{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T22:13:12Z","timestamp":1790806392610,"version":"4.1.0"},"reference-count":48,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>BUS\u2010Set is a reproducible benchmark for breast ultrasound (BUS) lesion segmentation, comprising of publicly available images with the aim of improving future comparisons between machine learning models within the field of\u00a0BUS.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>Four publicly available datasets were compiled creating an overall set of 1154 BUS images, from five different scanner types. Full dataset details have been provided, which include clinical labels and detailed annotations. Furthermore, nine state\u2010of\u2010the\u2010art deep learning architectures were selected to form the initial benchmark segmentation result, tested using five\u2010fold cross\u2010validation and MANOVA\/ANOVA with Tukey statistical significance test with a threshold of 0.01. Additional evaluation of these architectures was conducted, exploring possible training bias, and lesion size and type\u00a0effects.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Of the nine state\u2010of\u2010the\u2010art benchmarked architectures, Mask R\u2010CNN obtained the highest overall results, with the following mean metric scores: Dice score of 0.851, intersection over union of 0.786 and pixel accuracy of 0.975. MANOVA\/ANOVA and Tukey test results showed Mask R\u2010CNN to be statistically significant better compared to all other benchmarked models with a <jats:italic>p<\/jats:italic>\u2010value\u00a0&gt;0.01. Moreover, Mask R\u2010CNN achieved the highest mean Dice score of 0.839 on an additional 16 image dataset, that contained multiple lesions per image. Further analysis on regions of interest was conducted, assessing Hamming distance, depth\u2010to\u2010width ratio (DWR), circularity, and elongation, which showed that the Mask R\u2010CNN's segmentations maintained the most morphological features with correlation coefficients of 0.888, 0.532, 0.876 for DWR, circularity, and elongation, respectively. Based on the correlation coefficients, statistical test indicated that Mask R\u2010CNN was only significantly different to\u00a0Sk\u2010U\u2010Net.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>BUS\u2010Set is a fully reproducible benchmark for BUS lesion segmentation obtained through the use of public datasets and GitHub. Of the state\u2010of\u2010the\u2010art convolution neural network (CNN)\u2010based architectures, Mask R\u2010CNN achieved the highest performance overall, further analysis indicated that a training bias may have occurred due to the lesion size variation in the dataset. All dataset and architecture details are available at GitHub: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/corcor27\/BUS-Set\">https:\/\/github.com\/corcor27\/BUS\u2010Set<\/jats:ext-link>, which allows for a fully reproducible\u00a0benchmark.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16287","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T11:14:07Z","timestamp":1676546047000},"page":"3223-3243","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["BUS\u2010Set: A benchmark for quantitative evaluation of breast ultrasound segmentation networks with public datasets"],"prefix":"10.1002","volume":"50","author":[{"given":"Cory","family":"Thomas","sequence":"first","affiliation":[{"name":"Department of Computer Science Aberystwyth University Aberystwyth UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal","family":"Byra","sequence":"additional","affiliation":[{"name":"Institute of Fundamental Technological Research Polish Academy of Sciences Warsaw Poland"},{"name":"Department of Radiology University of California San Diego California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Marti","sequence":"additional","affiliation":[{"name":"Computer Vision and Robotics Institute University of Girona Girona Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moi Hoon","family":"Yap","sequence":"additional","affiliation":[{"name":"Department of Computing and Mathematics Manchester Metropolitan University Manchester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reyer","family":"Zwiggelaar","sequence":"additional","affiliation":[{"name":"Department of Computer Science Aberystwyth University Aberystwyth UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"e_1_2_9_2_1","unstructured":"Breast Cancer Now. Facts and statistics2020.\u00a0Last accessed December 2020.\u00a0https:\/\/breastcancernow.org\/about\u2010us\/media\/facts\u2010statistics"},{"key":"e_1_2_9_3_1","unstructured":"Breast Cancer UK. Survival for breast cancer | Breast Cancer | Cancer Research UK. December2020.\u00a0Last\u00a0accessed\u00a0December 2020.