{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T19:26:37Z","timestamp":1794079597859,"version":"4.8.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T00:00:00Z","timestamp":1663804800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T00:00:00Z","timestamp":1663804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["KL2TR001882"],"award-info":[{"award-number":["KL2TR001882"]}],"id":[{"id":"10.13039\/100000002","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>Multiple studies have created state-of-the-art liver segmentation models using Deep Convolutional Neural Networks (DCNNs) such as the V-net and H-DenseUnet. Oversegmentation however continues to be a problem. We set forth to address these limitations by developing a an automated workflow that leverages the strengths of different DCNN architectures, resulting in a pipeline that enables fully automated liver segmentation. A Pipeline for Automated Deep Learning Liver Segmentation (PADLLS) was developed and implemented that cascades multiple DCNNs that were trained on more than 200 CT scans. First, a V-net is used to create a rough liver, spleen, and stomach mask. After stomach and spleen pixels are removed using their respective masks and ascites is removed using a morphological algorithm, the scan is passed to a H-DenseUnet to yield the final segmentation. The segmentation accuracy of the pipleline was compared to the H-DenseUnet and the V-net using the SLIVER07 and 3DIRCADb datasets as benchmarks. The PADLLS Dice score for the SLIVER07 dataset was calculated to be 0.957\u2009\u00b1\u20090.033 and was significantly better than the H-DenseUnet\u2019s score of 0.927\u2009\u00b1\u20090.044 (<jats:italic>p<\/jats:italic>\u2009=\u20090.0219) and the V-net\u2019s score of 0.872\u2009\u00b1\u20090.121 (<jats:italic>p<\/jats:italic>\u2009=\u20090.0067). The PADLLS Dice score for the 3DIRCADb dataset was 0.965\u2009\u00b1\u20090.016 and was significantly better than the H-DenseUnet\u2019s score of 0.930\u2009\u00b1\u20090.041 (<jats:italic>p<\/jats:italic>\u2009=\u20090.0014) the V-net\u2019s score of 0.874\u2009\u00b1\u20090.060 (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). In conclusion, our pipeline (PADLLS) outperforms existing liver segmentation models, serves as a valuable tool for image-based analysis, and is freely available for download and use.\n<\/jats:p>","DOI":"10.1038\/s41598-022-20108-8","type":"journal-article","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T09:03:09Z","timestamp":1663837389000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["A pipeline for automated deep learning liver segmentation (PADLLS) from contrast enhanced CT exams"],"prefix":"10.1038","volume":"12","author":[{"given":"Jayasuriya","family":"Senthilvelan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neema","family":"Jamshidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,22]]},"reference":[{"key":"20108_CR1","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s13244-017-0558-1","volume":"8","author":"A Gotra","year":"2017","unstructured":"Gotra, A. et al. Liver segmentation: Indications, techniques and future directions. Insights Imaging 8, 377\u2013392. https:\/\/doi.org\/10.1007\/s13244-017-0558-1 (2017).","journal-title":"Insights Imaging"},{"key":"20108_CR2","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1056\/NEJMra1610570","volume":"377","author":"EB Tapper","year":"2017","unstructured":"Tapper, E. B. & Lok, A.S.-F. Use of liver imaging and biopsy in clinical practice. N. Engl. J. Med. 377, 756\u2013768. https:\/\/doi.org\/10.1056\/NEJMra1610570 (2017).","journal-title":"N. Engl. J. Med."},{"key":"20108_CR3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.2147\/JHC.S186239","volume":"6","author":"KM Elsayes","year":"2019","unstructured":"Elsayes, K. M. et al. LI-RADS: A conceptual and historical review from its beginning to its recent integration into AASLD clinical practice guidance. J. Hepatocell Carcinoma 6, 49\u201369. https:\/\/doi.org\/10.2147\/JHC.S186239 (2019).","journal-title":"J. Hepatocell Carcinoma"},{"key":"20108_CR4","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1080\/02564602.2014.906861","volume":"31","author":"A Norouzi","year":"2014","unstructured":"Norouzi, A. et al. Medical image segmentation methods, algorithms, and applications. IETE Tech. Rev. 31, 199\u2013213. https:\/\/doi.org\/10.1080\/02564602.2014.906861 (2014).","journal-title":"IETE Tech. Rev."