{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:09:03Z","timestamp":1777705743372,"version":"3.51.4"},"reference-count":32,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2022,3,4]]},"abstract":"<jats:p>Accurate segmentation of fractures in coal rock CT images is important for the development of coalbed methane. However, due to the large variation of fracture scale and the similarity of gray values between weak fractures and the surrounding matrix, it remains a challenging task. And there is no published dataset of coal rock, which make the task even harder. In this paper, a novel adaptive multi-scale feature fusion method based on U-net (AMSFF-U-net) is proposed for fracture segmentation in coal rock CT images. Specifically, encoder and decoder path consist of residual blocks (ReBlock), respectively. The attention skip concatenation (ASC) module is proposed to capture more representative and distinguishing features by combining the high-level and low-level features of adjacent layers. The adaptive multi-scale feature fusion (AMSFF) module is presented to adaptively fuse different scale feature maps of encoder path; it can effectively capture rich multi-scale features. In response to the lack of coal rock fractures training data, we applied a set of comprehensive data augmentation operations to increase the diversity of training samples. These extensive experiments are conducted via seven state-of-the-art methods (i.e., FCEM, U-net, Res-Unet, Unet++, MSN-Net, WRAU-Net and ours). The experiment results demonstrate that the proposed AMSFF-U-net can achieve better segmentation performance in our works, particularly for weak fractures and tiny scale fractures.<\/jats:p>","DOI":"10.3233\/jifs-211968","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T10:22:50Z","timestamp":1634725370000},"page":"3761-3774","source":"Crossref","is-referenced-by-count":7,"title":["Adaptive multi-scale feature fusion based U-net for fracture segmentation in coal rock images"],"prefix":"10.1177","volume":"42","author":[{"given":"Fengli","family":"Lu","sequence":"first","affiliation":[{"name":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengcai","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoying","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"10","key":"10.3233\/JIFS-211968_ref2","doi-asserted-by":"publisher","first-page":"113428","DOI":"10.1016\/j.eswa.2020.113428","article-title":"An efficient harris hawks-inspired image segmentation method","volume":"155","author":"Rodr\u00edguez-Esparza","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-211968_ref3","doi-asserted-by":"publisher","first-page":"12917","DOI":"10.1007\/s11042-018-6421-7","article-title":"A hybrid edge-based technique for segmentation of renal lesions in CT images","volume":"78","author":"Kaur","year":"2018","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/JIFS-211968_ref4","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1109\/TMI.2018.2815013","article-title":"Multi-pass fast watershed for accurate segmentation of overlapping cervical cells","volume":"37","author":"Tareef","year":"2018","journal-title":"IEEE Trans. Med, Imaging"},{"key":"10.3233\/JIFS-211968_ref5","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.cageo.2013.03.006","article-title":"Multiscale Hessian fracture filtering for the enhancement and segmentation of narrow fractures in 3D image data","volume":"57","author":"Voorn","year":"2013","journal-title":"Computers & Geosciences"},{"key":"10.3233\/JIFS-211968_ref6","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/2980747"},{"key":"10.3233\/JIFS-211968_ref7","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1007\/s12559-019-09692-6","article-title":"A cognitively-inspired system architecture for the Mengshi cognitive vehicle","volume":"12","author":"Zhang","year":"2019","journal-title":"Cognit Comput"},{"key":"10.3233\/JIFS-211968_ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"11","key":"10.3233\/JIFS-211968_ref10","doi-asserted-by":"publisher","first-page":"3777","DOI":"10.3390\/app10113777","article-title":"Multi-path recurrent u-net segmentation of retinal fundus image","volume":"10","author":"Jiang","year":"2020","journal-title":"Applied Sciences"},{"issue":"10","key":"10.3233\/JIFS-211968_ref11","doi-asserted-by":"publisher","first-page":"102025","DOI":"10.1016\/j.media.2021.102025","article-title":"SCS-Net: A scale and context sensitive network for retinal vessel segmentation","volume":"70","author":"Wu","year":"2021","journal-title":"Medical Image Analysis"},{"key":"10.3233\/JIFS-211968_ref12","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","article-title":"MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"lbtehaz","year":"2020","journal-title":"Neural Networks"},{"key":"10.3233\/JIFS-211968_ref13","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12155"},{"key":"10.3233\/JIFS-211968_ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2020.07.007"},{"key":"10.3233\/JIFS-211968_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00162"},{"key":"10.3233\/JIFS-211968_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2018.8451636"},{"issue":"8","key":"10.3233\/JIFS-211968_ref18","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3390\/e22080811","article-title":"A