{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T11:04:04Z","timestamp":1784027044579,"version":"3.55.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"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>To develop and evaluate an automated CT liver lesion-tracking algorithm that matches lesions over time, detects new metastases, and reports per\u2011lesion confidence to support response assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>The study included 87 adults with unresectable colorectal liver metastases (CRLM) who had baseline and 8-week follow-up contrast-enhanced CT. Three radiologists generated a consensus reference. We developed a machine learning-driven, automated model-based lesion tracking (Auto-MBT) that provides per-lesion matching confidence. Performance was compared with: (1) deformable registration + overlap; (2) deformable registration + Auto-MBT; and (3) affine registration + Auto-MBT. Analyses were stratified by lesion size (&lt;\u20091\u2009cm, 1\u20133\u2009cm, overall) and count (\u2264\u20095, 6\u201310, &gt; 10 per scan), and the triage utility of confidence scores was assessed by blinded adjudication. A publicly available melanoma dataset was used for external testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On the CRLM test set (35 pairs), affine + Auto-MBT matched 458\/464 lesions (precision\/recall 99%), detected 28\/30 new lesions (90%\/93%), and identified 42\/44 disappeared lesions (93%\/96%). Overall matching F1 was 0.989; affine + Auto-MBT outperformed deformable + overlap (0.797) and deformable + Auto-MBT (0.959). Confidence scores were higher for radiologist-accepted matches than rejected matches (0.72\n                      <jats:italic>versus<\/jats:italic>\n                      0.54) supporting triage utility. On the external set (23 pairs), overall matching F1 was 0.994, affine + Auto-MBT outperformed deformable + overlap (0.768) and deformable + Auto-MBT (0.971).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Auto-MBT accurately tracks CRLM and flags new lesions across sizes and counts, with per\u2011lesion confidence to triage, not replace, clinician review, enabling more comprehensive and accurate therapy response assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>The automated tracking framework accurately matched liver lesions, including new and subcentimeter lesions, improving longitudinal assessment.<\/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>Manual tracking of colorectal liver metastases (CRLM) on routine CT images is time-consuming and subject to inter-observer variability.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The algorithm demonstrates robust lesion\u2011level tracking performance (F1\u2009&gt;\u20090.9) in high lesion\u2011count CRLM, including matched, new, and disappeared lesions.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Automated total-tumor tracking complements Response Evaluation Criteria in Solid Tumors\u2012RECIST by quantifying all lesions, extending evaluation beyond limited target metastases.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00750-x","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:08:54Z","timestamp":1784023734000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated model-based lesion tracking in CT: colorectal liver metastases as a use case for development and performance analysis"],"prefix":"10.1186","volume":"10","author":[{"given":"Nalan","family":"Karunanayake","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard Kinh","family":"Do","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence H.","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7743-7022","authenticated-orcid":false,"given":"Lin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binsheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"750_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-018-0047-0","volume":"2","author":"W Chen","year":"2018","unstructured":"Chen W, Hoffmann AD, Liu H, Liu X (2018) Organotropism: new insights into molecular mechanisms of breast cancer metastasis. NPJ Precis Oncol 2:4. https:\/\/doi.org\/10.1038\/s41698-018-0047-0","journal-title":"NPJ Precis Oncol"},{"key":"750_CR2","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.trecan.2015.07.009","volume":"1","author":"AC Obenauf","year":"2015","unstructured":"Obenauf AC, Massagu\u00e9 J (2015) Surviving at a distance: organ-specific metastasis. Trends Cancer 1:76\u201391. https:\/\/doi.org\/10.1016\/j.trecan.2015.07.009","journal-title":"Trends Cancer"},{"key":"750_CR3","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209\u2013249. https:\/\/doi.org\/10.3322\/caac.21660","journal-title":"CA Cancer J Clin"},{"key":"750_CR4","doi-asserted-by":"publisher","unstructured":"Siegel RL, Giaquinto AN, Jemal A (2024) Cancer statistics, 2024. CA Cancer J Clin 