{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:33:53Z","timestamp":1791506033484,"version":"4.3.4"},"reference-count":48,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T00:00:00Z","timestamp":1627516800000},"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":["61971213"],"award-info":[{"award-number":["61971213"]}],"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":["61671230"],"award-info":[{"award-number":["61671230"]}],"id":[{"id":"10.13039\/501100001809","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":[[2021,8]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Breast ultrasound (BUS) image segmentation plays a crucial role in computer\u2010aided diagnosis systems for BUS examination, which are useful for improved accuracy of breast cancer diagnosis. However, such performance remains a challenging task owing to the poor image quality and large variations in the sizes, shapes, and locations of breast lesions. In this paper, we propose a new convolutional neural network with coarse\u2010to\u2010fine feature fusion to address the aforementioned challenges.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The proposed fusion network consists of an encoder path, a decoder path, and a core fusion stream path (FSP). The encoder path is used to capture the context information, and the decoder path is used for localization prediction. The FSP is designed to generate beneficial aggregate feature representations (i.e., various\u2010sized lesion features, aggregated coarse\u2010to\u2010fine information, and high\u2010resolution edge characteristics) from the encoder and decoder paths, which are eventually used for accurate breast lesion segmentation. To better retain the boundary information and alleviate the effect of image noise, we input the superpixel image along with the original image to the fusion network. Furthermore, a weighted\u2010balanced loss function was designed to address the problem of lesion regions having different sizes. We then conducted exhaustive experiments on three public BUS datasets to evaluate the proposed network.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed method outperformed state\u2010of\u2010the\u2010art (SOTA) segmentation methods on the three public BUS datasets, with average dice similarity coefficients of 84.71(\u00b11.07), 83.76(\u00b10.83), and 86.52(\u00b11.52), average intersection\u2010over\u2010union values of 76.34(\u00b11.50), 75.70(\u00b10.98), and 77.86(\u00b12.07), average sensitivities of 86.66(\u00b11.82), 85.21(\u00b11.98), and 87.21(\u00b12.51), average specificities of 97.92(\u00b10.46), 98.57(\u00b10.19), and 99.42(\u00b10.21), and average accuracies of 95.89(\u00b10.57), 97.17(\u00b10.3), and 98.51(\u00b10.3).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The proposed fusion network could effectively segment lesions from BUS images, thereby presenting a new feature fusion strategy to handle challenging task of segmentation, while outperforming the SOTA segmentation methods. The code is publicly available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/mniwk\/CF2-NET\">https:\/\/github.com\/mniwk\/CF2\u2010NET<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15006","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T12:53:46Z","timestamp":1622811226000},"page":"4262-4278","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Breast ultrasound image segmentation: A coarse\u2010to\u2010fine fusion convolutional neural network"],"prefix":"10.1002","volume":"48","author":[{"given":"Ke","family":"Wang","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujun","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengzhou","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianjin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyuan","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Southern Medical University Guangzhou Guangdong 510515 China"},{"name":"Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou Guangdong 510515 China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,7,29]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21583"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2731873"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101753"},{"key":"e_1_2_9_5_1","unstructured":"XianM ZhangY ChengH\u2010D et al.A benchmark for breast ultrasound image segmentation (BUSIS). arXiv preprint arXiv:1801.03182v1;2018."},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.02.012"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2017.01.021"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.12.012"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20320-6_64"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.5121\/sipij.2014.5301"},{"key":"e_1_2_9_11_1","unstructured":"XingJ LiZ WangB et al.Automated segmentation of lesions in ultrasound using semi\u2010pixel\u2010wise cycle generative adversarial nets arXiv preprint arXiv:1905.01902;2019."},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-016-1513-1"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.07.010"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.1429239"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1076-6332(03)00719-0"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4747271"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.7863\/ultra.32.9.1659"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.05.092"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2013.10.003"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"XianM HuangJ ZhangY TangX.Multiple\u2010domain knowledge based MRF model for tumor segmentation in breast ultrasound images. In 2012 19th IEEE International Conference on Image Processing IEEE;2012:2021\u20132024.","DOI":"10.1109\/ICIP.2012.6467286"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2015.01.012"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101657"},{"key":"e_1_2_9_23_1","first-page":"1","article-title":"A survey of ultrasonography breast cancer image segmentation techniques","volume":"9","author":"Saeed JN","year":"2020","journal-title":"Inf Study"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"HuangK ChengH\u2010D ZhangY ZhangB XingP NingC.Medical knowledge constrained semantic breast ultrasound image segmentation. In 2018 24th International Conference on Pattern Recognition (ICPR)IEEE;2018:1193\u20131198.","DOI":"10.1109\/ICPR.2018.8545272"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"AlmajalidR ShanJ DuY ZhangM.Development of a deep\u2010learning\u2010based method for breast ultrasound image segmentation. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)IEEE;2018:1103\u20131108.","DOI":"10.1109\/ICMLA.2018.00179"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0195816"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2936500"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT U\u2010net: Convolutional networks for biomedical image segsmentation. In International Conference on Medical Image Computing and Computer Assisted Intervention Springer;2015:234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1166\/jmihi.2019.2828"},{"key":"e_1_2_9_30_1","unstructured":"SinghVK RashwanHA Abdel\u2010NasserM et al.An efficient solution for breast tumor segmentation and classification in ultrasound images using deep adversarial learning arXiv preprint arXiv:1907.00887;2019."},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2020.06.015"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221535"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_9_35_1","unstructured":"IglovikovV ShvetsA Ternausnet: U\u2010net with vgg11 encoder pre\u2010trained on imagenet for image segmentation arXiv preprint arXiv:1801.05746;2018."},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"LiC SunH LiuZ WangM ZhengH WangS.Learning cross\u2010modal deep representations for multi\u2010Modal MR image segmentation. In International Conference on Medical Image Computing and Computer\u2010Assisted Intervention Springer;2019:57\u201365.","DOI":"10.1007\/978-3-030-32245-8_7"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"XiaoX ZhaoJ QiangY et al.Radiomics\u2010guided GAN for segmentation of liver tumor without contrast agents. In International Conference on Medical Image Computing and Computer\u2010Assisted Intervention Springer;2019:237\u2013245.","DOI":"10.1007\/978-3-030-32245-8_27"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_9_39_1","unstructured":"OktayO.Attention u\u2010net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999;2018."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2903562"},{"key":"e_1_2_9_41_1","doi-asserted-by":"crossref","unstructured":"LinT\u2010Y DollarP GirshickR HeK HariharanB BelongieS.Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;2017.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"ChenL\u2010C ZhuY PapandreouG SchroffF AdamH.Encoder\u2010decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision;2018:801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"BianC LeeR ChouY\u2010H ChengJ\u2010Z.Boundary regularized convolutional neural network for layer parsing of breast anatomy in automated whole breast ultrasound. In International Conference on Medical Image Computing and Computer\u2010Assisted Intervention Springer;2017:259\u2013266.","DOI":"10.1007\/978-3-319-66179-7_30"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Delving deep into rectifiers: Surpassing human\u2010level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision;2015:1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.6.1.011007"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102027"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.105275"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14470"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15006","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15006","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T13:09:16Z","timestamp":1693141756000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15006"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,29]]},"references-count":48,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["10.1002\/mp.15006"],"URL":"https:\/\/doi.org\/10.1002\/mp.15006","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,29]]},"assertion":[{"value":"2020-12-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}