},{"key":"20108_CR5","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.csi.2010.06.003","volume":"33","author":"G Rabottino","year":"2011","unstructured":"Rabottino, G. et al. Performance evaluation of a region growing procedure for mammographic breast lesion identification. Comput. Stand. Interfaces 33, 128\u2013135. https:\/\/doi.org\/10.1016\/j.csi.2010.06.003 (2011).","journal-title":"Comput. Stand. Interfaces"},{"key":"20108_CR6","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/0730-725X(93)90417-C","volume":"11","author":"LP Clarke","year":"1993","unstructured":"Clarke, L. P. et al. MRI: Stability of three supervised segmentation techniques. Magn. Reson. Imaging 11, 95\u2013106. https:\/\/doi.org\/10.1016\/0730-725X(93)90417-C (1993).","journal-title":"Magn. Reson. Imaging"},{"key":"20108_CR7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11263-006-7934-5","volume":"70","author":"Y Boykov","year":"2006","unstructured":"Boykov, Y. & Funka-Lea, G. Graph cuts and efficient N-D image segmentation. Int. J. Comput. Vis. 70, 109\u2013131. https:\/\/doi.org\/10.1007\/s11263-006-7934-5 (2006).","journal-title":"Int. J. Comput. Vis."},{"key":"20108_CR8","doi-asserted-by":"publisher","first-page":"8676","DOI":"10.1088\/1361-6560\/61\/24\/8676","volume":"61","author":"P Hu","year":"2016","unstructured":"Hu, P. et al. Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution. Phys. Med. Biol. 61, 8676\u20138698. https:\/\/doi.org\/10.1088\/1361-6560\/61\/24\/8676 (2016).","journal-title":"Phys. Med. Biol."},{"key":"20108_CR9","unstructured":"Bilic, P., Christ, P. F., Vorontsov, E. et al. The liver tumor segmentation benchmark (LiTS). arXiv:190104056 [cs] (2019)."},{"key":"20108_CR10","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. https:\/\/doi.org\/10.1109\/TMI.2018.2806309 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20108_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Chen, H., Qi, X. et al. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes. arXiv:170907330 [cs] (2018).","DOI":"10.1109\/TMI.2018.2845918"},{"key":"20108_CR12","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1109\/TMI.2009.2013851","volume":"28","author":"T Heimann","year":"2009","unstructured":"Heimann, T. et al. Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Trans. Med. Imaging 28, 1251\u20131265. https:\/\/doi.org\/10.1109\/TMI.2009.2013851 (2009).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20108_CR13","unstructured":"3Dircadb | IRCAD France. https:\/\/www.ircad.fr\/research\/3dircadb\/. Accessed 26 Aug 2020."},{"key":"20108_CR14","unstructured":"Roth, H., Farag, A., Turkbey, E. B. et al. Data from pancreas-CT (2016)."},{"key":"20108_CR15","doi-asserted-by":"publisher","unstructured":"Landman, B., Xu, Z., Igelsias, J. E. Segmentation outside the cranial vault challenge. https:\/\/doi.org\/10.7303\/SYN3193805 (2015).","DOI":"10.7303\/SYN3193805"},{"key":"20108_CR16","first-page":"728","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017","author":"E Gibson","year":"2017","unstructured":"Gibson, E. et al. Towards image-guided pancreas and biliary endoscopy: Automatic multi-organ segmentation on abdominal CT with dense dilated networks. In Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017 (eds Descoteaux, M., Maier-Hein, L., Franz, A. et al.) 728\u2013736 (Springer International Publishing, 2017)."},{"key":"20108_CR17","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1109\/TMI.2019.2948320","volume":"39","author":"H Seo","year":"2020","unstructured":"Seo, H. et al. Modified U-Net (mU-Net) with incorporation of object-dependent high level features for improved liver and liver-tumor segmentation in CT images. IEEE Trans. Med. Imaging 39, 1316\u20131325. https:\/\/doi.org\/10.1109\/TMI.2019.2948320 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20108_CR18","volume-title":"Atlas of Human Anatomy","author":"F Netter","year":"2006","unstructured":"Netter, F. Atlas of Human Anatomy 18th edn. (Saunders\/Elsevier, Philadelphia, PA, 2006).","edition":"18"},{"key":"20108_CR19","doi-asserted-by":"publisher","first-page":"AC09","DOI":"10.7860\/JCDR\/2017\/24467.10020","volume":"11","author":"HJ Chaudhari","year":"2017","unstructured":"Chaudhari, H. J., Ravat, M. K., Vaniya, V. H. & Bhedi, A. N. Morphological study of human liver and its surgical importance. J. Clin. Diagn. Res. 11, AC09-AC12. https:\/\/doi.org\/10.7860\/JCDR\/2017\/24467.10020 (2017).","journal-title":"J. Clin. Diagn. Res."