74:12\u201349. https:\/\/doi.org\/10.3322\/caac.21820","DOI":"10.3322\/caac.21820"},{"key":"750_CR5","doi-asserted-by":"publisher","unstructured":"Li J, Pan J, Wang L et al (2025) Colorectal cancer: pathogenesis and targeted therapy. MedComm 6:e70127. https:\/\/doi.org\/10.1002\/mco2.70127","DOI":"10.1002\/mco2.70127"},{"key":"750_CR6","doi-asserted-by":"publisher","first-page":"S135","DOI":"10.1016\/j.ijsu.2016.06.014","volume":"33","author":"B Nardo","year":"2016","unstructured":"Nardo B, Serafini S, Ruggiero M et al (2016) Liver resection for metastases from colorectal cancer in very elderly patients: new surgical horizons. Int J Surg 33:S135\u2013S141. https:\/\/doi.org\/10.1016\/j.ijsu.2016.06.014","journal-title":"Int J Surg"},{"key":"750_CR7","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1111\/j.1477-2574.2012.00440.x","volume":"14","author":"WM Mohammad","year":"2012","unstructured":"Mohammad WM, Martel G, Mimeault R et al (2012) Evaluating agreement regarding the resectability of colorectal liver metastases: a national case-based survey of hepatic surgeons. HPB (Oxford) 14:291\u2013297. https:\/\/doi.org\/10.1111\/j.1477-2574.2012.00440.x","journal-title":"HPB (Oxford)"},{"key":"750_CR8","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s00384-023-04469-8","volume":"38","author":"N Leone","year":"2023","unstructured":"Leone N, Arolfo S, Spadi R et al (2023) Colorectal cancer with synchronous unresectable liver metastases: resecting the primary tumor improves survival. Int J Colorectal Dis 38:169. https:\/\/doi.org\/10.1007\/s00384-023-04469-8","journal-title":"Int J Colorectal Dis"},{"key":"750_CR9","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s41747-023-00383-4","volume":"7","author":"NJ Wesdorp","year":"2023","unstructured":"Wesdorp NJ, Zeeuw JM, Postma SCJ et al (2023) Deep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases. Eur Radiol Exp 7:75. https:\/\/doi.org\/10.1186\/s41747-023-00383-4","journal-title":"Eur Radiol Exp"},{"key":"750_CR10","doi-asserted-by":"publisher","first-page":"618","DOI":"10.2214\/AJR.12.10136","volume":"201","author":"LR Folio","year":"2013","unstructured":"Folio LR, Sandouk A, Huang J et al (2013) Consistency and efficiency of CT analysis of metastatic disease: semiautomated lesion management application within a PACS. AJR Am J Roentgenol 201:618\u2013625. https:\/\/doi.org\/10.2214\/AJR.12.10136","journal-title":"AJR Am J Roentgenol"},{"key":"750_CR11","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.ejca.2008.10.026","volume":"45","author":"EA Eisenhauer","year":"2009","unstructured":"Eisenhauer EA, Therasse P, Bogaerts J et al (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45:228\u2013247. https:\/\/doi.org\/10.1016\/j.ejca.2008.10.026","journal-title":"Eur J Cancer"},{"key":"750_CR12","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1097\/RLI.0000000000001045","volume":"59","author":"TMT Bucho","year":"2024","unstructured":"Bucho TMT, Tissier RLM, Bodalal Z et al (2024) How does target lesion selection affect RECIST? A computer simulation study. Invest Radiol 59:465\u2013471. https:\/\/doi.org\/10.1097\/RLI.0000000000001045","journal-title":"Invest Radiol"},{"key":"750_CR13","doi-asserted-by":"publisher","unstructured":"Fournier L, de Geus-Oei L-F, Regge D et al (2022) Twenty years on: RECIST as a biomarker of response in solid tumours an EORTC imaging group\u2014ESOI joint paper. Front Oncol 11:800547. https:\/\/doi.org\/10.3389\/fonc.2021.800547","DOI":"10.3389\/fonc.2021.800547"},{"key":"750_CR14","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1001\/jama.2009.1755","volume":"302","author":"YS Chun","year":"2009","unstructured":"Chun YS, Vauthey J, Boonsirikamchai P et al\u00a0(2009) Association of computed tomography morphologic criteria with pathologic response and survival in patients treated with bevacizumab for colorectal liver metastases. JAMA 302:2338\u20132344. https:\/\/doi.org\/10.1001\/jama.2009.1755","journal-title":"JAMA"},{"key":"750_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102675","volume":"83","author":"A Szeskin","year":"2023","unstructured":"Szeskin A, Rochman S, Weiss S et al (2023) Liver lesion changes analysis in longitudinal CECT scans by simultaneous deep learning voxel classification with SimU-Net. Med Image Anal 83:102675. https:\/\/doi.org\/10.1016\/j.media.2022.102675","journal-title":"Med Image Anal"},{"key":"750_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103268","volume":"97","author":"Beniamin Di Veroli","year":"2024","unstructured":"Di Veroli B, Lederman R, Shoshan Y et al (2024) A graph-theoretic approach for the analysis of lesion changes and lesions detection review in longitudinal oncological imaging. Med Image Anal 97:103268. https:\/\/doi.org\/10.1016\/j.media.2024.103268","journal-title":"Med Image Anal"},{"key":"750_CR17","doi-asserted-by":"publisher","unstructured":"Rochman S, Szeskin A, Lederman R et al (2024) Graph-based automatic detection and