{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:09:31Z","timestamp":1780056571349,"version":"3.54.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"DFG","award":["SFB 1382"],"award-info":[{"award-number":["SFB 1382"]}]}],"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>Automated, artificial intelligence (AI)-based, organ segmentation has the potential to streamline preclinical imaging workflows, but its suitability must be evaluated not only by geometric accuracy, but also by impact on downstream quantitative analyses. We validated a commercially available AI-based organ segmentation workflow for whole-body micro-computed tomography (micro-CT) data regarding segmentation accuracy, reproducibility, processing time, and effects on fluorescence tomography (FLT) quantification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Heart, lungs, liver, and kidneys were segmented in micro-CT scans from 27 mice by three independent experts and by a commercially available automated deep learning tool applied to standard and iteratively reconstructed CT datasets. Segmentation performance was evaluated using the S\u00f8rensen-Dice similarity coefficient (DSC) and organ volumes, while downstream effects were assessed using FLT overlay quantification across five fluorescent probes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>AI-based segmentations showed organ-dependent agreement with experts, with lower DSC scores for heart and lungs reflecting systematic boundary differences. Repeated AI segmentations yielded identical results, demonstrating reproducibility while reducing segmentation time from approximately 30\u2009min per mouse to about 5\u2009min, with AI inference completed within seconds. While segmentation geometry and organ volumes differed from expert annotations in an organ-dependent manner, these differences showed no linear relationship with downstream FLT quantification. Iterative CT reconstruction improved the agreement of fluorescence measurements with expert-derived values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Geometric segmentation metrics alone are insufficient to predict downstream fluorescence quantification, underscoring the need for task-based evaluation strategies in preclinical multimodal imaging. AI-based segmentation offers a reproducible and time-efficient alternative to manual annotation, enabling practical, scalable, and generalizable image analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Reproducible, AI-based organ segmentation can substantially improve the efficiency and scalability of quantitative preclinical imaging workflows, supporting more robust translation of multimodal imaging biomarkers toward clinical research and future patient-focused applications.<\/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>In hybrid micro-CT\/FLT imaging, geometric segmentation metrics did not reliably predict downstream fluorescence quantification outcomes.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>AI segmentation assessment should shift from benchmark accuracy metrics toward task-based validation reflecting real downstream imaging applications across different workflows.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>A commercially available AI-based organ segmentation tool demonstrates fully reproducible segmentation and substantially reduced analysis time compared with expert annotations.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>AI applied to iteratively reconstructed CT data improves the agreement of fluorescence quantification with expert annotations compared with standard reconstruction.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00742-x","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:43:54Z","timestamp":1780055034000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Validation of an automated AI-based micro-CT organ segmentation workflow against expert annotations and its impact on fluorescence quantification"],"prefix":"10.1186","volume":"10","author":[{"given":"Elena","family":"Rama","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sihe","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Schraven","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zachary","family":"Gurberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ekaterina","family":"Savina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuzanna Anna","family":"Magnuska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Gremse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7341-0399","authenticated-orcid":false,"given":"Fabian","family":"Kiessling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"742_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41746-020-00376-2","volume":"4","author":"A Esteva","year":"2021","unstructured":"Esteva A, Chou K, Yeung S et al (2021) Deep learning-enabled medical computer vision. NPJ Digit Med 4:5","journal-title":"NPJ Digit Med"},{"key":"742_CR2","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.3390\/ijms23095023","volume":"23","author":"G Crisan","year":"2022","unstructured":"Crisan G, Moldovean-Cioroianu NS, Timaru D, Andries G, Cainap C, Chis V (2022) Radiopharmaceuticals for PET and SPECT imaging: a literature review over the last decade. Int J Mol Sci 23:5023","journal-title":"Int J Mol Sci"},{"key":"742_CR3","doi-asserted-by":"publisher","first-page":"4159","DOI":"10.3390\/ijms22084159","volume":"22","author":"V Duclos","year":"2021","unstructured":"Duclos V, Iep A, Gomez L, Goldfarb L, Besson FL (2021) PET molecular imaging: a holistic review of current practice and emerging perspectives for diagnosis, therapeutic evaluation and prognosis in clinical oncology. Int J Mol Sci 22:4159","journal-title":"Int J Mol Sci"},{"key":"742_CR4","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1097\/RLI.0000000000001052","volume":"59","author":"S Schraven","year":"2023","unstructured":"Schraven S, Br\u00fcck R, Rosenhain S et al (2023) CT- and MRI-aided fluorescence tomography reconstructions for biodistribution analysis. Invest Radiol 59:504\u2013512","journal-title":"Invest Radiol"},{"key":"742_CR5","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1002\/lsm.23414","volume":"53","author":"L Tian","year":"2021","unstructured":"Tian L, Hunt B, Bell MAL et al (2021) Deep learning in biomedical optics. Lasers Surg Med 53:748\u2013775","journal-title":"Lasers Surg Med"},{"key":"742_CR6","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention (MICCAI). Lecture notes in computer Science. Springer, Heidelberg, pp 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"742_CR7","doi-asserted-by":"publisher","unstructured":"Oktay O, Schlemper J, Le Folgoc L et al (2018) Attention U-Net: learning where to look for the pancreas. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1804.03999","DOI":"10.48550\/arXiv.1804.03999"},{"key":"742_CR8","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","volume":"15","author":"Z Zhang","year":"2018","unstructured":"Zhang Z, Liu Q, Wang Y (2018) Road extraction by deep residual U-Net. Z. IEEE Geosci Remote Sens Lett 15:749\u2013753","journal-title":"Z. IEEE Geosci Remote Sens Lett"},{"key":"742_CR9","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","volume":"37","author":"X Li","year":"2018","unstructured":"Li X, Chen H, Qi X, Dou Q, Fu CW, Heng PA (2018) H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imaging 37:2663\u20132674","journal-title":"IEEE Trans Med Imaging"},{"key":"742_CR10","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2020","unstructured":"Zhou Z, Siddiquee MR, Tajbakhsh N, Liang J (2020) UNet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 39:1856\u20131867","journal-title":"IEEE Trans Med Imaging"},{"key":"742_CR11","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.878966","volume":"9","author":"M Thamm","year":"2022","unstructured":"Thamm M, Rosenhain S, Leonardic K et al (2022) Intrinsic respiratory gating for simultaneous multi-mouse \u03bcCT imaging to assess liver tumors. Front Med 9:878966","journal-title":"Front Med"},{"key":"742_CR12","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1016\/j.jconrel.2020.09.046","volume":"328","author":"I Biancacci","year":"2021","unstructured":"Biancacci I, Sun Q, M\u00f6ckel D et al (2021) Optical imaging of the whole-body to cellular biodistribution of clinical-stage PEG-b-pHPMA-based core-crosslinked polymeric micelles. J Control Release 328:805\u2013816","journal-title":"J Control Release"},{"key":"742_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nano.2023.102650","volume":"48","author":"S Schraven","year":"2023","unstructured":"Schraven S, Rosenhain S, Brueck R et al (2023) Dye labeling for optical imaging biases drug carriers\u2019 biodistribution and tumor uptake. Nanomed Nanotechnol Biol Med 48:102650","journal-title":"Nanomed Nanotechnol Biol Med"},{"key":"742_CR14","doi-asserted-by":"publisher","first-page":"960","DOI":"10.7150\/thno.9293","volume":"4","author":"F Gremse","year":"2014","unstructured":"Gremse F, Theek B, Kunjachan S et al (2014) Absorption reconstruction improves biodistribution assessment of fluorescent nanoprobes using hybrid fluorescence-mediated tomography. Theranostics 4:960","journal-title":"Theranostics"},{"key":"742_CR15","doi-asserted-by":"publisher","first-page":"328","DOI":"10.7150\/thno.13624","volume":"6","author":"F Gremse","year":"2016","unstructured":"Gremse F, St\u00e4rk M, Ehling J, Menzel JR, Lammers T, Kiessling F (2016) Imalytics preclinical: interactive analysis of biomedical volume data. Theranostics 6:328","journal-title":"Theranostics"},{"key":"742_CR16","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1109\/TMI.2017.2665165","volume":"36","author":"VV Valindria","year":"2017","unstructured":"Valindria VV, Lavdas I, Bai W et al (2017) Reverse classification accuracy: predicting segmentation performance in the absence of ground truth. IEEE Trans Med Imaging 36:1597\u20131606","journal-title":"IEEE Trans Med Imaging"},{"key":"742_CR17","doi-asserted-by":"publisher","unstructured":"Lemay A, Gros C, Naga Karthik E, Cohen-Adad J, Mach J (2023) Label fusion and training methods for reliable representation of inter-rater uncertainty. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2202.07550","DOI":"10.48550\/arXiv.2202.07550"},{"key":"742_CR18","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20220972","volume":"96","author":"L Quinn","year":"2023","unstructured":"Quinn L, Tryposkiadis K, Deeks J et al (2023) Interobserver variability studies in diagnostic imaging: a methodological systematic review. Br J Radiol 96:20220972","journal-title":"Br J Radiol"},{"key":"742_CR19","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/s11307-022-01775-5","volume":"25","author":"J Van Sluis","year":"2022","unstructured":"Van Sluis J, Noordzij W, De Vries EGE et al (2022) Manual versus artificial intelligence\u2011based segmentations as a pre\u2011processing step in whole\u2011body PET dosimetry calculations. Mol Imaging Biol 25:435\u2013441","journal-title":"Mol Imaging Biol"},{"key":"742_CR20","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/s10278-015-9839-8","volume":"29","author":"A Ramkumar","year":"2016","unstructured":"Ramkumar A, Dolz J, Kirisli HA et al (2016) User interaction in semi-automatic segmentation of organs at risk: a case study in radiotherapy. J Digit Imaging 29:264\u2013277","journal-title":"J Digit Imaging"},{"key":"742_CR21","first-page":"124670R","volume":"12467","author":"Z Liu","year":"2024","unstructured":"Liu Z, Mhlanga JC, Siegel BA, Jha AK (2024) Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET. Proc SPIE Int Soc Opt Eng 12467:124670R","journal-title":"Proc SPIE Int Soc Opt Eng"},{"key":"742_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-022-06096-y","volume":"15","author":"D M\u00fcller","year":"2022","unstructured":"M\u00fcller D, Rey IS, Kramer F (2022) Towards a guideline for evaluation metrics in medical image segmentation. BMC Res Notes 15:210","journal-title":"BMC Res Notes"},{"key":"742_CR23","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14254","volume":"25","author":"M Karimipourfard","year":"2023","unstructured":"Karimipourfard M, Sina S, Mahani H, Alavi M, Yazdi M (2023) Impact of deep learning-based multiorgan segmentation methods on patient-specific internal dosimetry in PET\/CT imaging: a comparative study. J Appl Clin Med Phys 25:e14254","journal-title":"J Appl Clin Med Phys"},{"key":"742_CR24","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1016\/j.acra.2013.11.008","volume":"21","author":"JR Spears","year":"2014","unstructured":"Spears JR, Schoepf UJ, Henzler T et al (2014) Comparison of the effect of iterative reconstruction versus filtered back projection on cardiac CT postprocessing. Acad Radiol 21:318\u2013324","journal-title":"Acad Radiol"},{"key":"742_CR25","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1007\/s00330-012-2489-z","volume":"22","author":"OM Mets","year":"2012","unstructured":"Mets OM, Willemink MJ, de Kort FPL et al (2012) The effect of iterative reconstruction on computed tomography assessment of emphysema, air trapping and airways dimensions. Eur Radiol 22:2103\u20132109","journal-title":"Eur Radiol"},{"key":"742_CR26","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/TBME.2021.3117407","volume":"69","author":"H Guan","year":"2022","unstructured":"Guan H, Liu M (2022) Domain adaptation for medical image analysis: a survey. IEEE Trans Biomed Eng 69:1173\u20131185","journal-title":"IEEE Trans Biomed Eng"},{"key":"742_CR27","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1109\/TMI.2020.2973595","volume":"39","author":"L Zhang","year":"2021","unstructured":"Zhang L, Wang X, Yang D et al (2021) Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans Med Imaging 39:2531\u20132540","journal-title":"IEEE Trans Med Imaging"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00742-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00742-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00742-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:43:56Z","timestamp":1780055036000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00742-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["742"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00742-x","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"11 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 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":"This study did not involve new animal experiments. All analyses were performed on imaging data acquired in previous studies that were approved by the respective local animal welfare authorities. Therefore, no additional ethical approval was required for the present work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"This study did not involve new animal experiments. All analyses were performed on imaging data acquired in previous studies that were approved by the respective local animal welfare authorities. Therefore, no additional ethical approval was required for the present work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Felix Gremse is the owner of Gremse-IT GmbH and Imalytics Preclinical. FG is also a member of the Scientific Editorial Board of\n                      European Radiology Experimental\n                      and, as such, did not participate in the selection or review processes for this article. Zachary Gurberg is the Chief Operating Officer (COO) of Gremse-IT GmbH, and Sarah Schraven is an employee of Gremse-IT GmbH. All other authors declare no conflicts of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"79"}}