{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T07:02:07Z","timestamp":1791874927895,"version":"4.3.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T00:00:00Z","timestamp":1747440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T00:00:00Z","timestamp":1747440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["NE 2136\/3-1"],"award-info":[{"award-number":["NE 2136\/3-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["LI 3893\/6-1"],"award-info":[{"award-number":["LI 3893\/6-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["TR 1700\/7-1"],"award-info":[{"award-number":["TR 1700\/7-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["INST222\/1261-1"],"award-info":[{"award-number":["INST222\/1261-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["031L0312A"],"award-info":[{"award-number":["031L0312A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01KD2215B"],"award-info":[{"award-number":["01KD2215B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["GA 101057091"],"award-info":[{"award-number":["GA 101057091"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009398","name":"Medizinische Fakult\u00e4t, RWTH Aachen University","doi-asserted-by":"publisher","award":["START Program"],"award-info":[{"award-number":["START Program"]}],"id":[{"id":"10.13039\/501100009398","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014690","name":"Ministerium f\u00fcr Kultur und Wissenschaft des Landes Nordrhein-Westfalen","doi-asserted-by":"publisher","award":["214-4.06.05.08 - 139057"],"award-info":[{"award-number":["214-4.06.05.08 - 139057"]}],"id":[{"id":"10.13039\/501100014690","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Artifacts in clinical MRI can compromise the performance of AI models. This study evaluates how different data augmentation strategies affect an AI model\u2019s segmentation performance under variable artifact severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We used an AI model based on the nnU-Net architecture to automatically quantify lower limb alignment using axial T2-weighted MR images. Three versions of the AI model were trained with different augmentation strategies: (1) no augmentation (\u201cbaseline\u201d), (2) standard nnU-net augmentations (\u201cdefault\u201d), and (3) \u201cdefault\u201d plus augmentations that emulate MR artifacts (\u201cMRI-specific\u201d). Model performance was tested on 600 MR image stacks (right and left; hip, knee, and ankle) from 20 healthy participants (mean age, 23\u2009\u00b1\u20093 years, 17 men), each imaged five times under standardized motion to induce artifacts. Two radiologists graded each stack\u2019s artifact severity as none, mild, moderate, and severe, and manually measured torsional angles. Segmentation quality was assessed using the Dice similarity coefficient (DSC), while torsional angles were compared between manual and automatic measurements using mean absolute deviation (MAD), intraclass correlation coefficient (ICC), and Pearson\u2019s correlation coefficient (r). Statistical analysis included parametric tests and a Linear Mixed-Effects Model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      MRI-specific augmentation resulted in slightly (yet not significantly) better performance than the default strategy. Segmentation quality decreased with increasing artifact severity, which was partially mitigated by default and MRI-specific augmentations (e.g., severe artifacts, proximal femur: DSC\n                      <jats:sub>baseline<\/jats:sub>\n                      \u2009=\u20090.58\u2009\u00b1\u20090.22; DSC\n                      <jats:sub>default<\/jats:sub>\n                      \u2009=\u20090.72\u2009\u00b1\u20090.22; DSC\n                      <jats:sub>MRI-specific<\/jats:sub>\n                      \u2009=\u20090.79\u2009\u00b1\u20090.14 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001]). These augmentations also maintained precise torsional angle measurements (e.g., severe artifacts, femoral torsion: MAD\n                      <jats:sub>baseline<\/jats:sub>\n                      \u2009=\u200920.6\u2009\u00b1\u200923.5\u00b0; MAD\n                      <jats:sub>default<\/jats:sub>\n                      \u2009=\u20097.0\u2009\u00b1\u200913.0\u00b0; MAD\n                      <jats:sub>MRI-specific<\/jats:sub>\n                      \u2009=\u20095.7\u2009\u00b1\u20099.5\u00b0 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001]; ICC\n                      <jats:sub>baseline<\/jats:sub>\n                      \u2009=\u2009\u22120.10 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.63; 95% CI: \u22120.61 to 0.47]; ICC\n                      <jats:sub>default<\/jats:sub>\n                      \u2009=\u20090.38 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.08; \u22120.17 to 0.76]; ICC\n                      <jats:sub>MRI-specific<\/jats:sub>\n                      \u2009=\u20090.86 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001; 0.62 to 0.95]; r\n                      <jats:sub>baseline<\/jats:sub>\n                      \u2009=\u20090.58 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001; 0.44 to 0.69]; r\n                      <jats:sub>default<\/jats:sub>\n                      \u2009=\u20090.68 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001; 0.56 to 0.77]; r\n                      <jats:sub>MRI-specific<\/jats:sub>\n                      \u2009=\u20090.86 [\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001; 0.81 to 0.9]).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Motion artifacts negatively impact AI models, but general-purpose augmentations enhance robustness effectively. MRI-specific augmentations offer minimal additional benefit.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Motion artifacts negatively impact the performance of diagnostic AI models for MRI, but mitigation methods remain largely unexplored.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Domain-specific augmentation during training can improve the robustness and performance of a model for quantifying lower limb alignment in the presence of severe artifacts.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Excellent robustness and accuracy are crucial for deploying diagnostic AI models in clinical practice. Including domain knowledge in model training can benefit clinical adoption.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-025-11670-6","type":"journal-article","created":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T00:29:18Z","timestamp":1747441758000},"page":"6865-6878","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["AI in motion: the impact of data augmentation strategies on mitigating MRI motion artifacts"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7050-9924","authenticated-orcid":false,"given":"Simon D.","family":"Westfechtel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristoffer","family":"Ku\u00dfmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cederic","family":"A\u00dfmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc S.","family":"Huppertz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert M.","family":"Siepmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teresa","family":"Lemainque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vera R.","family":"Winter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandra","family":"Barabasch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christiane K.","family":"Kuhl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Truhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Nebelung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,17]]},"reference":[{"key":"11670_CR1","unstructured":"Shi Z, He L (2010) Application of neural networks in medical image processing. In: Proceedings of the second international symposium on networking and network security. Citeseer, pp 2\u20134"},{"key":"11670_CR2","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1007\/s00256-024-04601-x","volume":"53","author":"CB Chung","year":"2024","unstructured":"Chung CB, Pathria MN, Resnick D (2024) MRI in MSK: is it the ultimate examination? Skelet Radiol 53:1727\u20131735. https:\/\/doi.org\/10.1007\/s00256-024-04601-x","journal-title":"Skelet Radiol"},{"key":"11670_CR3","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.21595\/jve.2018.19756","volume":"20","author":"T Budrys","year":"2018","unstructured":"Budrys T, Veikutis V, Lukosevicius S et al (2018) Artifacts in magnetic resonance imaging: how it can really affect diagnostic image quality and confuse clinical diagnosis? J Vibroeng 20:1202\u20131213. https:\/\/doi.org\/10.21595\/jve.2018.19756","journal-title":"J Vibroeng"},{"key":"11670_CR4","doi-asserted-by":"publisher","first-page":"012","DOI":"10.1055\/s-0034-1365831","volume":"18","author":"D Singh","year":"2014","unstructured":"Singh D, Chin M, Peh W (2014) Artifacts in musculoskeletal MR imaging. Semin Musculoskelet Radiol 18:012\u2013022. https:\/\/doi.org\/10.1055\/s-0034-1365831","journal-title":"Semin Musculoskelet