{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T13:28:42Z","timestamp":1776086922447,"version":"3.50.1"},"reference-count":44,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"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":[[2026,2,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Bone scan imaging for the detection of bone metastasis of breast cancer has been widely adopted; however, noise, anatomy superimposition, and small size for early lesions will severely affect its prediction performance. In this work, we propose a new framework with two major contributions to solve the main problems existing in current deep-learning-based approaches.\n                    <jats:italic>Approach.<\/jats:italic>\n                    In this study, we put forward a new model called the dual branch feature alignment network (DBFANet) for automated breast cancer bone metastases detection in bone scintigraphy. DBFA-net adopts a dual-branch CNN\u2013Transformer structure: the CNN branch focuses on the local details, while the Transformer branch learns the global context. In addition, we design a feature alignment module (FRAT), which employs the bi-directional cross-attention mechanism for the complementary feature from two branches. Moreover, we propose an enhanced multi-scale attention module (EMSA) based on the squeeze-and-excitation (SE) block for stronger multi-scale lesion representations with less background noise suppression.\n                    <jats:italic>Main results.<\/jats:italic>\n                    We validated our proposed model based on a bone scintigraphy dataset containing 5092 images. In terms of bone metastasis prediction, DBFANet achieved an accuracy, precision, and recall value of 93.1%, 84.6%, and 84.7%, respectively, all superior to previous models (such as ResNet-50, EfficientNet-V2, and MaxViT). The ablation study has shown that both FRAT and EMSA have individual effectiveness and complementary benefits. Finally, additional external validation was performed on a publicly available bone scintigraphy dataset (BS-80K).\n                    <jats:italic>Significance.<\/jats:italic>\n                    DBFANet shows the highest detection performance for bone metastasis detection from multiview bone scintigraphy images with imbalanced classes and noise in the image, and the feature alignment with enhanced multiscale attention of DBFANet provides a useful and precise tool for bone metastasis diagnosis in a nuclear medicine imaging scenario.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ae4166","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T22:55:21Z","timestamp":1770159321000},"page":"035021","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DBFANet: a dual-branch feature alignment network for automated detection of breast cancer bone metastasis"],"prefix":"10.1088","volume":"71","author":[{"given":"Gang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3842-2634","authenticated-orcid":true,"given":"Qiang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwu","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1729-288X","authenticated-orcid":true,"given":"Yongchun","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6370-7332","authenticated-orcid":true,"given":"Tongtong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caihong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"pmbae4166bib1","first-page":"683","type":"conference-proceedings","article-title":"A novel focal tversky loss function with improved attention U-Net for lesion segmentation","author":"Abraham","year":"2019"},{"key":"pmbae4166bib2","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1007\/s00259-023-06558-w","type":"journal-article","article-title":"Ultra-fast whole-body bone tomoscintigraphies achieved with a high-sensitivity 360\u00b0 CZT camera and a dedicated deep-learning noise reduction algorithm","volume":"51","author":"Bahloul","year":"2024","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbae4166bib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijbiomac.2023.123855","type":"journal-article","article-title":"Glycosylated proteins with abnormal glycosylation changes are potential biomarkers for early diagnosis of breast cancer","volume":"236","author":"Chang","year":"2023","journal-title":"Int. J. Biol. Macromol."},{"key":"pmbae4166bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105370","type":"journal-article","article-title":"An efficient approach to medical image fusion based on optimization and transfer learning with VGG19","volume":"87","author":"Do","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae4166bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107154","type":"journal-article","article-title":"PFormer: an efficient CNN-Transformer hybrid network with content-driven P-attention for 3D medical image segmentation","volume":"101","author":"Gao","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae4166bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110491","type":"journal-article","article-title":"UCTNet: uncertainty-guided CNN-Transformer hybrid networks for medical image segmentation","volume":"152","author":"Guo","year":"2024","journal-title":"Pattern Recogn."},{"key":"pmbae4166bib7","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s40846-022-00770-z","type":"journal-article","article-title":"Integrating transfer learning and feature aggregation into self-defined convolutional neural network for automated detection of lung cancer bone metastasis","volume":"43","author":"Guo","year":"2023","journal-title":"J. Med. Biol. Eng."