},{"key":"20108_CR20","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","volume":"278","author":"RJ Gillies","year":"2016","unstructured":"Gillies, R. J., Kinahan, P. E. & Hricak, H. Radiomics: Images are more than pictures, they are data. Radiology 278, 563\u2013577. https:\/\/doi.org\/10.1148\/radiol.2015151169 (2016).","journal-title":"Radiology"},{"key":"20108_CR21","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1148\/radiol.13132195","volume":"270","author":"MD Kuo","year":"2014","unstructured":"Kuo, M. D. & Jamshidi, N. Behind the numbers: Decoding molecular phenotypes with radiogenomics\u2013guiding principles and technical considerations. Radiology 270, 320\u2013325. https:\/\/doi.org\/10.1148\/radiol.13132195 (2014).","journal-title":"Radiology"},{"key":"20108_CR22","unstructured":"Chlebus, G., Meine, H., Moltz, J. H., Schenk, A. Neural network-based automatic liver tumor segmentation with random forest-based candidate filtering. arXiv:170600842 [cs] (2017)."},{"key":"20108_CR23","unstructured":"Han, X. Automatic liver lesion segmentation using a deep convolutional neural network method. arXiv preprint arXiv:170407239 (2017)."},{"key":"20108_CR24","doi-asserted-by":"publisher","first-page":"5315","DOI":"10.1109\/TIP.2015.2481326","volume":"24","author":"G Li","year":"2015","unstructured":"Li, G. et al. Automatic liver segmentation based on shape constraints and deformable graph cut in CT images. IEEE Trans. Image Process. 24, 5315\u20135329 (2015).","journal-title":"IEEE Trans. Image Process."},{"key":"20108_CR25","first-page":"500","volume":"15","author":"M Moghbel","year":"2016","unstructured":"Moghbel, M., Mashohor, S., Mahmud, R. & Saripan, M. I. B. Automatic liver segmentation on computed tomography using random walkers for treatment planning. EXCLI J. 15, 500 (2016).","journal-title":"EXCLI J."},{"key":"20108_CR26","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11548-016-1467-3","volume":"12","author":"F Lu","year":"2017","unstructured":"Lu, F. et al. Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int. J. Comput. Assist. Radiol. Surg. 12, 171\u2013182 (2017).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"20108_CR27","doi-asserted-by":"publisher","first-page":"152","DOI":"10.18178\/joig.6.2.152-159","volume":"6","author":"Y Enokiya","year":"2018","unstructured":"Enokiya, Y. et al. Automatic liver segmentation using U-Net with wasserstein GANs. JOIG 6, 152\u2013159. https:\/\/doi.org\/10.18178\/joig.6.2.152-159 (2018).","journal-title":"JOIG"},{"key":"20108_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, C., Ai, D. & Feng, C. et al. Dial\/Hybrid cascade 3DResUNet for liver and tumor segmentation. In Proceedings of the 2020 4th International Conference on Digital Signal Processing 92\u201396 (2020).","DOI":"10.1145\/3408127.3408201"},{"key":"20108_CR29","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00530-020-00709-x","volume":"27","author":"Z Liu","year":"2021","unstructured":"Liu, Z. et al. Automatic liver segmentation from abdominal CT volumes using improved convolution neural networks. Multimedia Syst. 27, 111\u2013124. https:\/\/doi.org\/10.1007\/s00530-020-00709-x (2021).","journal-title":"Multimedia Syst."},{"key":"20108_CR30","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1007\/s11760-020-01835-9","volume":"15","author":"T Fan","year":"2021","unstructured":"Fan, T. et al. MSN-Net: A multi-scale context nested U-Net for liver segmentation. SIViP 15, 1089\u20131097. https:\/\/doi.org\/10.1007\/s11760-020-01835-9 (2021).","journal-title":"SIViP"},{"key":"20108_CR31","doi-asserted-by":"publisher","first-page":"105095","DOI":"10.1016\/j.compbiomed.2021.105095","volume":"140","author":"JDL Ara\u00fajo","year":"2021","unstructured":"Ara\u00fajo, J. D. L. et al. Liver segmentation from computed tomography images using cascade deep learning. Comput. Biol. Med. 140, 105095. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.105095 (2021).","journal-title":"Comput. Biol. Med."},{"key":"20108_CR32","doi-asserted-by":"publisher","first-page":"6370","DOI":"10.1038\/s41598-022-09978-0","volume":"12","author":"JG Jeong","year":"2022","unstructured":"Jeong, J. G. et al. Deep 3D attention CLSTM U-Net based automated liver segmentation and volumetry for the liver transplantation in abdominal CT volumes. Sci. Rep. 12, 6370. https:\/\/doi.org\/10.1038\/s41598-022-09978-0 (2022).","journal-title":"Sci. Rep."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20108-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20108-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20108-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T10:24:42Z","timestamp":1663842282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20108-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,22]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["20108"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-20108-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,22]]},"assertion":[{"value":"31 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"15794"}}