Radiol"},{"key":"11670_CR5","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/jmri.20996","volume":"26","author":"K Rafat Zand","year":"2007","unstructured":"Rafat Zand K, Reinhold C, Haider MA et al (2007) Artifacts and pitfalls in MR imaging of the pelvis. J Magn Reson Imaging 26:480\u2013497","journal-title":"J Magn Reson Imaging"},{"key":"11670_CR6","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/j.jacr.2015.03.007","volume":"12","author":"JB Andre","year":"2015","unstructured":"Andre JB, Bresnahan BW, Mossa-Basha M et al (2015) Toward quantifying the prevalence, severity, and cost associated with patient motion during clinical MR examinations. J Am Coll Radiol 12:689\u2013695. https:\/\/doi.org\/10.1016\/j.jacr.2015.03.007","journal-title":"J Am Coll Radiol"},{"key":"11670_CR7","doi-asserted-by":"publisher","first-page":"e0278668","DOI":"10.1371\/journal.pone.0278668","volume":"18","author":"L Cui","year":"2023","unstructured":"Cui L, Song Y, Wang Y et al (2023) Motion artifact reduction for magnetic resonance imaging with deep learning and k-space analysis. PLoS One 18:e0278668. https:\/\/doi.org\/10.1371\/journal.pone.0278668","journal-title":"PLoS One"},{"key":"11670_CR8","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1002\/mrm.27772","volume":"82","author":"PM Johnson","year":"2019","unstructured":"Johnson PM, Drangova M (2019) Conditional generative adversarial network for 3D rigid\u2010body motion correction in MRI. Magn Reson Med 82:901\u2013910. https:\/\/doi.org\/10.1002\/mrm.27772","journal-title":"Magn Reson Med"},{"key":"11670_CR9","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.yacr.2019.04.013","volume":"1","author":"F Liu","year":"2019","unstructured":"Liu F, Kijowski R (2019) Deep learning in musculoskeletal imaging. Adv Clin Radiol 1:83\u201394","journal-title":"Adv Clin Radiol"},{"key":"11670_CR10","doi-asserted-by":"crossref","unstructured":"Cuadra MB, Favre J, Omoumi P (2020) Quantification in musculoskeletal imaging using computational analysis and machine learning: segmentation and radiomics. Semin Musculoskelet Radiol 24:50\u201364","DOI":"10.1055\/s-0039-3400268"},{"key":"11670_CR11","doi-asserted-by":"crossref","unstructured":"Jeon JS, Kim YJ, Kim KG (2022) Automatic measurement algorithm of femoral\/tibial torsion on standardized CT slices. In: Proceedings of 2022 13th international conference on information and communication technology convergence (ICTC). IEEE, Jeju Island, pp 733\u2013735","DOI":"10.1109\/ICTC55196.2022.9952793"},{"key":"11670_CR12","doi-asserted-by":"crossref","unstructured":"Schmaranzer F, Movahhedi M, Singh M et al (2024) Computed tomography-based automated 3D measurement of femoral version: validation against standard 2D measurements in symptomatic patients. J Orthop Res 42:2237\u20132248","DOI":"10.1002\/jor.25865"},{"key":"11670_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02708-y","volume":"11","author":"J Schock","year":"2021","unstructured":"Schock J, Truhn D, N\u00fcrnberger D et al (2021) Artificial intelligence-based automatic assessment of lower limb torsion on MRI. Sci Rep 11:23244","journal-title":"Sci Rep"},{"key":"11670_CR14","doi-asserted-by":"publisher","first-page":"e293","DOI":"10.3928\/01477447-20130222-17","volume":"36","author":"L Ejnisman","year":"2013","unstructured":"Ejnisman L, Philippon MJ, Lertwanich P et al (2013) Relationship between femoral anteversion and findings in hips with femoroacetabular impingement. Orthopedics 36:e293\u2013e300","journal-title":"Orthopedics"},{"key":"11670_CR15","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.2106\/00004623-199912000-00014","volume":"81","author":"D T\u00f6nnis","year":"1999","unstructured":"T\u00f6nnis D, Heinecke A (1999) Acetabular and femoral anteversion: relationship with osteoarthritis of the hip. J Bone Joint Surg Am 81:1747\u20131770","journal-title":"J Bone Joint Surg Am"},{"key":"11670_CR16","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1148\/radiol.2020192723","volume":"296","author":"F Schmaranzer","year":"2020","unstructured":"Schmaranzer F, Kallini JR, Miller PE et al (2020) The effect of modality and landmark selection on MRI and CT femoral torsion angles. Radiology 296:381\u2013390","journal-title":"Radiology"},{"key":"11670_CR17","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.1007\/s00590-015-1694-2","volume":"25","author":"SH Basaran","year":"2015","unstructured":"Basaran SH, Ercin E, Bayrak A et al (2015) The measurement of tibial torsion by magnetic resonance