{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T03:59:37Z","timestamp":1774497577880,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Education and Research (BMBF)","award":["01KX2021"],"award-info":[{"award-number":["01KX2021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Lung lobe segmentation in chest CT is relevant to a wide range of clinical applications. However, existing segmentation pipelines often exhibit vulnerabilities and performance degradations when applied to external datasets. This is usually attributed to the size of the available dataset or model. We show that it is possible to enhance generalizability without huge resources by carefully curating the dataset and combining machine learning with medical expertise. Multiple machine learning techniques (self-supervision (SSL), attention (A), and data augmentation (DA)) are used to train a fast and fully-automated lung lobe segmentation model based on 2D U-Net. Our study involved evaluating these techniques on a diverse dataset collected under the RACOON project, encompassing 100 CT chest scans from patients with bacterial, viral, or SARS-CoV2 infections. We compare our model to a baseline U-Net trained on the same dataset. Our approach significantly improved segmentation accuracy (Dice score of 92.8% vs. 82.3%, p &lt; 0.001). Moreover, our model achieved state-of-the-art performance (Dice score of 92.8% vs. 90.8% for the literature\u2019s state-of-the-art, p = 0.102) with reduced training examples (69 vs. 231 CT Scans). Among the techniques, data augmentation with expert knowledge displayed the most significant impact, enhancing the Dice score by +0.056. Notably, these enhancements are not limited to lobe segmentation but can be seamlessly integrated into various medical imaging segmentation tasks, demonstrating their versatility and potential for broader applications.<\/jats:p>","DOI":"10.3390\/bioengineering11010021","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T03:42:12Z","timestamp":1703475732000},"page":"21","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Lightweight Techniques to Improve Generalization and Robustness of U-Net Based Networks for Pulmonary Lobe Segmentation"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6474-7208","authenticated-orcid":false,"given":"Armin A.","family":"Dadras","sequence":"first","affiliation":[{"name":"Division of Phoniatrics-Logopedics, Department of Otorhinolaryngology, Medical University of Vienna, W\u00e4hringer G\u00fcrtel 18-20, 1090 Vienna, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Achref","family":"Jaziri","sequence":"additional","affiliation":[{"name":"Center for Cognition and Computation, Goethe University Frankfurt, Robert Meyer Str. 10-12, 60323 Frankfurt am Main, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Frodl","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5218-1075","authenticated-orcid":false,"given":"Thomas J.","family":"Vogl","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"Dietz","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany"},{"name":"Department of Medicine, Medical Clinic 1, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9194-5955","authenticated-orcid":false,"given":"Andreas M.","family":"Bucher","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"ref_1","unstructured":"Zwanenburg, A., Leger, S., Valli\u00e8res, M., and L\u00f6ck, S. (2016). Image biomarker standardisation initiative-feature definitions. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1795","DOI":"10.1007\/s00330-020-07147-3","article-title":"Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks","volume":"31","author":"Koitka","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shikata, H., McLennan, G., Hoffman, E.A., and Sonka, M. (2009). Segmentation of pulmonary vascular trees from thoracic 3D CT images. Int. J. Biomed. Imaging, 2009.","DOI":"10.1155\/2009\/636240"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMI.2005.859209","article-title":"Atlas-driven lung lobe segmentation in volumetric X-ray CT images","volume":"25","author":"Zhang","year":"2005","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qi, S., van Triest, H.J., Yue, Y., Xu, M., and Kang, Y. (2014). Automatic pulmonary fissure detection and lobe segmentation in CT chest images. Biomed. Eng. Online, 13.","DOI":"10.1186\/1475-925X-13-59"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhu, C., Qi, S., van Triest, H., Wang, S., Kang, Y., and Yue, Y. (2010, January 16\u201318). Automatic 3d segmentation of human airway tree in ct image. Proceedings of the 2010 3rd International Conference on Biomedical Engineering and Informatics, Yantai, China.","DOI":"10.1109\/BMEI.2010.5639658"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/TMI.2012.2219881","article-title":"Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi","volume":"32","author":"Lassen","year":"2012","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1986","DOI":"10.1109\/TMI.2009.2027117","article-title":"Pulmonary lobe segmentation in CT examinations using implicit surface fitting","volume":"28","author":"Pu","year":"2009","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1117\/12.480321","article-title":"Lung lobe segmentation by anatomy-guided 3D watershed transform","volume":"Volume 5032","author":"Kuhnigk","year":"2003","journal-title":"Proceedings of the Medical Imaging 2003: Image Processing"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1117\/12.428138","article-title":"Lung lobe segmentation by graph search with 3D shape constraints","volume":"Volume 4321","author":"Zhang","year":"2001","journal-title":"Proceedings of the Medical Imaging 2001: Physiology and Function from Multidimensional Images"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ferreira, F.T., Sousa, P., Galdran, A., Sousa, M.R., and Campilho, A. (2018, January 8\u201313). End-to-end supervised lung lobe segmentation. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.","DOI":"10.1109\/IJCNN.2018.8489677"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_13","unstructured":"Imran, A.A.Z., Hatamizadeh, A., Ananth, S.P., Ding, X., Terzopoulos, D., and Tajbakhsh, N. (2018). Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, J., Zhao, J., Chi, Y., Xie, X., Zhang, L., and Hua, X. (2019, January 8\u201311). Automated segmentation of pulmonary lobes using coordination-guided deep neural networks. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759492"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Gerard, S.E., and Reinhardt, J.M. (2019, January 8\u201311). Pulmonary lobe segmentation using a sequence of convolutional neural networks for marginal learning. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759212"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Harrison, A.P., Xu, Z., George, K., Lu, L., Summers, R.M., and Mollura, D.J. (2017, January 11\u201313). Progressive and multi-path holistically nested neural networks for pathological lung segmentation from CT images. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada.","DOI":"10.1007\/978-3-319-66179-7_71"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cardoso, M.J., Arbel, T., Carneiro, G., Syeda-Mahmood, T., Tavares, J.M.R., Moradi, M., Bradley, A., Greenspan, H., Papa, J.P., and Madabhushi, A. (2017). Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-319-67558-9"},{"key":"ref_18","unstructured":"Lassen-Schmidt, B., Hering, A., Krass, S., and Meine, H. (2020). Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s41747-020-00173-2","article-title":"Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem","volume":"4","author":"Hofmanninger","year":"2020","journal-title":"Eur. Radiol. Exp."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10278-019-00223-1","article-title":"Fully automated lung lobe segmentation in volumetric chest CT with 3D U-Net: Validation with intra-and extra-datasets","volume":"33","author":"Park","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1148\/radiol.2462070712","article-title":"Fleischner Society: Glossary of terms for thoracic imaging","volume":"246","author":"Hansell","year":"2008","journal-title":"Radiology"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","article-title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","volume":"3","author":"Roberts","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The lung image database consortium (LIDC) and image database resource initiative (IDRI): A completed reference database of lung nodules on CT scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys."},{"key":"ref_24","unstructured":"Wu, K. (2022, November 15). COVID-19 Lung Images. Available online: https:\/\/ieee-dataport.org\/documents\/covid-19-lung-images."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1109\/42.932749","article-title":"Addendum: B-spline interpolation in medical image processing","volume":"20","author":"Lehmann","year":"2001","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_27","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., and Song, D. (2019). Using self-supervised learning can improve model robustness and uncertainty. arXiv."},{"key":"ref_28","unstructured":"Navarro, F., Watanabe, C., Shit, S., Sekuboyina, A., Peeken, J.C., Combs, S.E., and Menze, B.H. (2021). Evaluating the Robustness of Self-Supervised Learning in Medical Imaging. arXiv."},{"key":"ref_29","unstructured":"Jetley, S., Lord, N.A., Lee, N., and Torr, P.H. (2018). Learn to pay attention. arXiv."},{"key":"ref_30","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.","DOI":"10.3390\/info11020125"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Castro, E., Cardoso, J.S., and Pereira, J.C. (2018, January 4\u20137). Elastic deformations for data augmentation in breast cancer mass detection. Proceedings of the 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA.","DOI":"10.1109\/BHI.2018.8333411"},{"key":"ref_33","unstructured":"Simard, P.Y., Steinkraus, D., and Platt, J.C. (2003, January 6). Best practices for convolutional neural networks applied to visual document analysis. Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, UK."},{"key":"ref_34","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings, Sardinia, Italy."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/11\/1\/21\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:41:31Z","timestamp":1760132491000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/11\/1\/21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["bioengineering11010021"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering11010021","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,25]]}}}