classification of lesion changes in pairs of CT studies for oncology follow-up. Int J Comput Assist Radiol Surg 19:241\u2013251. https:\/\/doi.org\/10.1007\/s11548-023-03000-2","DOI":"10.1007\/s11548-023-03000-2"},{"key":"750_CR18","doi-asserted-by":"publisher","first-page":"155017","DOI":"10.1088\/1361-6560\/ac1457","volume":"66","author":"V Santoro-Fernandes","year":"2021","unstructured":"Santoro-Fernandes V, Huff D, Scarpelli ML et al (2021) Development and validation of a longitudinal soft-tissue metastatic lesion matching algorithm. Phys Med Biol 66:155017. https:\/\/doi.org\/10.1088\/1361-6560\/ac1457","journal-title":"Phys Med Biol"},{"key":"750_CR19","unstructured":"Qahqaie M, Zimmer VA, Castaneda E et al (2025) Intelligent lesion selection: a novel method for longitudinal assessment of breast cancer lung metastases. In: Proceedings of medical imaging with deep learning (MIDL) 2025. Available via https:\/\/openreview.net\/forum?id=Xk69ksan04 Accessed date: 11 Feb 2025"},{"key":"750_CR20","doi-asserted-by":"crossref","unstructured":"Di Veroli B, Lederman R, Sosna J, Joskowicz L (2023) Graph-theoretic automatic lesion tracking and detection of patterns of lesion changes in longitudinal CT studies. In: Greenspan H, Madabhushi A, Mousavi P et al (eds) Proceedings of medical image computing and computer assisted intervention (MICCAI 2023). Springer Nature, Cham, pp 106\u2013115","DOI":"10.1007\/978-3-031-43904-9_11"},{"key":"750_CR21","doi-asserted-by":"publisher","unstructured":"K\u00fcstner T, Peisen F, Gatidis S et al (2025) Longitudinal-CT. University of T\u00fcbingen. Available via https:\/\/doi.org\/10.57754\/FDAT.qwsry-7t837 Accessed date: 05 May 2025","DOI":"10.57754\/FDAT.qwsry-7t837"},{"key":"750_CR22","doi-asserted-by":"publisher","unstructured":"Yang H, Schwartz LH, Zhao B (2016) A response assessment platform for development and validation of imaging biomarkers in oncology. Tomography 2:406\u2013410. https:\/\/doi.org\/10.18383\/j.tom.2016.00223","DOI":"10.18383\/j.tom.2016.00223"},{"key":"750_CR23","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","volume":"5","author":"J Wasserthal","year":"2023","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:e230024. https:\/\/doi.org\/10.1148\/ryai.230024","journal-title":"Radiol Artif Intell"},{"key":"750_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102830","volume":"87","author":"S Czolbe","year":"2023","unstructured":"Czolbe S, Pegios P, Krause O, Feragen A (2023) Semantic similarity metrics for image registration. Med Image Anal 87:102830. https:\/\/doi.org\/10.1016\/j.media.2023.102830","journal-title":"Med Image Anal"},{"key":"750_CR25","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T et al (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. Association for Computing Machinery, New York, pp 2623\u20132631","DOI":"10.1145\/3292500.3330701"},{"key":"750_CR26","unstructured":"Bergstra J, Bardenet R, Bengio Y, K\u00e9gl B (2011) Algorithms for hyper-parameter optimization. In: Proceedings of the 25th international conference on neural information processing systems. Curran Associates Inc., Red Hook, pp 2546\u20132554"},{"key":"750_CR27","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1002\/mp.17504","volume":"52","author":"J Ma","year":"2025","unstructured":"Ma J, Yang H, Chou Y et al (2025) Generalizability of lesion detection and segmentation when ScaleNAS is trained on a large multi-organ dataset and validated in the liver. Med Phys 52:1005\u20131018. https:\/\/doi.org\/10.1002\/mp.17504","journal-title":"Med Phys"},{"key":"750_CR28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/tomography11010003","volume":"11","author":"N Karunanayake","year":"2025","unstructured":"Karunanayake N, Lu L, Yang H et al (2025) Dual-stage AI model for enhanced CT imaging: precision segmentation of kidney and tumors. Tomography 11:3. https:\/\/doi.org\/10.3390\/tomography11010003","journal-title":"Tomography"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00750-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00750-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00750-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:08:58Z","timestamp":1784023738000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00750-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["750"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00750-x","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"12 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 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":"This study was approved by the Institutional Review Board of Memorial Sloan Kettering Cancer Center (IRB protocol number: 17-010; Date of Approval: June 22, 2022).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The requirement for informed consent was waived due to the retrospective nature of the study.","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":"107"}}