{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:38:11Z","timestamp":1791999491935,"version":"4.4.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T00:00:00Z","timestamp":1691971200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T00:00:00Z","timestamp":1691971200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"crossref","award":["A29911"],"award-info":[{"award-number":["A29911"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"crossref","award":["FC10988"],"award-info":[{"award-number":["FC10988"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100009187","name":"Medical Research Foundation","doi-asserted-by":"publisher","award":["FC10988"],"award-info":[{"award-number":["FC10988"]}],"id":[{"id":"10.13039\/501100009187","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["FC10988"],"award-info":[{"award-number":["FC10988"]}],"id":[{"id":"10.13039\/100010269","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","award":["A109"],"award-info":[{"award-number":["A109"]}],"id":[{"id":"10.13039\/100014461","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016916","name":"Royal Marsden Cancer Charity","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016916","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000833","name":"Rosetrees Trust","doi-asserted-by":"publisher","award":["A2204"],"award-info":[{"award-number":["A2204"]}],"id":[{"id":"10.13039\/501100000833","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ventana Medical Systems","award":["10467"],"award-info":[{"award-number":["10467"]}]},{"name":"Ventana Medical Systems","award":["10530"],"award-info":[{"award-number":["10530"]}]},{"name":"National Institute of Health","award":["U01 CA247439"],"award-info":[{"award-number":["U01 CA247439"]}]},{"DOI":"10.13039\/100005190","name":"Melanoma Research Alliance","doi-asserted-by":"publisher","award":["686061"],"award-info":[{"award-number":["686061"]}],"id":[{"id":"10.13039\/100005190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cancer Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The aim of this work is to evaluate the performance of radiomics predictions for a range of molecular, genomic and clinical targets in patients with clear cell renal cell carcinoma (ccRCC) and demonstrate the impact of novel feature selection strategies and sub-segmentations on model interpretability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Contrast-enhanced CT scans from the first 101 patients recruited to the TRACERx Renal Cancer study (NCT03226886) were used to derive radiomics classification models to predict 20 molecular, histopathology and clinical target variables. Manual 3D segmentation was used in conjunction with automatic sub-segmentation to generate radiomics features from the core, rim, high and low enhancing sub-regions, and the whole tumour. Comparisons were made between two classification model pipelines: a Conventional pipeline reflecting common radiomics practice, and a Proposed pipeline including two novel feature selection steps designed to improve model interpretability. For both pipelines nested cross-validation was used to estimate prediction performance and tune model hyper-parameters, and permutation testing was used to evaluate the statistical significance of the estimated performance measures. Further model robustness assessments were conducted by evaluating model variability across the cross-validation folds.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Classification performance was significant (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05, H<jats:sub>0<\/jats:sub>:AUROC\u2009=\u20090.5) for 11 of 20 targets using either pipeline and for these targets the AUROCs were within\u2009\u00b1\u20090.05 for the two pipelines, except for one target where the Proposed pipeline performance increased by\u2009&gt;\u20090.1. Five of these targets (necrosis on histology, presence of renal vein invasion, overall histological stage, linear evolutionary subtype and loss of 9p21.3 somatic alteration marker) had AUROC\u2009&gt;\u20090.8. Models derived using the Proposed pipeline contained fewer feature groups than the Conventional pipeline, leading to more straightforward model interpretations without loss of performance. Sub-segmentations lead to improved performance and\/or improved interpretability when predicting the presence of sarcomatoid differentiation and tumour stage.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Use of the Proposed pipeline, which includes the novel feature selection methods, leads to more interpretable models without compromising prediction performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Trial registration<\/jats:title><jats:p>NCT03226886 (TRACERx Renal)<\/jats:p><\/jats:sec>","DOI":"10.1186\/s40644-023-00594-3","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T07:02:20Z","timestamp":1691996540000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Interpretability of radiomics models is improved when using feature group selection strategies for predicting molecular and clinical targets in clear-cell renal cell carcinoma: insights from the TRACERx Renal study"],"prefix":"10.1186","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-763X","authenticated-orcid":false,"given":"Matthew R.","family":"Orton","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evan","family":"Hann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon J.","family":"Doran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott T. C.","family":"Shepherd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derfel","family":"Ap