli M, Mehta P et al Automatic segmentation of whole-body MRI using UnnU-Net: feasibility of whole-skeleton ADC evaluation in plasma cell disorders. In: Proc. Int. Soc. Magn. Reson. Med., 31st Annual Meeting, London, 2022, abstract #2162"},{"key":"1591_CR10","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/s00330-021-08150-y","volume":"32","author":"J Liu","year":"2022","unstructured":"Liu J, Guo W, Zeng P et al (2022) Vertebral MRI-based radiomics model to differentiate multiple myeloma from metastases: influence of features number on logistic regression model performance. Eur Radiol 32:572\u2013581","journal-title":"Eur Radiol"},{"key":"1591_CR11","doi-asserted-by":"publisher","unstructured":"Liu J, Wang C, Guo W et al (2021) A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med 126:1226\u20131235. https:\/\/doi.org\/10.1007\/s11547-021-01388-y","DOI":"10.1007\/s11547-021-01388-y"},{"key":"1591_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-42579-y","volume":"9","author":"E-J Hwang","year":"2019","unstructured":"Hwang E-J, Jung J-Y, Lee SK, Lee S-E, Jee W-H (2019) Machine learning for diagnosis of hematologic diseases in magnetic resonance imaging of lumbar spines. Sci Rep 9:1\u20139","journal-title":"Sci Rep"},{"key":"1591_CR13","first-page":"128","volume":"11","author":"X Xiong","year":"2021","unstructured":"Xiong X, Wang J, Hu S, Dai Y, Zhang Y, Hu C (2021) Differentiating between multiple myeloma and metastasis subtypes of lumbar vertebra lesions using machine learning\u2013based radiomics. Front Oncol 11:128","journal-title":"Front Oncol"},{"key":"1591_CR14","doi-asserted-by":"crossref","unstructured":"Jerebko AK, Schmidt G, Zhou X et al (2007) Robust parametric modeling approach based on domain knowledge for computer aided detection of vertebrae column metastases in MRI. Inf Process Med Imaging 20:713\u2013724","DOI":"10.1007\/978-3-540-73273-0_59"},{"key":"1591_CR15","doi-asserted-by":"publisher","unstructured":"He J and Zhang K (2021) Medical image analysis of multiple myeloma based on convolutional neural network. Exp Syst 2022;39:e12810. https:\/\/doi.org\/10.1111\/exsy.12810","DOI":"10.1111\/exsy.12810"},{"key":"1591_CR16","doi-asserted-by":"publisher","unstructured":"Zhou C, Chan H-P, Hadjiiski LM, Dong Q (2021) Deep learning based risk stratification for treatment management of multiple myeloma with sequential MRI scans. In: Medical Imaging Proceedings, vol 11597. p 1159716. https:\/\/doi.org\/10.1117\/12.2582203","DOI":"10.1117\/12.2582203"},{"key":"1591_CR17","doi-asserted-by":"publisher","unstructured":"Qaiser T, Winzeck S, Barfoot T et al (2021) Multiple instance learning with auxiliary task weighting for multiple myeloma classification. arXiv:2107.07805. https:\/\/doi.org\/10.48550\/arXiv.2107.07805","DOI":"10.48550\/arXiv.2107.07805"},{"key":"1591_CR18","doi-asserted-by":"publisher","first-page":"105105","DOI":"10.1016\/j.compbiomed.2021.105105","volume":"140","author":"E-J Hwang","year":"2022","unstructured":"Hwang E-J, Kim S, Jung J-Y (2022) Fully automated segmentation of lumbar bone marrow in sagittal, high-resolution T1-weighted magnetic resonance images using 2D U-NET. Comput Biol Med 140:105105","journal-title":"Comput Biol Med"},{"key":"1591_CR19","doi-asserted-by":"crossref","unstructured":"Pauly O, Glocker B, Criminisi A et al (2011) Fast multiple organ detection and localization in whole-body MR Dixon sequences. Med Image Comput Comput Assist Interv 14:239\u2013247","DOI":"10.1007\/978-3-642-23626-6_30"},{"key":"1591_CR20","first-page":"1097","volume":"10","author":"AG Rockall","year":"2023","unstructured":"Rockall AG, Li X, Johnson N et al (2023) Development and evaluation of machine learning in whole-body magnetic resonance imaging for detecting metastases in patients with lung or colon cancer: a diagnostic test accuracy study. Invest Radiol 10:1097","journal-title":"Invest Radiol"},{"key":"1591_CR21","doi-asserted-by":"crossref","unstructured":"Wolz R, Chu C, Misawa K, Mori K K, Rueckert D (2012) Multi-organ abdominal CT segmentation using hierarchically weighted subject-specific atlases. Med Image Comput Comput Assist Interv 15:10\u201317","DOI":"10.1007\/978-3-642-33415-3_2"},{"key":"1591_CR22","doi-asserted-by":"publisher","unstructured":"Xu L, Tetteh G, Lipkova J et al (2018) Automated whole-body bone lesion detection for multiple myeloma on 68Ga-pentixafor PET\/CT imaging using deep learning methods. Contrast Media Mol Imaging 2018:2391925. https:\/\/doi.org\/10.1155\/2018\/2391925","DOI":"10.1155\/2018\/2391925"},{"key":"1591_CR23","doi-asserted-by":"publisher","unstructured":"Kirillov