multi-scale feature fusion method based on U-Net for retinal vessel segmentation","volume":"22","author":"Yang","year":"2020","journal-title":"Entropy"},{"issue":"12","key":"10.3233\/JIFS-211968_ref19","doi-asserted-by":"publisher","first-page":"3499","DOI":"10.1109\/TBME.2019.2906667","article-title":"Dilated-Inception Net: multi-scale feature aggregation for cardiac right ventricle segmentation","volume":"66","author":"Li","year":"2019","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"10.3233\/JIFS-211968_ref20","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TIP.2019.2919937","article-title":"High-resolution encoder\u2013decoder networks for low-contrast medical image segmentation","volume":"29","author":"Zhou","year":"2019","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"10.3233\/JIFS-211968_ref21","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"UNet++: redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"10.3233\/JIFS-211968_ref22","doi-asserted-by":"publisher","first-page":"106070","DOI":"10.1016\/j.cmpb.2021.106070","article-title":"BSEResU-Net: An attention-based before-activation residual U-Net for retinal vessel segmentation","volume":"205","author":"Li","year":"2021","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"6","key":"10.3233\/JIFS-211968_ref23","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1007\/s11760-020-01835-9","article-title":"MSN-Net: a multi-scale context nested U-Net for liver segmentation","volume":"15","author":"Fan","year":"2021","journal-title":"Signal Image Video Process"},{"issue":"10","key":"10.3233\/JIFS-211968_ref24","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-Net: context encoder network for 2D medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.3233\/JIFS-211968_ref25","doi-asserted-by":"publisher","first-page":"166823","DOI":"10.1109\/ACCESS.2019.2953934","article-title":"U-Next: a novel convolution neural network with an aggregation U-Net architecture for gallstone segmentation in CT images","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"issue":"11","key":"10.3233\/JIFS-211968_ref27","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1109\/TMI.2018.2835303","article-title":"DRINet for medical image segmentation","volume":"37","author":"Chen","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.3233\/JIFS-211968_ref28","doi-asserted-by":"publisher","first-page":"105121","DOI":"10.1016\/j.cmpb.2019.105121","article-title":"GC-Net: global context network for medical image segmentation","volume":"190","author":"Ni","year":"2019","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"4","key":"10.3233\/JIFS-211968_ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3233\/XST-200650","article-title":"DCU-Net: Multi-scale U-Net for brain tumor segmentation","volume":"28","author":"Yang","year":"2020","journal-title":"Journal of X-Ray Science and Technology"},{"issue":"99","key":"10.3233\/JIFS-211968_ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3100137","article-title":"Multiscale CNN based on component analysis for SAR ATR","volume":"PP","author":"Li","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.3233\/JIFS-211968_ref32","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.patrec.2020.07.013","article-title":"RefineU-Net: improved U-Net with progressive global feedbacks and residual attention guided local refinement for medical image segmentation","volume":"138","author":"Lin","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/JIFS-211968_ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104449"},{"key":"10.3233\/JIFS-211968_ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019283"},{"key":"10.3233\/JIFS-211968_ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9-28"},{"issue":"3","key":"10.3233\/JIFS-211968_ref38","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1145\/1179352.1141920","article-title":"Image deformation using moving least squares","volume":"25","author":"Schaefer","year":"2006","journal-title":"ACM Transactions on Graphics"},{"issue":"5","key":"10.3233\/JIFS-211968_ref39","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1080\/2150704X.2019.1574990","article-title":"Using the wide-range attention U-Net for road segmentation","volume":"10","author":"Yuan","year":"2019","journal-title":"Remote Sensing Letters"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-211968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:03Z","timestamp":1777455903000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-211968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,4]]},"references-count":32,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/jifs-211968","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.2.23959\/v2","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.2.23959\/v1","asserted-by":"object"}]},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,4]]}}}