{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:55:44Z","timestamp":1791190544065,"version":"4.1.0"},"reference-count":34,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100014434","name":"Narodowa Agencja Wymiany Akademickiej","doi-asserted-by":"publisher","award":["BPN\/PPO\/2023\/1\/00029\/U\/00001"],"award-info":[{"award-number":["BPN\/PPO\/2023\/1\/00029\/U\/00001"]}],"id":[{"id":"10.13039\/501100014434","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n \n Diffusion\u2010weighted imaging (DWI) can support lesion detection and characterization in breast MRI. Therefore, DWI is increasingly being incorporated into breast MRI protocols to address some of the shortcomings of routine clinical breast MRI. However, especially high\n b<\/jats:italic>\n value DWI can be prone to intensity artifacts that can affect diagnostic image assessment.\n <\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n \n To detect hyper\u2010 and hypointense artifacts on high\n b<\/jats:italic>\n value DWI (\n b<\/jats:italic>\n \u2009=\u20091500\u2009s\/mm\n 2<\/jats:sup>\n ) using deep learning, employing either a binary classification (artifact presence) or a multiclass classification (artifact intensity) approach on a slice\u2010wise dataset.\n <\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Retrospective.<\/jats:p>\n <\/jats:sec>\n \n Study Population<\/jats:title>\n 11,806 DWI slices were acquired from 156 examinations performed on female patients between 2022 and mid\u20102023. For both hyper\u2010 and hypointense artifact classification, the slices were split into test, validation, and holdout test set with 8164\/1806\/1836 and 8164\/1820\/1822 slices in these sets respectively.<\/jats:p>\n <\/jats:sec>\n \n Field Strength\/Sequence<\/jats:title>\n \n 3\u2009T spin\u2010echo planar diffusion\u2010weighted sequence with\n b<\/jats:italic>\n values: 50, 750, and 1500\u2009s\/mm\n 2<\/jats:sup>\n .\n <\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n Three convolutional neural network (CNN) architectures (DenseNet121, ResNet18, and SEResNet50) were trained for binary classification of hyper\u2010 and hypointense artifacts on slice\u2010wise labeled data. The best performing model (DenseNet121) was applied to an independent holdout test set and further trained separately for multiclass classification.<\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n Performance of the networks was evaluated using accuracy, precision, recall, and areas under the receiver operating characteristic curve (AUROC) and under the precision recall curve (AUPRC). Radiologist evaluated bounding box positions on a 5\u2010point Likert\u2010like scale across 150 slices for validation and 200 slices for the holdout test set, derived from the network's Grad\u2010CAM heatmaps.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n DenseNet121 achieved AUROCs of 0.91 and 0.95 for hyper\u2010 and hypointense artifact detection, respectively, and weighted AUROCs of 0.84 and 0.90 for multiclass classification on single\u2010slice high\n b<\/jats:italic>\n value diffusion\u2010weighted images, achieving mean scores of 3.52\u2009\u00b1\u20090.81 for hyperintense artifacts and 3.62\u2009\u00b1\u20090.65 for hypointense artifacts.\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n \n Hyper\u2010 and hypointense artifact detection in slice\u2010wise breast DWI MRI dataset (\n b<\/jats:italic>\n \u2009=\u20091500\u2009s\/mm\n 2<\/jats:sup>\n ) using CNNs, particularly DenseNet121, suggests potential reliability and requires further validation.\n <\/jats:p>\n <\/jats:sec>\n \n Evidence Level<\/jats:title>\n 3.<\/jats:p>\n <\/jats:sec>\n \n Technical Efficacy<\/jats:title>\n Stage 3.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.70572","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:34:28Z","timestamp":1791189268000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Slice\u2010Wise Quality Assessment of High\n b<\/i>\n Value Breast\n DWI<\/scp>\n via Deep Learning\u2010Based Artifact Detection"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9830-7496","authenticated-orcid":false,"given":"Ameya","family":"Markale","sequence":"first","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"},{"name":"Institute of Computer Science, Polish Academy of Science Warsaw Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4591-4354","authenticated-orcid":false,"given":"Luise","family":"Brock","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"},{"name":"Department of Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ihor","family":"Horishnyi","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6531-4049","authenticated-orcid":false,"given":"Dominika","family":"Skwierawska","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0974-3299","authenticated-orcid":false,"given":"Tri\u2010Thien","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"},{"name":"Pattern Recognition Lab, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominique","family":"Hadler","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannes","family":"Schreiter","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7479-693X","authenticated-orcid":false,"given":"Shirin","family":"Heidarikahkesh","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1866-860X","authenticated-orcid":false,"given":"Lorenz