{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T06:27:00Z","timestamp":1792477620797,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["826494"],"award-info":[{"award-number":["826494"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The volume and diversity of large MR imaging datasets require efficient automated labelling tools for cataloguing MR series, as manual annotation is impractical and costly. However, relying on DICOM header fields alone is unreliable because sequence descriptors are heterogeneous and locally defined, frequently missing or incorrect, and may be altered or removed during anonymisation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We developed an AI-based modular model to classify MR series. The pipeline comprises five sequential classifiers (Family, Weighting, Fat Suppression, Contrast, and Others) and was trained and tested on 18,181 MRI series from the multicentre PRIMAGE repository. The dataset was split by patient into 80% training\/validation and 20% testing; within the training\/validation subset, five-fold cross-validation was used. With the exception of contrast classification, all modules used DICOM tag-based machine learning models (CatBoost\/Random Forest), while the Contrast classifier incorporated image analysis using a pretrained single-slice ResNet-50. Ethical approval for the study was obtained.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Accuracy was 0.994 for Weighting, 0.984 for Family, 0.959 for Fat suppression and 0.958 for Others; the Contrast classifier recorded 0.841. Overall, the end-to-end classification yielded a weighted F1 of 0.849 (CI: 0.837\u20130.861) and an accuracy of 0.853 (CI: 0.841\u20130.865).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed approach provides a reliable and scalable solution for labelling large, heterogeneous MRI datasets across multiple anatomical regions. The pipeline achieved excellent performance for Weighting and Family classification, solid performance for Fat Suppression and \u2018Others\u2019. However, Contrast classification remains the main limitation and warrants further refinement and\/or additional modules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Reliable, automated MRI sequence labelling enables faster, reproducible cohort selection and protocol harmonisation in large archives, supporting downstream clinical research and AI tools while reducing manual curation effort and error.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Multicentre PRIMAGE cohort (18,181 MR series) enabling evaluation in a heterogeneous setting.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Machine learning model combining DICOM metadata and image features.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>High accuracy in series classification: up to 0.994 on key tasks.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>A scalable pipeline reduces manual annotation workload for radiologists.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00740-z","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T13:07:33Z","timestamp":1779973653000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automated identification of MRI series using a hierarchical modular machine-learning pipeline"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4654-4321","authenticated-orcid":false,"given":"Mariusz J.","family":"Kujawa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9374-1411","authenticated-orcid":false,"given":"Mat\u00edas","family":"Fern\u00e1ndez\u2011Pat\u00f3n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5567-4278","authenticated-orcid":false,"given":"Leonor","family":"Cerd\u00e1 Alberich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6048-2940","authenticated-orcid":false,"given":"Diana","family":"Veiga-Canuto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8234-010X","authenticated-orcid":false,"given":"Luis","family":"Mart\u00ed\u2011Bonmat\u00ed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"740_CR1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2021.622951","volume":"15","author":"S Liang","year":"2021","unstructured":"Liang S, Beaton D, Arnott SR et al (2021) Magnetic resonance imaging sequence identification using a metadata learning approach. Front Neuroinform 15:622951. https:\/\/doi.org\/10.3389\/fninf.2021.622951","journal-title":"Front Neuroinform"},{"key":"740_CR2","doi-asserted-by":"publisher","unstructured":"de Mello JPV, Paix\u00e3o TM, Berriel R et al (2020) Deep learning-based type identification of volumetric MRI sequences. In: Proceedings of the 2020 25th international conference on pattern recognition (ICPR). IEEE, Milan, pp 5674\u20135681. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413120","DOI":"10.1109\/ICPR48806.2021.9413120"},{"key":"740_CR3","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s10278-019-00308-x","volume":"33","author":"R Gauriau","year":"2020","unstructured":"Gauriau R, Bridge C, Chen L et al (2020) Using DICOM metadata for radiological image series categorization: a feasibility study on large clinical brain MRI datasets. J Digit Imaging 33:747\u2013762. https:\/\/doi.org\/10.1007\/s10278-019-00308-x","journal-title":"J Digit Imaging"},{"key":"740_CR4","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1007\/S003300101100","volume":"12","author":"P Mildenberger","year":"2002","unstructured":"Mildenberger P, Eichelberg M, Martin E (2002) Introduction to the DICOM standard. Eur Radiol 12:920\u2013927. https:\/\/doi.org\/10.1007\/S003300101100","journal-title":"Eur Radiol"},{"key":"740_CR5","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1117\/12.467017","volume":"4685","author":"MO Gueld","year":"2002","unstructured":"Gueld MO, Kohnen M, Keysers D et al (2002) Quality of DICOM header information for image categorization. Proc SPIE 4685:280\u2013287. https:\/\/doi.org\/10.1117\/12.467017","journal-title":"Proc SPIE"},{"key":"740_CR6","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-025-01086-w","volume":"12","author":"A Gomis-Maya","year":"2025","unstructured":"Gomis-Maya A, Cerd\u00e1-Alberich L, Veiga-Canuto D et al (2025) Automatic magnetic resonance imaging series labelling for large repositories. J Big Data 12:39. https:\/\/doi.org\/10.1186\/s40537-025-01086-w","journal-title":"J Big Data"},{"key":"740_CR7","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s10278-019-00282-4","volume":"33","author":"S Ranjbar","year":"2020","unstructured":"Ranjbar S, Singleton KW, Jackson PR et al (2020) A deep convolutional neural network for annotation of magnetic resonance imaging sequence type. J Digit Imaging 33:439\u2013446. https:\/\/doi.org\/10.1007\/s10278-019-00282-4","journal-title":"J Digit Imaging"},{"key":"740_CR8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s12021-018-9387-8","volume":"17","author":"R Pizarro","year":"2019","unstructured":"Pizarro R, Assemlal HE, De Nigris D et al (2019) Using deep learning algorithms to automatically identify the brain MRI contrast: implications for managing large databases. Neuroinformatics 17:115\u2013130. https:\/\/doi.org\/10.1007\/s12021-018-9387-8","journal-title":"Neuroinformatics"},{"key":"740_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.110964","volume":"166","author":"GL Baumg\u00e4rtner","year":"2023","unstructured":"Baumg\u00e4rtner GL, Hamm CA, Schulze-Weddige S et al (2023) Metadata-independent classification of MRI sequences using convolutional neural networks: successful application to prostate MRI. Eur J Radiol 166:110964. https:\/\/doi.org\/10.1016\/j.ejrad.2023.110964","journal-title":"Eur J Radiol"},{"key":"740_CR10","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13244-025-01938-2","volume":"16","author":"JG de Almeida","year":"2025","unstructured":"de Almeida JG, Verde ASC, Bilreiro C et al (2025) Automatic sequence identification in multicentric prostate multiparametric MRI datasets for clinical machine-learning. Insights Imaging 16:75. https:\/\/doi.org\/10.1186\/s13244-025-01938-2","journal-title":"Insights Imaging"},{"key":"740_CR11","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TPAMI.2020.3033990","volume":"44","author":"Z Zhu","year":"2022","unstructured":"Zhu Z, Mittendorf A, Shropshire E et al (2022) 3D pyramid pooling network for abdominal MRI series classification. IEEE Trans Pattern Anal Mach Intell 44:1688\u20131698. https:\/\/doi.org\/10.1109\/TPAMI.2020.3033990","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"740_CR12","first-page":"405","volume":"2025","author":"J Pan","year":"2025","unstructured":"Pan J, Chen Q, Sun C et al (2025) MRISeqClassifier: a deep learning toolkit for precise MRI sequence classification. AMIA Jt Summits Transl Sci Proc 2025:405\u2013413","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"740_CR13","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13244-022-01355-9","volume":"14","author":"L Cerd\u00e1-Alberich","year":"2023","unstructured":"Cerd\u00e1-Alberich