{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T18:52:18Z","timestamp":1740163938311,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T00:00:00Z","timestamp":1662508800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T00:00:00Z","timestamp":1662508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R44CA213601"],"award-info":[{"award-number":["R44CA213601"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Cryo-imaging provided 3D whole-mouse microscopic color anatomy and fluorescence images that enables biotechnology applications (e.g., stem cells and metastatic cancer). In this report, we compared three methods of organ segmentation: 2D U-Net with <jats:italic>2D-slices<\/jats:italic> and 3D U-Net with either <jats:italic>3D-whole-mouse or 3D-patches<\/jats:italic>. We evaluated the brain, thymus, lung, heart, liver, stomach, spleen, left and right kidney, and bladder. Training with 63 mice, <jats:italic>2D-slices<\/jats:italic> had the best performance, with median Dice scores of\u2009&gt;\u20090.9 and median Hausdorff distances of\u2009&lt;\u20091.2\u00a0mm in eightfold cross validation for all organs, except bladder, which is a problem organ due to variable filling and poor contrast. Results were comparable to those for a second analyst on the same data. Regression analyses were performed to fit learning curves, which showed that <jats:italic>2D-slices<\/jats:italic> can succeed with fewer samples. Review and editing of <jats:italic>2D-slices<\/jats:italic> segmentation results reduced human operator time from\u2009~\u20092-h to\u2009~\u200925-min, with reduced inter-observer variability. As demonstrations, we used organ segmentation to evaluate size changes in liver disease and to quantify the distribution of therapeutic mesenchymal stem cells in organs. With a 48-GB GPU, we determined that extra GPU RAM improved the performance of 3D deep learning because we could train at a higher resolution.<\/jats:p>","DOI":"10.1038\/s41598-022-19037-3","type":"journal-article","created":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T22:02:51Z","timestamp":1662588171000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning multi-organ segmentation for whole mouse cryo-images including a comparison of 2D and 3D deep networks"],"prefix":"10.1038","volume":"12","author":[{"given":"Yiqiao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Madhusudhana","family":"Gargesha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Scott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arthure Olivia","family":"Tchilibou Wane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David L.","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,7]]},"reference":[{"key":"19037_CR1","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1002\/ar.20849","volume":"292","author":"D Roy","year":"2009","unstructured":"Roy, D., Steyer, G. J., Gargesha, M., Stone, M. E. & Wilson, D. L. 3D cryo-imaging: A very high-resolution view of the whole mouse. Anat. Rec. 292, 342\u2013351 (2009).","journal-title":"Anat. Rec."},{"key":"19037_CR2","doi-asserted-by":"publisher","first-page":"7984","DOI":"10.1038\/ncomms8984","volume":"6","author":"Z Zhou","year":"2015","unstructured":"Zhou, Z. et al. MRI detection of breast cancer micrometastases with a fibronectin-targeting contrast agent. Nat. Commun. 6, 7984 (2015).","journal-title":"Nat. Commun."},{"key":"19037_CR3","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/9780349","author":"M Qutaish","year":"2018","unstructured":"Qutaish, M. et al. Cryo-imaging and software platform for analysis of molecular MR imaging of micro-metastases. Int. J. Biomed. Imaging. https:\/\/doi.org\/10.1155\/2018\/9780349 (2018).","journal-title":"Int. J. Biomed. Imaging."},{"key":"19037_CR4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/s11307-011-0525-z","volume":"14","author":"MQ Qutaish","year":"2012","unstructured":"Qutaish, M. Q. et al. Cryo-image analysis of tumor cell migration, invasion, and dispersal in a mouse xenograft model of human glioblastoma multiforme. Mol. Imaging Biol. 14, 572\u2013583 (2012).","journal-title":"Mol. Imaging Biol."},{"key":"19037_CR5","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1109\/TMI.2015.2497285","volume":"35","author":"P Wuttisarnwattana","year":"2016","unstructured":"Wuttisarnwattana, P., Gargesha, M., van\u2019t Hof, W., Cooke, K. R. & Wilson, D. L. Automatic stem cell detection in microscopic whole mouse cryo-imaging. IEEE Trans. Med. Imaging 35, 819\u2013829 (2016).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"19037_CR6","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1097\/MPA.0000000000000607","volume":"45","author":"JE Kobes","year":"2016","unstructured":"Kobes, J. E. et al. Improved treatment of pancreatic cancer with drug delivery nanoparticles loaded with a novel AKT\/PDK1 inhibitor. Pancreas 45, 1158\u20131166 (2016).","journal-title":"Pancreas"},{"key":"19037_CR7","doi-asserted-by":"publisher","first-page":"17527","DOI":"10.1038\/s41598-021-96838-y","volume":"11","author":"Y Liu","year":"2021","unstructured":"Liu, Y. et al. Quantitative analysis of metastatic breast cancer in mice using deep learning on cryo-image data. Sci. Rep. 11, 17527 (2021).","journal-title":"Sci. Rep."