\u00a0https:\/\/www.cancerresearchuk.org\/about\u2010cancer\/breast\u2010cancer\/survival"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2244601"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/47\/8\/301"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.877968"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/rpd\/nch552"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929365"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12538"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.01.032"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2731873"},{"issue":"1","key":"e_1_2_9_12_1","article-title":"Breast ultrasound lesions recognition: end\u2010to\u2010end deep learning approaches","volume":"6","author":"Yap MH","year":"2018","journal-title":"J Med Imaging"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10040729"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13268"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000015200"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102027"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104036"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"ShareefB XianM VakanskiA.Stan: small tumor\u2010aware network for breast ultrasound image segmentation. In:2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).2020:1\u20135.","DOI":"10.1109\/ISBI45749.2020.9098691"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221535"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14470"},{"key":"e_1_2_9_22_1","unstructured":"ZhuX HuH WangH et\u00a0al.Region aware transformer for automatic breast ultrasound tumor segmentation. In: Medical Imaging with Deep Learning.2022.https:\/\/openreview.net\/forum?id=2bVDHzy7xwV"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.15680\/IJIRCCE.2014.0212024"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"MaityA PattanaikA SagnikaS PaniS.A comparative study on approaches to speckle noise reduction in images.In: 2015 International Conference on Computational Intelligence and Networks.2015:148\u2010155.","DOI":"10.1109\/CINE.2015.36"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10851\u2010007\u20100039\u20100"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"VuolaAO AkramSU KannalaJ.Mask\u2010RCNN and U\u2010Net ensembled for nuclei segmentation. In:2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).2019:208\u2010212.","DOI":"10.1109\/ISBI.2019.8759574"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"WangK KhanN HighnamR.Automated segmentation of breast arterial calcifications from digital mammography.In: 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ).","DOI":"10.1109\/IVCNZ48456.2019.8960956"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"JohnsonJW.Adapting mask\u2010rcnn for automatic nucleus segmentation.Proceedings of the 2019 Computer Vision Conference Vol.2.arXiv preprint arXiv:1805.005002018.","DOI":"10.1007\/978-3-030-17798-0_32"},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"HeK GkioxariG Doll\u00e1rP GirshickR \u201cMask R\u2010CNN \u201d2017 IEEE International Conference on Computer Vision (ICCV) Venice Italy 2017 pp.2980\u20132988. doi:10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_9_32_1","article-title":"Attention U\u2010Net: learning where to look for the pancreas","author":"Oktay O","year":"2018","journal-title":"Med Imaging Deep Learn"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914873"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_9_35_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et\u00a0al.An image is worth 16x16 words: transformers for image recognitionat scale.9th International Conference on Learning Representations ICLR 2021 Virtual Event Austria May 3\u20147 2021. OpenReview.net 2021.https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_2_9_36_1","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen J","year":"2021","journal-title":"CoRR"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation. Computer Vision and Pattern Recognition (cs.CV).2014. doi:10.48550\/arxiv.1411.4038","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_39_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Las Vegas NV USA 2016 pp.770\u2010778. doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_40_1","unstructured":"RenS HeK GirshickR et\u00a0al.Faster R\u2010CNN: towards real\u2010time object detection with region proposal networks 2015 MIT Press Cambridge MA USA Proceedings of the 28th International Conference on Neural Information Processing Systems. Volume1 pages91\u201399 Montreal Canada NIPS'15."},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_42_1","first-page":"1061","article-title":"Hamming distance metric learning","volume":"25","author":"Norouzi M","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_43_1","volume-title":"Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment","author":"Yap MH","year":"2016"},{"key":"e_1_2_9_44_1","volume-title":"SPSS Survival Manual: A Step by Step Guide to Data Analysis Using IBM SPSS","author":"Pallant J","year":"2020"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101796"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-015-0031-x"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07884-8"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2315206"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16287","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.16287","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T11:40:55Z","timestamp":1692531655000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10.1002\/mp.16287"],"URL":"https:\/\/doi.org\/10.1002\/mp.16287","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]},"assertion":[{"value":"2022-03-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}