imaging in children: the comparison of three different methods. Eur J Orthop Surg Traumatol 25:1327\u20131332","journal-title":"Eur J Orthop Surg Traumatol"},{"key":"11670_CR18","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/s00402-004-0729-7","volume":"124","author":"R Jaarsma","year":"2004","unstructured":"Jaarsma R, Bruggeman A, Pakvis D et al (2004) Computed tomography determined femoral torsion is not accurate. Arch Orthop Trauma Surg 124:552\u2013554","journal-title":"Arch Orthop Trauma Surg"},{"key":"11670_CR19","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s00256-011-1185-4","volume":"41","author":"E Liodakis","year":"2012","unstructured":"Liodakis E, Doxastaki I, Chu K et al (2012) Reliability of the assessment of lower limb torsion using computed tomography: analysis of five different techniques. Skelet Radiol 41:305\u2013311","journal-title":"Skelet Radiol"},{"key":"11670_CR20","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s00247-011-2206-0","volume":"42","author":"JK Koenig","year":"2012","unstructured":"Koenig JK, Pring ME, Dwek JR (2012) MR evaluation of femoral neck version and tibial torsion. Pediatr Radiol 42:113\u2013115. https:\/\/doi.org\/10.1007\/s00247-011-2206-0","journal-title":"Pediatr Radiol"},{"key":"11670_CR21","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1007\/s00256-022-04085-7","volume":"51","author":"A Kohli","year":"2022","unstructured":"Kohli A, Pilkinton DT, Xi Y et al (2022) Image quality improvement and motion degradation reduction in shoulder MR imaging: comparison of BLADE and rectilinear techniques at 3-Tesla scanning. Skelet Radiol 51:2291\u20132297","journal-title":"Skelet Radiol"},{"key":"11670_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 PF, Kohl SA et al (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203\u2013211","journal-title":"Nat Methods"},{"key":"11670_CR23","unstructured":"Isensee F, Jaeger PF, Kohl SA et al (2024) nnU-Net source code. GitHub https:\/\/github.com\/MIC-DKFZ\/nnUNet. Accessed 16 Sep 2024"},{"key":"11670_CR24","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1007\/s00330-006-0470-4","volume":"17","author":"A Stadler","year":"2007","unstructured":"Stadler A, Schima W, Ba-Ssalamah A et al (2007) Artifacts in body MR imaging: their appearance and how to eliminate them. Eur Radiol 17:1242\u20131255","journal-title":"Eur Radiol"},{"key":"11670_CR25","doi-asserted-by":"publisher","first-page":"106236","DOI":"10.1016\/j.cmpb.2021.106236","volume":"208","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda F, Sparks R, Ourselin S (2021) TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput Methods Prog Biomed 208:106236. https:\/\/doi.org\/10.1016\/j.cmpb.2021.106236","journal-title":"Comput Methods Prog Biomed"},{"key":"11670_CR26","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS et al (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu MR et al (eds) Medical image computing and computer-assisted intervention (MICCAI) 2016. Springer, Cham, pp 424\u2013432","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"11670_CR27","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s11517-006-0104-7","volume":"44","author":"YS Lee","year":"2006","unstructured":"Lee YS, Oh SH, Seon JK et al (2006) 3D femoral neck anteversion measurements based on the posterior femoral plane in ORTHODOC\u00ae system. Med Biol Eng Comput 44:895\u2013906","journal-title":"Med Biol Eng Comput"},{"key":"11670_CR28","doi-asserted-by":"crossref","unstructured":"Strecker W, Keppler P, Kinzl L (eds) (1997) Posttraumatische beindeformit\u00e4ten. Springer, Heidelberg, pp 3\u20136","DOI":"10.1007\/978-3-642-60727-1_1"},{"key":"11670_CR29","unstructured":"Johnson HJ, McCormick MM, Ib\u00e1\u00f1ez L et al (2019) The ITK Software Guide, Book 2: Design and Functionality, Fourth Edition, Insight Toolkit. Available via https:\/\/itk.org\/ITKSoftwareGuide\/html\/Book2\/ITKSoftwareGuide-Book2ch3.html. Accessed 16 Sep 2024"},{"key":"11670_CR30","doi-asserted-by":"publisher","first-page":"103767","DOI":"10.1016\/j.compbiomed.2020.103767","volume":"121","author":"S Noguchi","year":"2020","unstructured":"Noguchi S, Nishio M, Yakami M et al (2020) Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques. Comput Biol Med 121:103767. https:\/\/doi.org\/10.1016\/j.compbiomed.2020.103767","journal-title":"Comput Biol Med"},{"key":"11670_CR31","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/1754-9485.13261","volume":"65","author":"P Chlap","year":"2021","unstructured":"Chlap P, Min