},{"key":"19037_CR8","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.media.2019.04.005","volume":"55","author":"Y Wang","year":"2019","unstructured":"Wang, Y. et al. Abdominal multi-organ segmentation with organ-attention networks and statistical fusion. Med. Image Anal. 55, 88\u2013102 (2019).","journal-title":"Med. Image Anal."},{"key":"19037_CR9","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cviu.2017.04.002","volume":"164","author":"F Milletari","year":"2017","unstructured":"Milletari, F. et al. Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound. Comput. Vis. Image Underst. 164, 92\u2013102 (2017).","journal-title":"Comput. Vis. Image Underst."},{"key":"19037_CR10","first-page":"190","volume-title":"Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges","author":"C Payer","year":"2018","unstructured":"Payer, C., \u0160tern, D., Bischof, H. & Urschler, M. Multi-label whole heart segmentation using CNNs and anatomical label configurations. In Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges (eds Pop, M. et al.) 190\u2013198 (Springer, 2018)."},{"key":"19037_CR11","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1002\/mp.14580","volume":"48","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Zhao, T., Gay, H., Zhang, W. & Sun, B. ARPM-net: A novel CNN-based adversarial method with Markov random field enhancement for prostate and organs at risk segmentation in pelvic CT images. Med. Phys. 48, 227\u2013237 (2021).","journal-title":"Med. Phys."},{"key":"19037_CR12","doi-asserted-by":"publisher","first-page":"4971","DOI":"10.1002\/mp.14429","volume":"47","author":"Y Chen","year":"2020","unstructured":"Chen, Y. et al. Fully automated multiorgan segmentation in abdominal magnetic resonance imaging with deep neural networks. Med. Phys. 47, 4971\u20134982 (2020).","journal-title":"Med. Phys."},{"key":"19037_CR13","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.compmedimag.2018.03.001","volume":"66","author":"HR Roth","year":"2018","unstructured":"Roth, H. R. et al. An application of cascaded 3D fully convolutional networks for medical image segmentation. Comput. Med. Imaging Graph. 66, 90\u201399 (2018).","journal-title":"Comput. Med. Imaging Graph."},{"key":"19037_CR14","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N. & Ahmadi, S.-A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. http:\/\/arXiv.org\/1606.04797 (2016).","DOI":"10.1109\/3DV.2016.79"},{"key":"19037_CR15","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/TMI.2018.2806309","volume":"37","author":"E Gibson","year":"2018","unstructured":"Gibson, E. et al. Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Trans. Med. Imaging 37, 1822\u20131834 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"19037_CR16","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S. S., Brox, T. & Ronneberger, O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. http:\/\/arXiv.org\/1606.06650 (2016).","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"19037_CR17","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.1109\/TUFFC.2021.3068156","volume":"68","author":"Z Qiu","year":"2021","unstructured":"Qiu, Z. et al. A deep learning approach for segmentation, classification, and visualization of 3-D high-frequency ultrasound images of mouse embryos. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 68, 2460\u20132471 (2021).","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"19037_CR18","doi-asserted-by":"publisher","unstructured":"Xu, T. et al. Deep Mouse: An End-to-End Auto-Context Refinement Framework for Brain Ventricle and Body Segmentation in Embryonic Mice Ultrasound Volumes. https:\/\/doi.org\/10.48550\/arXiv.1910.09061 (2019).","DOI":"10.48550\/arXiv.1910.09061"},{"key":"19037_CR19","doi-asserted-by":"publisher","unstructured":"Qiu, Z. et al. Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic Mice. https:\/\/doi.org\/10.48550\/arXiv.1811.03601 (2018).","DOI":"10.48550\/arXiv.1811.03601"},{"key":"19037_CR20","doi-asserted-by":"publisher","unstructured":"Qiu, Z. et al. Automatic mouse embryo brain ventricle & body segmentation and mutant classification from ultrasound data using deep learning. In 2019 IEEE International Ultrasonics Symposium (IUS), 12\u201315. https:\/\/doi.org\/10.1109\/ULTSYM.2019.8925720 (2019).","DOI":"10.1109\/ULTSYM.2019.8925720"},{"key":"19037_CR21","first-page":"635","volume":"2018","author":"J-W Kuo","year":"2018","unstructured":"Kuo, J.-W. et al. Automatic body localization and brain ventricle segmentation in 3D high frequency ultrasound images of mouse embryos. Proc. IEEE Int. Symp. Biomed. Imaging 2018, 635\u2013639 (2018).","journal-title":"Proc. IEEE Int. Symp. Biomed. Imaging"},{"key":"19037_CR22","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"19037_CR23","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s11548-016-1501-5","volume":"12","author":"P Hu","year":"2017","unstructured":"Hu, P. et al. Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets. Int. J. CARS 12, 399\u2013411 (2017).","journal-title":"Int. J. CARS"},{"key":"19037_CR24","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-319-46723-8_48","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016","author":"PF Christ","year":"2016","unstructured":"Christ, P. F. et al. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016 (eds Ourselin, S. et al.) 415\u2013423 (Springer, 2016)."},{"key":"19037_CR25","doi-asserted-by":"publisher","first-page":"5626","DOI":"10.1038\/s41467-020-19449-7","volume":"11","author":"O Schoppe","year":"2020","unstructured":"Schoppe, O. et al. Deep learning-enabled multi-organ segmentation in whole-body mouse scans. Nat. Commun. 11, 5626 (2020).","journal-title":"Nat. Commun."},{"key":"19037_CR26","first-page":"30","volume-title":"Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging","author":"Y Liu","year":"2020","unstructured":"Liu, Y. et al. Deep learning based multi-organ segmentation and metastases segmentation in whole mouse body and the cryo-imaging cancer imaging and therapy analysis platform (CITAP). In Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging (eds Gimi, B. S. & Krol, A.) 30 (SPIE, 2020)."},{"key":"19037_CR27","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1109\/TMI.2020.2973595","volume":"39","author":"L Zhang","year":"2020","unstructured":"Zhang, L. et al. Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans. Med. Imaging 39, 2531\u20132540 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"19037_CR28","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1472-6947-12-8","volume":"12","author":"RL Figueroa","year":"2012","unstructured":"Figueroa, R. L., Zeng-Treitler, Q., Kandula, S. & Ngo, L. H. Predicting sample size required for classification performance. BMC Med. Inform. Decis. Mak. 12, 8 (2012).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"19037_CR29","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/s12194-021-00630-6","volume":"14","author":"T Nemoto","year":"2021","unstructured":"Nemoto, T. et al. Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs. Radiol. Phys. Technol. 14, 318\u2013327 (2021).","journal-title":"Radiol. Phys. Technol."},{"key":"19037_CR30","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s13287-017-0590-6","volume":"8","author":"SFH de Witte","year":"2017","unstructured":"de Witte, S. F. H. et al. Cytokine treatment optimises the immunotherapeutic effects of umbilical cord-derived MSC for treatment of inflammatory liver disease. Stem Cell Res. Ther. 8, 140 (2017).","journal-title":"Stem Cell Res. Ther."},{"key":"19037_CR31","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1177\/0049124104268644","volume":"33","author":"KP Burnham","year":"2004","unstructured":"Burnham, K. P. & Anderson, D. R. Multimodel inference: Understanding AIC and BIC in model selection. Sociol. Methods Res. 33, 261\u2013304 (2004).","journal-title":"Sociol. Methods Res."},{"key":"19037_CR32","unstructured":"Masters, D. & Luschi, C. Revisiting small batch training for deep neural networks. http:\/\/arXiv.org\/1804.07612 (2018)."},{"key":"19037_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15283\/ijsc.2008.1.1.1","volume":"1","author":"A Kurtz","year":"2008","unstructured":"Kurtz, A. Mesenchymal stem cell delivery routes and fate. Int. J. Stem Cells 1, 1\u20137 (2008).","journal-title":"Int. J. Stem Cells"},{"key":"19037_CR34","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/labinvest.2012.145","volume":"93","author":"K Toriumi","year":"2013","unstructured":"Toriumi, K. et al. Carbon tetrachloride-induced hepatic injury through formation of oxidized diacylglycerol and activation of the PKC\/NF-\u03baB pathway. Lab. Investig. 93, 218\u2013229 (2013).","journal-title":"Lab. Investig."},{"issue":"734","key":"19037_CR35","first-page":"e13","volume":"74","author":"P Khoshpouri","year":"2019","unstructured":"Khoshpouri, P. et al. Quantitative spleen and liver volume changes predict survival of patients with primary sclerosing cholangitis. Clin. Radiol. 74(734), e13\u2013e20 (2019).","journal-title":"Clin. Radiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-19037-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-19037-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-19037-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T12:50:41Z","timestamp":1664974241000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-19037-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,7]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["19037"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-19037-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"type":"electronic","value":"2045-2322"}],"subject":[],"published":{"date-parts":[[2022,9,7]]},"assertion":[{"value":"19 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Case Western Reserve University has licensed cryo-imaging technology to BioInVision, Inc.; Dr. Wilson is part owner of BioInVision, Inc.; and Dr. Gargesha is an employee of BioInVision, Inc. This information has been disclosed to Case Western Reserve University, and Dr. Wilson has an approved CWRU plan for managing potential conflicts of interest. The rest of the authors do not have competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"15161"}}