},{"key":"pmbae4166bib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108391","type":"journal-article","article-title":"Interpretability in the medical field: a systematic mapping and review study","volume":"117","author":"Hakkoum","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"pmbae4166bib9","first-page":"15908","type":"journal-article","article-title":"Transformer in transformer","volume":"vol 34","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pmbae4166bib10","doi-asserted-by":"publisher","first-page":"6290","DOI":"10.1038\/s41598-024-56698-8","type":"journal-article","article-title":"An efficient breast cancer classification model using bilateral filtering and fuzzy convolutional neural network","volume":"14","author":"Hayum","year":"2024","journal-title":"Sci. Rep."},{"key":"pmbae4166bib11","first-page":"94097","type":"conference-proceedings","article-title":"Perceiving longer sequences with bi-directional cross-attention transformers","volume":"vol 37","author":"Hiller","year":"2024"},{"key":"pmbae4166bib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106221","type":"journal-article","article-title":"BS-80K: the first large open-access dataset of bone scan images","volume":"151","author":"Huang","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"pmbae4166bib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534","type":"journal-article","article-title":"HiFuse: hierarchical multi-scale feature fusion network for medical image classification","volume":"87","author":"Huo","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae4166bib14","doi-asserted-by":"publisher","DOI":"10.1088\/1402-4896\/ade91a","type":"journal-article","article-title":"Automated diagnosis of cancer bone metastases using multi-view contrastive learning","volume":"100","author":"Jian","year":"2025","journal-title":"Phys. Scr."},{"key":"pmbae4166bib15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-22874-7","type":"journal-article","article-title":"ResNet-EfficientNet powered framework for high-precision cough-based classification of infectious diseases","volume":"15","author":"Johnson","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae4166bib16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41591-025-03502-3","type":"journal-article","article-title":"Global patterns and trends in breast cancer incidence and mortality across 185 countries","volume":"31","author":"Kim","year":"2025","journal-title":"Nat. Med."},{"key":"pmbae4166bib17","first-page":"63","author":"Koonce","year":"2021","type":"book"},{"key":"pmbae4166bib18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-17799-0","type":"journal-article","article-title":"Multi-resolution transfer learning for tampered image classification using SE-enhanced fused-MBConv and optimized CNN heads","volume":"15","author":"Korsipati","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae4166bib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108635","type":"journal-article","article-title":"A review of deep learning-based information fusion techniques for multimodal medical image classification","volume":"177","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"pmbae4166bib20","first-page":"2980","type":"conference-proceedings","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"pmbae4166bib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103850","type":"journal-article","article-title":"CIMB-MVQA: causal intervention on modality-specific biases for medical visual question answering","volume":"107","author":"Liu","year":"2025","journal-title":"Med. Image Anal."},{"key":"pmbae4166bib22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-73991-8","type":"journal-article","article-title":"Bone scintigraphy based on deep learning model and modified growth optimizer","volume":"14","author":"Magdy","year":"2024","journal-title":"Sci. Rep."},{"key":"pmbae4166bib23","doi-asserted-by":"publisher","first-page":"3596","DOI":"10.1038\/s41598-025-86752-y","type":"journal-article","article-title":"Dilated SE-DenseNet for brain tumor MRI classification","volume":"15","author":"Mao","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae4166bib24","doi-asserted-by":"publisher","first-page":"7895","DOI":"10.1007\/s00330-024-10834-0","type":"journal-article","article-title":"Class imbalance on medical image classification: towards better evaluation practices for discrimination and calibration performance","volume":"34","author":"Mosquera","year":"2024","journal-title":"Eur. Radiol."},{"key":"pmbae4166bib25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109762","type":"journal-article","article-title":"QMaxViT-Unet+: a query-based MaxViT-Unet with edge enhancement for scribble-supervised segmentation of medical images","volume":"187","author":"Nguyen-Tat","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"pmbae4166bib26","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.3390\/cancers16101870","type":"journal-article","article-title":"Clinical applications of artificial intelligence in medical imaging and image processing\u2014a review","volume":"16","author":"Obuchowicz","year":"2024","journal-title":"Cancers"},{"key":"pmbae4166bib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107627","type":"journal-article","article-title":"A novel CNN-ViT-based deep learning model for early skin cancer diagnosis","volume":"104","author":"Pacal","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae4166bib28","doi-asserted-by":"publisher","first-page":"5414","DOI":"10.1002\/mp.17094","type":"journal-article","article-title":"Fast SPECT\/CT planar bone imaging enabled by deep learning enhancement","volume":"51","author":"Pan","year":"2024","journal-title":"Med. Phys."