Dafydd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlotte E.","family":"Spencer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 I.","family":"L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00edctor","family":"Albarr\u00e1n-Artahona","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca","family":"Comito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Warren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Shur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Messiou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Larkin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samra","family":"Turajlic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"on behalf of the TRACERx Renal Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dow-Mu","family":"Koh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,14]]},"reference":[{"issue":"10","key":"594_CR1","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1038\/nrurol.2017.112","volume":"14","author":"S Turajlic","year":"2017","unstructured":"Turajlic S, Swanton C, T.R. Consortium. TRACERx Renal: tracking renal cancer evolution through therapy. Nat Rev Urol. 2017;14(10):575\u20136.","journal-title":"Nat Rev Urol"},{"issue":"3","key":"594_CR2","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1016\/j.cell.2018.03.057","volume":"173","author":"S Turajlic","year":"2018","unstructured":"Turajlic S, et al. Tracking cancer evolution reveals constrained routes to metastases: TRACERx renal. Cell. 2018;173(3):581-594.e12.","journal-title":"Cell"},{"issue":"3","key":"594_CR3","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1016\/j.cell.2018.03.043","volume":"173","author":"S Turajlic","year":"2018","unstructured":"Turajlic S, et al. Deterministic evolutionary trajectories influence primary tumor growth: TRACERx renal. Cell. 2018;173(3):595-610.e11.","journal-title":"Cell"},{"issue":"12","key":"594_CR4","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","volume":"14","author":"P Lambin","year":"2017","unstructured":"Lambin P, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14(12):749\u201362.","journal-title":"Nat Rev Clin Oncol"},{"issue":"1","key":"594_CR5","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/s13244-020-00887-2","volume":"11","author":"JE van Timmeren","year":"2020","unstructured":"van Timmeren JE, et al. Radiomics in medical imaging-\u201chow-to\u201d guide and critical reflection. Insights Imaging. 2020;11(1):91.","journal-title":"Insights Imaging"},{"issue":"1","key":"594_CR6","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s40644-020-00311-4","volume":"20","author":"N Papanikolaou","year":"2020","unstructured":"Papanikolaou N, Matos C, Koh DM. How to develop a meaningful radiomic signature for clinical use in oncologic patients. Cancer Imaging. 2020;20(1):33.","journal-title":"Cancer Imaging"},{"issue":"3","key":"594_CR7","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1148\/radiol.2021202553","volume":"298","author":"MR Tomaszewski","year":"2021","unstructured":"Tomaszewski MR, Gillies RJ. The biological meaning of radiomic features. Radiology. 2021;298(3):505\u201316.","journal-title":"Radiology"},{"issue":"1","key":"594_CR8","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/s13014-021-01810-9","volume":"16","author":"Y Sugai","year":"2021","unstructured":"Sugai Y, et al. Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients. Radiat Oncol. 2021;16(1):80.","journal-title":"Radiat Oncol"},{"key":"594_CR9","doi-asserted-by":"publisher","first-page":"100801","DOI":"10.1016\/j.imu.2021.100801","volume":"27","author":"R Laajili","year":"2021","unstructured":"Laajili R, Said M, Tagina M. Application of radiomics features selection and classification algorithms for medical imaging decision: MRI radiomics breast cancer cases study. Inform Med Unlocked. 2021;27:100801.","journal-title":"Inform Med Unlocked"},{"issue":"7","key":"594_CR10","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1097\/RLI.0000000000000855","volume":"57","author":"A Demircio\u011flu","year":"2022","unstructured":"Demircio\u011flu A. Benchmarking feature selection methods in radiomics. Invest Radiol. 2022;57(7):433\u201343.","journal-title":"Invest Radiol"},{"issue":"6","key":"594_CR11","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1148\/rg.2021210037","volume":"41","author":"JD Shur","year":"2021","unstructured":"Shur JD, et al. Radiomics in oncology: a practical guide. Radiographics. 2021;41(6):1717\u201332.","journal-title":"Radiographics"},{"issue":"1","key":"594_CR12","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1385\/NI:5:1:11","volume":"5","author":"DS Marcus","year":"2007","unstructured":"Marcus DS, et al. The Extensible Neuroimaging Archive Toolkit: an informatics platform for managing, exploring, and sharing neuroimaging data. Neuroinformatics. 2007;5(1):11\u201334.","journal-title":"Neuroinformatics"},{"issue":"2","key":"594_CR13","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1148\/radiol.2020191145","volume":"295","author":"A Zwanenburg","year":"2020","unstructured":"Zwanenburg A, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology. 2020;295(2):328\u201338.","journal-title":"Radiology"},{"issue":"21","key":"594_CR14","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","volume":"77","author":"JJM van Griethuysen","year":"2017","unstructured":"van Griethuysen JJM, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77(21):e104\u20137.","journal-title":"Cancer Res"},{"issue":"1","key":"594_CR15","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani R. Regression shrinkage and selection via the Lasso. J R Stat Soc Ser B Methodol. 