{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T15:09:52Z","timestamp":1792681792495,"version":"4.5.0"},"reference-count":54,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2024,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Breast cancer is the major cause of cancer death among women worldwide. Deep learning-based computer-aided diagnosis (CAD) systems for classifying lesions in breast ultrasound images can help materialise the early detection of breast cancer and enhance survival chances.\n                    <jats:italic>Approach.<\/jats:italic>\n                    This paper presents a completely automated BUS diagnosis system with modular convolutional neural networks tuned with novel loss functions. The proposed network comprises a dynamic channel input enhancement network, an attention-guided InceptionV3-based feature extraction network, a classification network, and a parallel feature transformation network to map deep features into quantitative ultrasound (QUS) feature space. These networks function together to improve classification accuracy by increasing the separation of benign and malignant class-specific features and enriching them simultaneously. Unlike the categorical crossentropy (CCE) loss-based traditional approaches, our method uses two additional novel losses: class activation mapping (CAM)-based and QUS feature-based losses, to capacitate the overall network learn the extraction of clinically valued lesion shape and texture-related properties focusing primarily the lesion area for explainable AI (XAI).\n                    <jats:italic>Main results.<\/jats:italic>\n                    Experiments on four public, one private, and a combined breast ultrasound dataset are used to validate our strategy. The suggested technique obtains an accuracy of 97.28%, sensitivity of 93.87%, F1-score of 95.42% on dataset 1 (BUSI), and an accuracy of 91.50%, sensitivity of 89.38%, and F1-score of 89.31% on the combined dataset, consisting of 1494 images collected from hospitals in five demographic locations using four ultrasound systems of different manufacturers. These results outperform techniques reported in the literature by a considerable margin.\n                    <jats:italic>Significance.<\/jats:italic>\n                    The proposed CAD system provides diagnosis from the auto-focused lesion area of B-mode BUS images, avoiding the explicit requirement of any segmentation or region of interest extraction, and thus can be a handy tool for making accurate and reliable diagnoses even in unspecialized healthcare centers.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ad1319","type":"journal-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T17:58:39Z","timestamp":1701885519000},"page":"015018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["CAM-QUS guided self-tuning modular CNNs with multi-loss functions for fully automated breast lesion classification in ultrasound images"],"prefix":"10.1088","volume":"69","author":[{"given":"Jarin","family":"Tasnim","sequence":"first","affiliation":[{"name":"Bangladesh University of Engineering and Technology (BUET)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Kamrul","family":"Hasan","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology (BUET)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"pmbad1319bib1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863","type":"journal-article","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"pmbad1319bib2","type":"web-resource"},{"key":"pmbad1319bib3","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1016\/j.ultrasmedbio.2015.01.023","type":"journal-article","article-title":"Bimodal multiparameter-based approach for benign\u2013malignant classification of breast tumors","volume":"41","author":"Ara","year":"2015","journal-title":"Ultrasound Med. Biol."},{"key":"pmbad1319bib4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ultras.2017.04.006","type":"journal-article","article-title":"EMD-DWT based transform domain feature reduction approach for quantitative multi-class classification of breast lesions","volume":"80","author":"Ara","year":"2017","journal-title":"Ultrasonics"},{"key":"pmbad1319bib5","type":"web-resource"},{"key":"pmbad1319bib6","type":"web-resource"},{"key":"pmbad1319bib7","type":"web-resource"},{"key":"pmbad1319bib8","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1002\/mp.13361","type":"journal-article","article-title":"Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion","volume":"46","author":"Byra","year":"2019","journal-title":"Med. Phys."},{"key":"pmbad1319bib9","type":"web-resource"},{"key":"pmbad1319bib10","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1007\/s10278-022-00711-x","type":"journal-article","article-title":"Breast tumor classification in ultrasound images by fusion of deep convolutional neural network and shallow LBP feature","volume":"36","author":"Chen","year":"2023","journal-title":"J. Digit. Imaging"},{"key":"pmbad1319bib11","doi-asserted-by":"crossref","DOI":"10.1109\/SITIS.2019.00037","type":"other","article-title":"Breast ultrasound image classification using a pre-trained convolutional neural network","author":"Daoud","year":"2019"},{"key":"pmbad1319bib12","doi-asserted-by":"publisher","DOI":"10.3390\/s20236838","type":"journal-article","article-title":"Breast tumor classification in ultrasound images using combined deep and handcrafted features","volume":"20","author":"Daoud","year":"2020","journal-title":"Sensors"},{"key":"pmbad1319bib13","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/s11604-019-00831-5","type":"journal-article","article-title":"Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network","volume":"37","author":"Fujioka","year":"2019","journal-title":"Jpn. J. Radiol."