{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:59:37Z","timestamp":1792000777504,"version":"4.4.0"},"reference-count":50,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"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":["61871437"],"award-info":[{"award-number":["61871437"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2019CFA022"],"award-info":[{"award-number":["2019CFA022"]}],"id":[{"id":"10.13039\/501100003819","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":[[2022,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Skull fracture, as a common traumatic brain injury, can lead to multiple complications including bleeding, leaking of cerebrospinal fluid, infection, and seizures. Automatic skull fracture detection (SFD) is of great importance, especially in emergency\u00a0medicine.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Existing algorithms for SFD, developed based on hand\u2010crafted features, suffer from low detection accuracy due to poor generalizability to unseen samples. Deploying deep detectors designed for natural images like Faster Region\u2010based Convolutional Neural Network (R\u2010CNN) for SFD can be helpful but are of high redundancy and with nonnegligible false detections due to the cranial suture and skull base interference. Therefore, we, for the first time, propose an anchor\u2010efficient anti\u2010interference deep learning framework named Fracture R\u2010CNN for accurate SFD with low computational\u00a0cost.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The proposed Fracture R\u2010CNN is developed by incorporating the prior knowledge utilized in clinical diagnosis into the original Faster R\u2010CNN. Specifically, based on the distributions of skull fractures, we first propose an adaptive anchoring region proposal network (AA\u2010RPN) to generate proposals for diverse\u2010scale fractures with low computational complexity. Then, based on the prior knowledge that cranial sutures exist in the junctions of bones and usually contain sclerotic margins, we design an anti\u2010interference head (A\u2010Head) network to eliminate the cranial suture interference for better SFD detection. In addition, to further enhance the anti\u2010interference ability of the proposed A\u2010Head, a difficulty\u2010balanced weighted loss function is proposed to emphasize more on distinguishing the interference areas from the skull base and the cranial sutures during\u00a0training.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experimental results demonstrate that the proposed Fracture R\u2010CNN outperforms the current state\u2010of\u2010the\u2010art (SOTA) deep detectors for SFD with a higher recall and fewer false detections. Compared to Faster R\u2010CNN, the proposed Fracture R\u2010CNN improves the average precision (AP) by 11.74% and the free\u2010response receiver operating characteristic (FROC) score by 11.08%. Through validating on various backbones, we further demonstrate the architecture independence of Fracture R\u2010CNN, making it extendable to other detection\u00a0applications.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>As the customized deep learning\u2013based framework for SFD, Fracture R\u2010CNN can effectively overcome the unique challenges in SFD with less computational cost, leading to a better detection performance compared to the SOTA deep detectors. Moreover, we believe the prior knowledge explored for Fracture R\u2010CNN would shed new light on future deep learning approaches for SFD.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15809","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T14:29:17Z","timestamp":1655476157000},"page":"7179-7192","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Fracture R\u2010CNN: An anchor\u2010efficient anti\u2010interference framework for skull fracture detection in CT images"],"prefix":"10.1002","volume":"49","author":[{"given":"Xian","family":"Lin","sequence":"first","affiliation":[{"name":"School of Electronic Information and Communication Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zengqiang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communication Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Kuang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communication Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianbo","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Radiology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communication Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,7,10]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.18535\/jmscr\/v7i1.166"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocn.2015.10.012"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.3171\/jns.1990.72.2.0189"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"ZakiWMDW