L, Solana J, Mallol P et al (2023) MAIC\u201310 brief quality checklist for publications using artificial intelligence and medical images. Insights Imaging 14:11. https:\/\/doi.org\/10.1186\/s13244-022-01355-9","journal-title":"Insights Imaging"},{"key":"740_CR14","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s41747-020-00150-9","volume":"4","author":"L Mart\u00ed-Bonmat\u00ed","year":"2020","unstructured":"Mart\u00ed-Bonmat\u00ed L, Alberich-Bayarri \u00c1, Ladenstein R et al (2020) PRIMAGE project: predictive in silico multiscale analytics to support childhood cancer personalised evaluation empowered by imaging biomarkers. Eur Radiol Exp 4:22. https:\/\/doi.org\/10.1186\/s41747-020-00150-9","journal-title":"Eur Radiol Exp"},{"key":"740_CR15","first-page":"6638","volume":"31","author":"L Prokhorenkova","year":"2018","unstructured":"Prokhorenkova L, Gusev G, Vorobev A et al (2018) CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst 31:6638\u20136648","journal-title":"Adv Neural Inf Process Syst"},{"key":"740_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"740_CR17","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Las Vegas, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"740_CR18","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1016\/j.acra.2024.11.046","volume":"32","author":"B Kim","year":"2025","unstructured":"Kim B, Mathai TS, Helm K et al (2025) Automated classification of body MRI sequences using convolutional neural networks. Acad Radiol 32:1192\u20131203. https:\/\/doi.org\/10.1016\/j.acra.2024.11.046","journal-title":"Acad Radiol"},{"key":"740_CR19","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1148\/rg.262055063","volume":"26","author":"R Bitar","year":"2006","unstructured":"Bitar R, Leung G, Perng R et al (2006) MR pulse sequences: what every radiologist wants to know but is afraid to ask. Radiographics 26:513\u2013537. https:\/\/doi.org\/10.1148\/rg.262055063","journal-title":"Radiographics"},{"key":"740_CR20","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1007\/S003300050780","volume":"9","author":"WR Nitz","year":"1999","unstructured":"Nitz WR (1999) MR imaging: acronyms and clinical applications. Eur Radiol 9:979\u2013997. https:\/\/doi.org\/10.1007\/S003300050780","journal-title":"Eur Radiol"},{"key":"740_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109256","volume":"183","author":"S Matta","year":"2024","unstructured":"Matta S, Lamard M, Zhang P et al (2024) A systematic review of generalization research in medical image classification. Comput Biol Med 183:109256. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.109256","journal-title":"Comput Biol Med"},{"key":"740_CR22","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.compbiomed.2016.06.018","volume":"76","author":"M T\u00f3th","year":"2016","unstructured":"T\u00f3th M, Rusk\u00f3 L, Cs\u00e9bfalvi B (2016) Automatic recognition of anatomical regions in three-dimensional medical images. Comput Biol Med 76:120\u2013133. https:\/\/doi.org\/10.1016\/j.compbiomed.2016.06.018","journal-title":"Comput Biol Med"},{"key":"740_CR23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s41747-021-00214-4","volume":"5","author":"C Scapicchio","year":"2021","unstructured":"Scapicchio C, Gabelloni M, Forte SM et al (2021) DICOM-MIABIS integration model for biobanks: a use case of the EU PRIMAGE project. Eur Radiol Exp 5:20. https:\/\/doi.org\/10.1186\/s41747-021-00214-4","journal-title":"Eur Radiol Exp"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00740-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00740-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00740-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T13:07:34Z","timestamp":1779973654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00740-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["740"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00740-z","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"1 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethical approval was obtained from the Ethics Committee for Investigation with medicinal products of the University and Polytechnic La Fe Hospital (ethic code: 2018\/0228). Written informed consent was obtained from all participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Written informed consent was obtained from all participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no conflicts of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"77"}}