},{"key":"pmbad1319bib14","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI.2015.7163961","type":"other","article-title":"BM3D-based ultrasound image denoising via brushlet thresholding","author":"Gan","year":"2015"},{"key":"pmbad1319bib15","doi-asserted-by":"publisher","first-page":"1889","DOI":"10.1109\/TMI.2012.2206398","type":"journal-article","article-title":"Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound","volume":"31","author":"Gomez","year":"2012","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad1319bib16","first-page":"331","type":"book","article-title":"Detection and classification of breast lesions using ultrasound-based imaging modalities","author":"Hasan","year":"2019"},{"key":"pmbad1319bib17","first-page":"770","type":"other","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbad1319bib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102053","type":"journal-article","article-title":"RATE-iPATH: on the design of integrated ultrasonic biomarkers for breast cancer detection","volume":"62","author":"Hossen","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbad1319bib19","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00745","type":"other","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"pmbad1319bib20","first-page":"4700","type":"other","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"pmbad1319bib21","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1002\/uog.5205","type":"journal-article","article-title":"Computer-aided diagnosis using morphological features for classifying breast lesions on ultrasound","volume":"32","author":"Huang","year":"2008","journal-title":"Ultrasound Obstetrics Gynecol."},{"key":"pmbad1319bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101851","type":"journal-article","article-title":"Boundary loss for highly unbalanced segmentation","volume":"67","author":"Kervadec","year":"2021","journal-title":"Med. Image Anal."},{"key":"pmbad1319bib23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108427","type":"journal-article","article-title":"Segmentation information with attention integration for classification of breast tumor in ultrasound image","volume":"124","author":"Luo","year":"2022","journal-title":"Pattern Recognit."},{"key":"pmbad1319bib24","doi-asserted-by":"publisher","first-page":"11383","DOI":"10.1007\/s00521-020-05394-5","type":"journal-article","article-title":"Convolutional neural network-based models for diagnosis of breast cancer","volume":"34","author":"Masud","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"pmbad1319bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5120\/10041-4635","type":"journal-article","article-title":"Breast cancer diagnosis by using k-nearest neighbor with different distances and classification rules","volume":"62","author":"Medjahed","year":"2013","journal-title":"Int. J. Comput. Appl."},{"key":"pmbad1319bib26","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s11548-013-0838-2","type":"journal-article","article-title":"An evaluation of image descriptors combined with clinical data for breast cancer diagnosis","volume":"8","author":"Moura","year":"2013","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"pmbad1319bib27","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.patrec.2012.10.025","type":"journal-article","article-title":"A new distance measure based on generalized image normalized cross-correlation for robust video tracking and image recognition","volume":"34","author":"Nakhmani","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"pmbad1319bib28","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","type":"journal-article","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbad1319bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2022.101816","type":"journal-article","article-title":"Fully-automated deep learning pipeline for segmentation and classification of breast ultrasound images","volume":"63","author":"Podda","year":"2022","journal-title":"J. Comput. Sci."},{"key":"pmbad1319bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13673-015-0029-y","type":"journal-article","article-title":"Assessment of combined textural and morphological features for diagnosis of breast masses in ultrasound","volume":"5","author":"Prabusankarlal","year":"2015","journal-title":"Human-centric Comput. Inf. Sci."},{"key":"pmbad1319bib31","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3934\/mfc.2018008","type":"journal-article","article-title":"convolutional neural networks see the world\u2013a survey of convolutional neural network visualization methods","volume":"1","author":"Qin","year":"2018","journal-title":"Math. Foundations Comput."},{"key":"pmbad1319bib32","doi-asserted-by":"publisher","first-page":"16533","DOI":"10.1007\/s00521-022-07230-4","type":"journal-article","article-title":"Segmentation and classification of breast cancer using novel deep learning architecture","volume":"34","author":"Ramesh","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"pmbad1319bib33","doi-asserted-by":"publisher","DOI":"10.17632\/wmy84gzngw.1","type":"dataset","article-title":"Breast ultrasound image","volume":"1","author":"Rodrigues","year":"2017","unstructured":"Rodrigues P S Breast U 2017 Breast ultrasound image Mendeley Data 1 10.17632\/wmy84gzngw.1"},{"key":"pmbad1319bib34","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.patcog.2018.01.032","type":"journal-article","article-title":"Automatic initialization of active contours and level set method in ultrasound images of breast abnormalities","volume":"79","author":"Rodtook","year":"2018","journal-title":"Pattern Recognit."