A.","family":"Kapsner","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"},{"name":"Medical Informatics, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Uder","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabine","family":"Ohlmeyer","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9269-5609","authenticated-orcid":false,"given":"Frederik B.","family":"Laun","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8450-3021","authenticated-orcid":false,"given":"Andrzej","family":"Liebert","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"},{"name":"Institute of Computer Science, Polish Academy of Science Warsaw Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Bickelhaupt","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Universit\u00e4tsklinikum Erlangen, Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg (FAU) Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"e_1_2_14_2_1","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s00330-024-10973-4","article-title":"Fat\u2010Signal Suppression in Breast Diffusion\u2010Weighted Imaging: The Good, the Bad, and the Ugly","volume":"35","author":"Le Bihan D.","year":"2025","journal-title":"European Radiology"},{"key":"e_1_2_14_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25479"},{"key":"e_1_2_14_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2024.01.005"},{"key":"e_1_2_14_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010023\u201037342\u20103"},{"key":"e_1_2_14_6_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015150425"},{"key":"e_1_2_14_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2012.03.002"},{"key":"e_1_2_14_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2461061298"},{"key":"e_1_2_14_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mric.2013.04.007"},{"key":"e_1_2_14_10_1","first-page":"85","volume-title":"Virtual Dynamic Contrast Enhanced Breast MRI Using 2D U\u2010Net Architectures","author":"Schreiter H.","year":"2025"},{"key":"e_1_2_14_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010025\u201011670\u20106"},{"key":"e_1_2_14_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010024\u201011142\u20103"},{"key":"e_1_2_14_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2019.02.008"},{"key":"e_1_2_14_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_76"},{"key":"e_1_2_14_15_1","unstructured":"K.O'sheaandR.Nash \u201cAn Introduction to Convolutional Neural Networks \u201d(2015) arXiv preprint arXiv:1511.08458."},{"key":"e_1_2_14_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13121996"},{"key":"e_1_2_14_17_1","doi-asserted-by":"publisher","DOI":"10.1097\/rli.0000000000000784"},{"key":"e_1_2_14_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26809"},{"key":"e_1_2_14_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.23689"},{"key":"e_1_2_14_20_1","doi-asserted-by":"crossref","unstructured":"G.Huang Z.Liu L.van derMaaten andK. Q.Weinberger \u201cDensely Connected Convolutional Networks \u201d(2017) Institute of Electrical Electronics Engineers 2261\u20132269.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_14_21_1","doi-asserted-by":"crossref","unstructured":"K.He X.Zhang S.Ren andJ.Sun \u201cProceedings of the IEEE Conference on Computer Vision and Pattern Recognition \u201d(2016) 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_14_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_14_23_1","unstructured":"S.Raschka \u201cModel Evaluation Model Selection and Algorithm Selection in Machine Learning \u201d(2018) arXiv preprint arXiv:1811.12808."},{"key":"e_1_2_14_24_1","unstructured":"T.M. Consortium \u201cProject MONAI \u201d(2020) https:\/\/doi.org\/10.5281\/zenodo.4323059."},{"key":"e_1_2_14_25_1","unstructured":"A.Paszke A.Tejani A.Lerer et\u00a0al. \u201cPytorch: An Imperative Style High\u2010Performance Deep Learning Library \u201d(2019) arXiv preprint arXiv:1912.01703."},{"key":"e_1_2_14_26_1","unstructured":"W.Falcon J.Borovec A.W\u00e4lchli et\u00a0al. \u201cPyTorchLightning\/Pytorch\u2010Lightning: 0.7. 6 Release \u201d(2020) Zenodo."},{"key":"e_1_2_14_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_14_28_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0026256"},{"key":"e_1_2_14_29_1","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_2_14_30_1","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000031214"},{"key":"e_1_2_14_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010022\u201008626\u20105"},{"key":"e_1_2_14_32_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.210021"},{"key":"e_1_2_14_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010026\u201012439\u20101"},{"key":"e_1_2_14_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_14_35_1","unstructured":"S.Ren K.He R.Girshick andJ.Sun \u201cFaster r\u2010Cnn: Towards Real\u2010Time Object Detection With Region Proposal Networks \u201d(2016) 1506.01497."}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70572","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.70572","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:34:31Z","timestamp":1791189271000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":34,"alternative-id":["10.1002\/jmri.70572"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70572","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"assertion":[{"value":"2026-04-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"jmri.70572"}}