H, Vandenberg N et al (2021) A review of medical image data augmentation techniques for deep learning applications. J Med Imag Rad Onc 65:545\u2013563. https:\/\/doi.org\/10.1111\/1754-9485.13261","journal-title":"J Med Imag Rad Onc"},{"key":"11670_CR32","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1109\/TMI.2020.2973595","volume":"39","author":"L Zhang","year":"2020","unstructured":"Zhang L, Wang X, Yang D et al (2020) Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans Med Imaging 39:2531\u20132540. https:\/\/doi.org\/10.1109\/TMI.2020.2973595","journal-title":"IEEE Trans Med Imaging"},{"key":"11670_CR33","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1587\/transinf.2022DLP0066","volume":"E106.D","author":"H Nozaka","year":"2023","unstructured":"Nozaka H, Kamata K, Yamagata K (2023) The effectiveness of data augmentation for mature white blood cell image classification in deep learning\u2014selection of an optimal technique for hematological morphology recognition. IEICE Trans Inf Syst E106.D:707\u2013714. https:\/\/doi.org\/10.1587\/transinf.2022DLP0066","journal-title":"IEICE Trans Inf Syst"},{"key":"11670_CR34","unstructured":"Schock J, Baumgartner M, Weninger L (2022) PhoenixDL\/rising. GitHub https:\/\/github.com\/PhoenixDL\/rising. Accessed 4 Feb 2025"},{"key":"11670_CR35","unstructured":"Isensee F, Baumgartner M, Kovacs B (2024) batchgeneratorsv2. GitHub https:\/\/github.com\/MIC-DKFZ\/batchgeneratorsv2. Accessed 4 Feb 2025"},{"key":"11670_CR36","doi-asserted-by":"crossref","unstructured":"Mathai TS, Wang Y, Cross N (2021) Assessing lesion segmentation bias of neural networks on motion corrupted brain MRI. In: Crimi A, Bakas S (eds) Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer, Cham, pp 143\u2013156","DOI":"10.1007\/978-3-030-72084-1_14"},{"key":"11670_CR37","doi-asserted-by":"publisher","first-page":"488","DOI":"10.3390\/a16100488","volume":"16","author":"G Mosquera-Rojas","year":"2023","unstructured":"Mosquera-Rojas G, Ouadah C, Hadadi A et al (2023) Automatic myocardium segmentation in delayed-enhancement MRI with pathology-specific data augmentation and deep learning architectures. Algorithms 16:488. https:\/\/doi.org\/10.3390\/a16100488","journal-title":"Algorithms"},{"key":"11670_CR38","doi-asserted-by":"crossref","unstructured":"Arega TW, Legrand F, Bricq S, Meriaudeau F (2021) Using MRI-specific data augmentation to enhance the segmentation of right ventricle in multi-disease, multi-center and multi-view cardiac MRI. In: International workshop on statistical atlases and computational models of the heart. Springer, Cham, pp 250\u2013258","DOI":"10.1007\/978-3-030-93722-5_27"},{"key":"11670_CR39","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.3390\/electronics13101870","volume":"13","author":"R Huysentruyt","year":"2024","unstructured":"Huysentruyt R, Van Den Borre I, Lazendi\u0107 S et al (2024) Sample size effect on musculoskeletal segmentation: how low can we go? Electronics 13:1870. https:\/\/doi.org\/10.3390\/electronics13101870","journal-title":"Electronics"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11670-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-11670-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11670-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:02:23Z","timestamp":1761627743000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-11670-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,17]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["11670"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-11670-6","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,17]]},"assertion":[{"value":"14 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Simon Westfechtel.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"D.T. received honoraria for lectures by Bayer, GE, and Philips and holds shares in StratifAI GmbH, Germany, and in Synagen GmbH, Germany, neither of whom have supported or influenced this study. All ethical standards have been strictly adhered to.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"One of the authors has significant statistical expertise.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects in this study. Written informed consent was waived for all patients by the Institutional Review Board.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Some study subjects or cohorts have been previously reported in Schock et al [\n                      \n                      ].","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}