},{"key":"pmbad1319bib35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","type":"journal-article","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vision"},{"key":"pmbad1319bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105353","type":"journal-article","article-title":"Breast cancer classification using deep learned features boosted with handcrafted features","volume":"86","author":"Sajid","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbad1319bib37","doi-asserted-by":"publisher","first-page":"9631","DOI":"10.1007\/s11042-021-11756-5","type":"journal-article","article-title":"Automatic classification with concatenation of deep and handcrafted features of histological images for breast carcinoma diagnosis","volume":"81","author":"Sethy","year":"2022","journal-title":"Multimedia Tools Appl."},{"key":"pmbad1319bib38","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1016\/j.ultrasmedbio.2015.11.016","type":"journal-article","article-title":"Computer-aided diagnosis for breast ultrasound using computerized BI-RADS features and machine learning methods","volume":"42","author":"Shan","year":"2016","journal-title":"Ultrasound Med. Biol."},{"key":"pmbad1319bib39","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1007\/s11517-022-02583-3","type":"journal-article","article-title":"Automatic skin lesion classification using a new densely connected convolutional network with an SF module","volume":"60","author":"Shan","year":"2022","journal-title":"Med. Biol. Eng. Comput."},{"key":"pmbad1319bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101829","type":"journal-article","article-title":"Classification of malignant tumors in breast ultrasound using a pretrained deep residual network model and support vector machine","volume":"87","author":"Shia","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbad1319bib41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6034","type":"preprint","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"pmbad1319bib42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","type":"preprint","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"pmbad1319bib43","first-page":"2818","type":"other","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"pmbad1319bib44","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab5093","type":"journal-article","article-title":"Computer-aided diagnosis system for breast ultrasound images using deep learning","volume":"64","author":"Tanaka","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbad1319bib45","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/tnnls.2020.3027314","type":"journal-article","article-title":"A survey on explainable artificial intelligence (XAI): toward medical XAI","volume":"32","author":"Tjoa","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"pmbad1319bib46","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s40745-020-00253-5","type":"journal-article","article-title":"A comprehensive survey of loss functions in machine learning","volume":"9","author":"Wang","year":"2020","journal-title":"Ann. Data Sci."},{"key":"pmbad1319bib47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/5894010","type":"journal-article","article-title":"A benign and malignant breast tumor classification method via efficiently combining texture and morphological features on ultrasound images","volume":"2020","author":"Wei","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"pmbad1319bib48","first-page":"3","type":"book","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"pmbad1319bib49","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1109\/JBHI.2017.2731873","type":"journal-article","article-title":"Automated breast ultrasound lesions detection using convolutional neural networks","volume":"22","author":"Yap","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbad1319bib50","doi-asserted-by":"publisher","first-page":"75641","DOI":"10.1109\/access.2021.3082076","type":"journal-article","article-title":"NeighborLoss: a loss function considering spatial correlation for semantic segmentation of remote sensing image","volume":"9","author":"Yuan","year":"2021","journal-title":"IEEE Access"},{"key":"pmbad1319bib51","doi-asserted-by":"publisher","first-page":"133349","DOI":"10.1109\/access.2020.3010863","type":"journal-article","article-title":"Breast lesion classification in ultrasound images using deep convolutional neural network","volume":"8","author":"Zeimarani","year":"2020","journal-title":"IEEE Access"},{"key":"pmbad1319bib52","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1007\/s10278-020-00357-7","type":"journal-article","article-title":"Diagnostic efficiency of the breast ultrasound computer-aided prediction model based on convolutional neural network in breast cancer","volume":"33","author":"Zhang","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"pmbad1319bib53","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.319","type":"other","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"pmbad1319bib54","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106221","type":"journal-article","article-title":"Breast ultrasound tumor image classification using image decomposition and fusion based on adaptive multi-model spatial feature fusion","volume":"208","author":"Zhuang","year":"2021","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:03:59Z","timestamp":1778778239000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad1319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12,26]]},"published-print":{"date-parts":[[2024,1,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad1319","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"CAM-QUS guided self-tuning modular CNNs with multi-loss functions for fully automated breast lesion classification in ultrasound images","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2023-08-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-26","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}