FauziMFA BesarR.Automated method of fracture detection in CT brain images. In:International Conference on Intelligent System and Knowledge Engineering. IEEE; 2008 1156\u20101160.","DOI":"10.1109\/ISKE.2008.4731105"},{"key":"e_1_2_9_6_1","doi-asserted-by":"crossref","unstructured":"ZakiWMDW FauziMFA BesarR.A new approach of skull fracture detection in CT brain images. In:International Visual Informatics Conference.Springer;2009 156\u2010167.","DOI":"10.1007\/978-3-642-05036-7_16"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","unstructured":"AbubackerNF AzmanA AzrifahM DoraisamyS.An approach for an automatic fracture detection of skull dicom images based on neighboring pixels. In:International Conference on Intellient Systems Design and Applications.IEEE;2013 177\u2010181.","DOI":"10.1109\/ISDA.2013.6920731"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"YamadaA TeramotoA OtsukaT KudoK AnnoH FujitaH.Preliminary study on the automated skull fracture detection in CT images using black\u2010hat transform. In:Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE;2016 6437\u20106440.","DOI":"10.1109\/EMBC.2016.7592202"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1166\/jmihi.2018.2410"},{"key":"e_1_2_9_10_1","first-page":"91","article-title":"Faster R\u2010CNN: towards real\u2010time object detection with region proposal networks","author":"Ren S","year":"2015","journal-title":"Adv Neural Inf Proc Syst"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2021.687931"},{"issue":"5","key":"e_1_2_9_12_1","first-page":"1785","article-title":"Automated skull damage detection from assembled skull model using computer vision and machine learning","volume":"13","author":"Mangrulkar A","year":"2021","journal-title":"Int J Inf Technol"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"LiuG WuQ YuanG WuX.Skull fracture detection method based on improved feature pyramid network. In:2021 International Conference on Electronic Information Engineering and Computer Science (EIECS). IEEE;2021 756\u2010762.","DOI":"10.1109\/EIECS53707.2021.9587992"},{"key":"e_1_2_9_14_1","first-page":"382","article-title":"Skull R\u2010CNN: a CNN\u2010based network for the skull fracture detection","author":"Kuang Z","year":"2020","journal-title":"Med Imaging Deep Learn"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"WangJ ChenK YangS LoyCC LinD.Region proposal by guided anchoring. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2019;2965\u20102974.","DOI":"10.1109\/CVPR.2019.00308"},{"key":"e_1_2_9_16_1","unstructured":"ZhangX WanF LiuC JiR YeQ.Free anchor: learning to match anchors for visual object detection. In: Advances in Neural Information Processing Systems (NeurIPS). MIT Press;2019 147\u2010155."},{"key":"e_1_2_9_17_1","unstructured":"RedmonJ FarhadiA.Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 2018.https:\/\/doi.org\/10.48550\/arXiv.1804.02767"},{"key":"e_1_2_9_18_1","unstructured":"BochkovskiyA WangCY LiaoHYM.Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 2020.https:\/\/doi.org\/10.48550\/2004.10934"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"LiuW AnguelovD ErhanD et\u00a0al.Ssd: Single shot multibox detector. In:European Conference on Computer Vision (ECCV). Springer;2016 21\u201037.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12846"},{"key":"e_1_2_9_21_1","doi-asserted-by":"crossref","unstructured":"CaiZ VasconcelosN.Cascade R\u2010CNN: delving into high quality object detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2018 6154\u20106162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14161"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14129"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180001"},{"key":"e_1_2_9_25_1","unstructured":"LawH TengY RussakovskyO DengJ.Cornernet\u2010lite: efficient keypoint based object detection. arXiv preprint arXiv:1904.08900 2019.https:\/\/doi.org\/10.48550\/arXiv.1904.08900"},{"key":"e_1_2_9_26_1","unstructured":"ZhouX WangD Kr\u00e4henb\u00fchlP.Objects as points. arXiv preprint arXiv:1904.07850 2019.https:\/\/doi.org\/10.48550\/arXiv.1904.07850"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"ZhouX ZhuoJ KrahenbuhlP.Bottom\u2010up object detection by grouping extreme and center points. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2019 850\u2010859.","DOI":"10.1109\/CVPR.2019.00094"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"DongZ LiG LiaoY WangF RenP QianC.Centripetalnet: pursuing high\u2010quality keypoint pairs for object detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE;2020 10519\u201010528.","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"TianZ ShenC ChenH HeT.Fcos: Fully convolutional one\u2010stage object detection. In:Proceedings of the IEEE International Conference on Computer Vision (ICCV). IEEE;2019 9627\u20109636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"LiuW LiaoS RenW HuW YuY.High\u2010level semantic feature detection: a new perspective for pedestrian detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2019 5187\u20105196.","DOI":"10.1109\/CVPR.2019.00533"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14648"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13945"},{"key":"e_1_2_9_34_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. arXiv preprint arXiv:1409.1556 2014.https:\/\/doi.org\/10.48550\/arXiv.1409.1556"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"SzegedyC LiuW JiaY et\u00a0al.Going deeper with convolutions. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2015 1\u20109.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"KaurT GandhiTK.Automated brain image classification based on VGG\u201016 and transfer learning. In:International Conference on Information Technology (ICIT). IEEE;2019 94\u201098.","DOI":"10.1109\/ICIT48102.2019.00023"},{"key":"e_1_2_9_37_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 (CVPR). IEEE;2016 770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2018 7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12399"},{"key":"e_1_2_9_40_1","unstructured":"GaoW ZhangX YangL LiuH.An improved Sobel edge detection. In:International Conference on Computer Science and Information Technology. IEEE;2010 67\u201071."},{"key":"e_1_2_9_41_1","unstructured":"MacQueenJ.Some methods for classification and analysis of multivariate observations.Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability1967;1(14):281\u2010297."},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"WangJ ZhangW CaoY et\u00a0al.Side\u2010aware boundary localization for more precise object detection. In:Proceedings of the European Conference on Computer Vision (ECCV). Springer;2020 403\u2010419.","DOI":"10.1007\/978-3-030-58548-8_24"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"HeK GkioxariG Doll\u00e1rP GirshickR.Mask R\u2010CNN. In:Proceedings of the IEEE International Conference on Computer Vision (ICCV). IEEE;2017 2961\u20102969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"LinTY GoyalP GirshickR Doll\u00e1rP.Focal loss for dense object detection. In:Proceedings of the IEEE International Conference on Computer Vision (ICCV). IEEE;2017 2980\u20102988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_45_1","doi-asserted-by":"crossref","unstructured":"TanM PangR LeQV.Efficientdet: scalable and efficient object detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2020 10781\u201010790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_9_46_1","doi-asserted-by":"crossref","unstructured":"RotheR GuillauminM Van GoolL.Non\u2010maximum suppression for object detection by passing messages between windows. In:Asian Conference on Computer Vision. Springer;2014 290\u2010306.","DOI":"10.1007\/978-3-319-16865-4_19"},{"key":"e_1_2_9_47_1","doi-asserted-by":"crossref","unstructured":"TianZ HeT ShenC YanY.Decoders matter for semantic segmentation: data\u2010dependent decoding enables flexible feature aggregation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2019 3126\u20103135.","DOI":"10.1109\/CVPR.2019.00324"},{"key":"e_1_2_9_48_1","doi-asserted-by":"crossref","unstructured":"WooS ParkJ LeeJY KweonIS.Cbam: Convolutional block attention module. In:Proceedings of the European Conference on Computer Vision (ECCV). Springer;2018 3\u201019.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_9_49_1","doi-asserted-by":"crossref","unstructured":"FanQ ZhuoW TangCK TaiYW.Few\u2010shot object detection with attention\u2010RPN and multi\u2010relation detector.In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;\u00a02020 4013\u20104022.","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"e_1_2_9_50_1","doi-asserted-by":"crossref","unstructured":"WangW ZhaoS ShenJ HoiSC BorjiA.Salient object detection with pyramid attention and salient edges.In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2019 1448\u20101457.","DOI":"10.1109\/CVPR.2019.00154"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103514"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15809","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15809","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T23:27:43Z","timestamp":1692487663000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":50,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["10.1002\/mp.15809"],"URL":"https:\/\/doi.org\/10.1002\/mp.15809","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2021-12-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-05-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}