1996;58(1):267\u201388.","journal-title":"J R Stat Soc Ser B Methodol"},{"issue":"1","key":"594_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332.","journal-title":"Mach Learn"},{"key":"594_CR17","first-page":"177","volume":"20","author":"A Fisher","year":"2019","unstructured":"Fisher A, Rudin C, Dominici F. All models are wrong, but many are useful: learning a variable\u2019s importance by studying an entire class of prediction models simultaneously. J Mach Learn Res. 2019;20:177.","journal-title":"J Mach Learn Res"},{"key":"594_CR18","unstructured":"Ojala M, Garriga GC. Permutation tests for studying classifier performance. J Mach Learn Res. 2010;11(6):1833\u201363."},{"issue":"1","key":"594_CR19","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s41559-021-01586-x","volume":"6","author":"X Fu","year":"2022","unstructured":"Fu X, et al. Spatial patterns of tumour growth impact clonal diversification in a computational model and the TRACERx Renal study. Nat Ecol Evol. 2022;6(1):88\u2013102.","journal-title":"Nat Ecol Evol"},{"issue":"21","key":"594_CR20","doi-asserted-by":"publisher","first-page":"215008","DOI":"10.1088\/1361-6560\/aae5cd","volume":"63","author":"X Chen","year":"2018","unstructured":"Chen X, et al. Reliable gene mutation prediction in clear cell renal cell carcinoma through multi-classifier multi-objective radiogenomics model. Phys Med Biol. 2018;63(21):215008.","journal-title":"Phys Med Biol"},{"key":"594_CR21","doi-asserted-by":"publisher","first-page":"279","DOI":"10.3389\/fonc.2020.00279","volume":"10","author":"Z Feng","year":"2020","unstructured":"Feng Z, et al. Identifying BAP1 mutations in clear-cell renal cell carcinoma by CT radiomics: preliminary findings. Front Oncol. 2020;10:279.","journal-title":"Front Oncol"},{"issue":"3","key":"594_CR22","doi-asserted-by":"publisher","first-page":"W55","DOI":"10.2214\/AJR.18.20443","volume":"212","author":"B Kocak","year":"2019","unstructured":"Kocak B, et al. Radiogenomics in clear cell renal cell carcinoma: machine learning-based high-dimensional quantitative CT texture analysis in predicting PBRM1 mutation status. AJR Am J Roentgenol. 2019;212(3):W55\u201363.","journal-title":"AJR Am J Roentgenol"},{"issue":"7","key":"594_CR23","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1038\/s41559-021-01456-6","volume":"5","author":"Y Zhao","year":"2021","unstructured":"Zhao Y, et al. Selection of metastasis competent subclones in the tumour interior. Nat Ecol Evol. 2021;5(7):1033\u201345.","journal-title":"Nat Ecol Evol"},{"issue":"1","key":"594_CR24","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1186\/s12859-018-2344-6","volume":"19","author":"S Klau","year":"2018","unstructured":"Klau S, et al. Priority-Lasso: a simple hierarchical approach to the prediction of clinical outcome using multi-omics data. BMC Bioinformatics. 2018;19(1):322.","journal-title":"BMC Bioinformatics"},{"key":"594_CR25","doi-asserted-by":"crossref","unstructured":"Carrasquinha E, et al. Regularization techniques in radiomics: a case study on the prediction of pCR in breast tumours and the axilla. In: Computational intelligence methods for bioinformatics and biostatistics. Cham: Springer International Publishing; 2020.","DOI":"10.1007\/978-3-030-63061-4_24"},{"issue":"1","key":"594_CR26","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1111\/j.1467-9868.2005.00532.x","volume":"68","author":"M Yuan","year":"2006","unstructured":"Yuan M, Lin Y. Model selection and estimation in regression with grouped variables. J R Stat Soc Ser B Stat Methodol. 2006;68(1):49\u201367.","journal-title":"J R Stat Soc Ser B Stat Methodol"}],"container-title":["Cancer Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40644-023-00594-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40644-023-00594-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40644-023-00594-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T03:35:02Z","timestamp":1729913702000},"score":1,"resource":{"primary":{"URL":"https:\/\/cancerimagingjournal.biomedcentral.com\/articles\/10.1186\/s40644-023-00594-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,14]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["594"],"URL":"https:\/\/doi.org\/10.1186\/s40644-023-00594-3","relation":{},"ISSN":["1470-7330"],"issn-type":[{"value":"1470-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,14]]},"assertion":[{"value":"10 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Subjects in this study are the first 101 patients enrolled to TRACERx Renal, approved as a prospective cohort study by the National Health Service Research Ethics Committee (11\/LO\/1996). The study sponsor is the Royal Marsden NHS Foundation Trust.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.M.R.O. is a former Editorial Board member for Cancer Imaging.J.L. has received research funding from Bristol-Myers Squibb, Merck, Novartis, Pfizer, Achilles Therapeutics, Roche, Nektar Therapeutics, Covance, Immunocore, Pharmacyclics, and Aveo, and served as a consultant to Achilles, AstraZeneca, Boston Biomedical, Bristol-Myers Squibb, Eisai, EUSA Pharma, GlaxoSmithKline, Ipsen, Imugene, Incyte, iOnctura, Kymab, Merck Serono, Nektar, Novartis, Pierre Fabre, Pfizer, Roche Genentech, Secarna, and Vitaccess.S.T. has received speaking fees from Roche, Astra Zeneca, Novartis, and Ipsen. ST has the following patents filed: Indel mutations as a therapeutic target and predictive biomarker PCTGB2018\/051892 PCTGB2018\/051893 and Clear Cell Renal Cell Carcinoma Biomarkers P113326GB.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"76"}}