{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:00:57Z","timestamp":1784228457689,"version":"3.55.0"},"reference-count":39,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12126610"],"award-info":[{"award-number":["12126610"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81971691"],"award-info":[{"award-number":["81971691"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81801809"],"award-info":[{"award-number":["81801809"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81830052"],"award-info":[{"award-number":["81830052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81827802"],"award-info":[{"award-number":["81827802"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"publisher","award":["20190302108GX"],"award-info":[{"award-number":["20190302108GX"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>The Breast Imaging\u2010Reporting and Data System (BI\u2010RADS) for ultrasound imaging provides a widely used reporting schema for breast imaging. Previous studies have shown that in ultrasound imaging, 90% of BI\u2010RADS 4A tumors are benign lesions after biopsies. Unnecessary biopsy procedures can be avoided by accurate classification of BI\u2010RADS 4A tumors. However, the classification task is challenging and has not been fully investigated by existing studies. For benign and malignant tumors of BI\u2010RADS 4A, the appearances of intra\u2010class tumors are highly variable, the characteristics of inter\u2010class tumors is overall\u2010similar. Discriminative features need to be found to improve classification accuracy of BI\u2010RADS 4A tumors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this study, we designed the network using the clinical features of BI\u2010RADS 4A tumors to improve the discrimination ability of network. The boundary information is embedded into the input of the network using the uncertainty. A fine\u2010grained data augmentation method is used to find discriminative features in tumor information embedded with boundary information. Two mathematical methods, voting\u2010based and variance\u2010based, are used to define the uncertainty of boundary, and the differences of these two definitions are compared in a classification network.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The dataset we used to evaluate our method had 1155 2D grayscale images. Each image represented a unique BI\u2010RADS 4A tumor. Among them, 248 tumors were proven to be malignant by biopsy, and the remaining 907 were benign. A weakly supervised data augmentation network (WS\u2010DAN) was used as the backbone classification network, which showed competitive performance in finding discriminative features. Using the auxiliary input of the uncertain boundaries defined by the voting method, the area under the curve (AUC) value of our method was 0.8347 (sensitivity\u00a0=\u00a00.7774, specificity\u00a0=\u00a00.7459). The AUC value of the variance\u2010based uncertainty was 0.7789. The voting\u2010based uncertainty was higher than the baseline (AUC\u00a0=\u00a00.803), which only inputs the original image. Compared with the classic classification network, our method had a significant effect improvement (<jats:italic>p<\/jats:italic>\u00a0&lt;\u00a00.01).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Using the uncertain boundaries defined by the voting methods as auxiliary information, we obtained a better performance in the classification of BI\u2010RADS 4A ultrasound images, while variance\u2010based uncertain boundaries had no effect on improving classification performance. Additionally, fine\u2010grained network helped find discriminative features comparing with the commonly used classification networks.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15590","type":"journal-article","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T01:39:35Z","timestamp":1646789975000},"page":"3314-3324","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["The uncertainty of boundary can improve the classification accuracy of BI\u2010RADS 4A ultrasound image"],"prefix":"10.1002","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0891-7828","authenticated-orcid":false,"given":"Huayu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering Sun Yat\u2010Sen University  Guangzhou P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3552-5774","authenticated-orcid":false,"given":"Yixin","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Sun Yat\u2010Sen University Cancer Center, State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine  Guangzhou P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Sun Yat\u2010Sen University  Guangzhou P.R. China"},{"name":"Guangdong Province Key Laboratory of Computational Science Sun Yat\u2010Sen University  Guangzhou P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2096-8126","authenticated-orcid":false,"given":"Jianhua","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Sun Yat\u2010Sen University Cancer Center, State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine  Guangzhou P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongze","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Sun Yat\u2010Sen University  Guangzhou P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21492"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17071572"},{"key":"e_1_2_8_4_1","volume-title":"ACR BI\u2010RADS Atlas: Breast Imaging Reporting and Data System; Mammography, Ultrasound, Magnetic Resonance Imaging, Follow\u2010up and Outcome Monitoring, Data Dictionary","author":"American College of Radiology","year":"2013"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.388"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010020\u201007413\u2010z"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-013-2576-0"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2018.12.008"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-014-3109-1"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2015.11.016"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12713"},{"key":"e_1_2_8_12_1","first-page":"200","volume-title":"Advances in Multimedia Information Processing \u2013 PCM","author":"Xie X"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101819"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen\u20102019\u2010035757"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10549\u2010018\u201005072\u20100"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105361"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"XuJ YangY&YangPHybrid label noise correction algorithm for medical auxiliary diagnosis. In: 2020 IEEE 18th International Conference on Industrial Informatics (INDIN). Vol 1. IEEE; 2020:567\u2010572.","DOI":"10.1109\/INDIN45582.2020.9442246"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.7150\/jca.51302"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2017.01.001"},{"issue":"1","key":"e_1_2_8_20_1","first-page":"209","article-title":"Thyroid nodules: risk stratification for malignancy with ultrasound and guided biopsy","volume":"11","author":"Anil G","year":"2011","journal-title":"Cancer Imaging"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896409"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101555"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"TomasiC ManduchiR.Bilateral filtering for gray and color images. In:Sixth International Conference on Computer Vision(IEEE Cat. No. 98CH36271). IEEE;1998:839\u2010846.https:\/\/doi.org\/10.1109\/ICCV.1998.710815","DOI":"10.1109\/ICCV.1998.710815"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0734\u2010189X(87)80186\u2010X"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"ComaniciuD MeerP.Mean shift analysis and applications. In:Proceedings of the Seventh IEEE International Conference on Computer Vision. Vol 2. IEEE;1999:1197\u20101203.https:\/\/doi.org\/10.1109\/ICCV.1999.790416","DOI":"10.1109\/ICCV.1999.790416"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab652b"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"Milletari NavabN&AhmadiSF . V\u2010Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE; 2016:565\u2010571.https:\/\/doi.org\/10.1109\/3DV.2016.79","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"FuJ ZhengH MeiT.Look closer to see better: recurrent attention convolutional neural network for fine\u2010grained image recognition. In:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2017:4476\u20104484.https:\/\/doi.org\/10.1109\/CVPR.2017.476","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_2_8_30_1","article-title":"See better before looking closer: weakly supervised data augmentation network for fine\u2010grained visual classification","author":"Hu T","year":"2019","journal-title":"ArXiv Preprint ArXiv190109891"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13361"},{"key":"e_1_2_8_32_1","doi-asserted-by":"crossref","unstructured":"SzegedyC VanhouckeV IoffeS ShlensJ WojnaZ.Rethinking the inception architecture for computer vision. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_8_33_1","article-title":"Very deep convolutional networks for large\u2010scale image recognition","author":"Simonyan K","year":"2014","journal-title":"ArXiv Preprint ArXiv14091556"},{"key":"e_1_2_8_34_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE;2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_35_1","doi-asserted-by":"crossref","unstructured":"XieS GirshickR Doll\u00e1rP TuZ HeK.Aggregated residual transformations for deep neural networks. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE;2017:1492\u20101500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"e_1_2_8_37_1","unstructured":"DiederikPD&BaJAdam: a method for stochastic optimization. ArXiv Preprint ArXiv14126980. 2017."},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2019.08.016"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2018.09.002"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2015.08.010"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15590","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15590","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T14:56:37Z","timestamp":1692456997000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,15]]},"references-count":39,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10.1002\/mp.15590"],"URL":"https:\/\/doi.org\/10.1002\/mp.15590","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,15]]},"assertion":[{"value":"2021-07-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}