},{"key":"pmbae4166bib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3625287","type":"journal-article","article-title":"Explainable deep learning methods in medical image classification: a survey","volume":"56","author":"Patr\u00edcio","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"pmbae4166bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2019.09.027","type":"journal-article","article-title":"A mixture of views network with applications to multi-view medical imaging","volume":"374","author":"Shachor","year":"2020","journal-title":"Neurocomputing"},{"key":"pmbae4166bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103166","type":"journal-article","article-title":"A survey of label-noise deep learning for medical image analysis","volume":"95","author":"Shi","year":"2024","journal-title":"Med. Image Anal."},{"key":"pmbae4166bib32","doi-asserted-by":"publisher","first-page":"7876","DOI":"10.1038\/s41598-025-92594-5","type":"journal-article","article-title":"Automatic detecting multiple bone metastases in breast cancer using deep learning based on low-resolution bone scan images","volume":"15","author":"Shi","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae4166bib33","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","type":"journal-article","article-title":"Image fusion in the loop of high-level vision tasks: a semantic-aware real-time infrared and visible image fusion network","volume":"82","author":"Tang","year":"2022","journal-title":"Inform. Fusion"},{"key":"pmbae4166bib34","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s00259-023-06459-y","type":"journal-article","article-title":"Cardiac [99mTc] Tc-hydroxydiphosphonate uptake on bone scintigraphy in patients with hereditary transthyretin amyloidosis: an early follow-up marker?","volume":"51","author":"Tingen","year":"2024","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbae4166bib35","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1007\/s00259-016-3415-4","type":"journal-article","article-title":"The EANM practice guidelines for bone scintigraphy","volume":"43","author":"Van den Wyngaert","year":"2016","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbae4166bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.apergo.2024.104243","type":"journal-article","article-title":"Radiologists\u2019 perspectives on the workflow integration of an artificial intelligence-based computer-aided detection system: a qualitative study","volume":"117","author":"Wenderott","year":"2024","journal-title":"Appl. Ergon."},{"key":"pmbae4166bib37","first-page":"16133","type":"conference-proceedings","article-title":"Convnext v2: co-designing and scaling convnets with masked autoencoders","author":"Woo","year":"2023"},{"key":"pmbae4166bib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.130451","type":"journal-article","article-title":"SKENet: a spectral and symmetry-guided deep network for bone metastasis segmentation in SPECT imaging","volume":"301","author":"Xie","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"pmbae4166bib39","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41392-024-02108-4","type":"journal-article","article-title":"Breast cancer: pathogenesis and treatments","volume":"10","author":"Xiong","year":"2025","journal-title":"Signal Transduct. Target. Ther."},{"key":"pmbae4166bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102962","type":"journal-article","article-title":"Multi-modal disease segmentation with continual learning and adaptive decision fusion","volume":"118","author":"Xu","year":"2025","journal-title":"Inform. Fusion"},{"key":"pmbae4166bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109228","type":"journal-article","article-title":"An effective CNN and Transformer complementary network for medical image segmentation","volume":"136","author":"Yuan","year":"2023","journal-title":"Pattern Recogn."},{"key":"pmbae4166bib42","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.media.2019.02.010","type":"journal-article","article-title":"Medical image classification using synergic deep learning","volume":"54","author":"Zhang","year":"2019","journal-title":"Med. Image Anal."},{"key":"pmbae4166bib43","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2025.217939","type":"journal-article","article-title":"NSUN2-mediated m5C modification of KDM6B mRNA enhances osteoclast differentiation and promotes breast cancer bone metastasis","volume":"631","author":"Zhang","year":"2025","journal-title":"Cancer Lett."},{"key":"pmbae4166bib44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107861","type":"journal-article","article-title":"Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI","volume":"169","author":"Zhou","year":"2024","journal-title":"Comput. Biol. Med."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T08:47:39Z","timestamp":1770886059000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae4166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,12]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2,12]]},"published-print":{"date-parts":[[2026,2,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae4166","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,12]]},"assertion":[{"value":"DBFANet: a dual-branch feature alignment network for automated detection of breast cancer bone metastasis","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 2026 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":"2025-11-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}