A, Mintun E, Ravi N et al (2023) Segment anything. arXiv:2304.02643. https:\/\/doi.org\/10.48550\/arXiv.2304.02643","DOI":"10.48550\/arXiv.2304.02643"},{"key":"1591_CR24","doi-asserted-by":"crossref","unstructured":"Wasserthal J, Breit H-C, Meyer MT et al (2023) TotalSegmentator: robust segmentation of 104 anatomic structures in CT Images. Radiol Artif Intell 5(5):e230024","DOI":"10.1148\/ryai.230024"},{"key":"1591_CR25","unstructured":"Basty N, Thanaj M, Cule M et al (2021) Swap-free fat-water separation in Dixon MRI using conditional generative adversarial networks. arXiv preprint arXiv:2107.14175"},{"key":"1591_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40644-021-00406-6","volume":"21","author":"SJ Doran","year":"2021","unstructured":"Doran SJ, Kumar S, Orton M et al (2021) \u201cReal-world\u201d radiomics from multi-vendor MRI: an original retrospective study on the prediction of nodal status and disease survival in breast cancer, as an exemplar to promote discussion of the wider issues. Cancer Imaging 21:1\u201318","journal-title":"Cancer Imaging"},{"key":"1591_CR27","unstructured":"Messiou C, Booth T, Robinson D et al (2017) Guidance on the use of patient images obtained as part of standard care for teaching, training and research. Available via https:\/\/www.sor.org\/getmedia\/48ce6a7b-88b8-4c02-a402-ab5afcca89fe\/bfcr177_use_of_pateint_images.pdf"},{"key":"1591_CR28","doi-asserted-by":"publisher","first-page":"giaa095","DOI":"10.1093\/gigascience\/giaa095","volume":"9","author":"T Nind","year":"2020","unstructured":"Nind T, Sutherland J, McAllister G et al (2020) An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population. Gigascience 9:giaa095","journal-title":"Gigascience"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-023-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-023-01591-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-023-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T13:02:23Z","timestamp":1711371743000},"score":1,"resource":{"primary":{"URL":"https:\/\/insightsimaging.springeropen.com\/articles\/10.1186\/s13244-023-01591-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1591"],"URL":"https:\/\/doi.org\/10.1186\/s13244-023-01591-7","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,16]]},"assertion":[{"value":"25 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study protocol was reviewed by the Royal Marsden NHS Foundation Trust and Institute of Cancer Research Combined Committee for Clinical Research (CCR) and underwent proportionate review by the South Central \u2014 Oxford C. Research Ethics Committee in November 2017 (IRAS Project ID: 233501) and the Health Research Authority. The study was also approved for CPMS portfolio adoption (CPMS ID: 36766). The research was carried out in accordance with the Declaration of Helsinki (1996). Healthy volunteers included in the study consented to the study. Scans included from the prospective iTIMM study were consented for study entry and future use of data. Consent was waived for the use of de-identified retrospective data. The Royal Marsden NHS Foundation Trust and The Imperial College Healthcare NHS Trust acted as data controllers for the study, with the Institute of Cancer Research and Imperial College acting as data processors. The legal basis for processing data was \u201ctask carried out in the public interest\u201d (GDPR Article 6.1(e)) with processing of special category (health) data permitted under GDPR Article 9.2(j) and appropriate safeguards implemented to satisfy the requirements of GDPR Article 89(1).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"As described above, the study\u2019s ethics committee waived consent for the use of de-identified retrospective data. Furthermore, the current position of the UK\u2019s Royal College of Radiologists on the use of patient images for teaching training and research [27] is this (our italics): \u201cYou may disclose anonymised or coded recordings for use in research, teaching or training, or other healthcare-related purposes without consent. In deciding whether a recording is anonymised, you should bear in mind that apparently insignificant details may still be capable of identifying the patient. You should be particularly careful about the anonymity of such recordings before using or publishing them without consent in journals and other learning materials, whether they are printed or in an electronic format. <i>Explicit consent is only required if the patient is, or may be, identifiable<\/i>\u201d.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"47"}}