{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T03:21:11Z","timestamp":1784690471464,"version":"3.55.0"},"reference-count":73,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82071992"],"award-info":[{"award-number":["82071992"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515012943"],"award-info":[{"award-number":["2025A1515012943"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515220033"],"award-info":[{"award-number":["2024A1515220033"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.media.2026.103966","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T07:56:53Z","timestamp":1769587013000},"page":"103966","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Multimodal sparse fusion transformer network with spatio-temporal decoupling for breast tumor classification"],"prefix":"10.1016","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6849-8236","authenticated-orcid":false,"given":"Jiahao","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuxin","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haolin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhemin","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huancheng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.103966_bib0001","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1007\/s00330-019-06417-z","article-title":"Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network","volume":"30","author":"Aldoj","year":"2020","journal-title":"Eur. Radiol."},{"key":"10.1016\/j.media.2026.103966_bib0002","doi-asserted-by":"crossref","first-page":"4523","DOI":"10.3390\/app10134523","article-title":"Towards a better understanding of transfer learning for medical imaging: a case study","volume":"10","author":"Alzubaidi","year":"2020","journal-title":"Appl. Sci."},{"key":"10.1016\/j.media.2026.103966_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105253","article-title":"A review on multimodal medical image fusion: compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics","volume":"144","author":"Azam","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103966_bib0004","author":"Baid"},{"key":"10.1016\/j.media.2026.103966_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14507","article-title":"AdaMAE: adaptive masking for efficient spatiotemporal learning with masked autoencoders","author":"Bandara","year":"2023"},{"key":"10.1016\/j.media.2026.103966_bib0006","doi-asserted-by":"crossref","first-page":"93","DOI":"10.14366\/usg.18053","article-title":"Future of breast elastography","volume":"38","author":"Barr","year":"2019","journal-title":"Ultrasonography"},{"key":"10.1016\/j.media.2026.103966_bib0007","doi-asserted-by":"crossref","first-page":"15845","DOI":"10.1007\/s11042-023-15913-w","article-title":"A systematic literature review on multimodal medical image fusion","volume":"83","author":"Basu","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.media.2026.103966_bib0008","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","first-page":"1","article-title":"Is Space-Time Attention All You Need for Video Understanding?","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.media.2026.103966_bib0010","doi-asserted-by":"crossref","first-page":"117","DOI":"10.3390\/diagnostics3010117","article-title":"Strain elastography ultrasound: an overview with emphasis on breast cancer diagnosis","volume":"3","author":"Carlsen","year":"2013","journal-title":"Diagnostics"},{"key":"10.1016\/j.media.2026.103966_bib0011","series-title":"A New Model and the Kinetics Dataset, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6299","article-title":"Quo Vadis, Action Recognition?","author":"Carreira","year":"2017"},{"key":"10.1016\/j.media.2026.103966_bib0013","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1002\/uog.930","article-title":"Analysis of sonographic features for the differentiation of benign and malignant breast tumors of different sizes","volume":"23","author":"Chen","year":"2004","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"10.1016\/j.media.2026.103966_bib0014","first-page":"19974","article-title":"Chasing sparsity in vision transformers: an end-to-end exploration","author":"Chen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5896","article-title":"Learning a Sparse Transformer Network for Effective Image Deraining","author":"Chen","year":"2023"},{"key":"10.1016\/j.media.2026.103966_bib0012","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1016\/j.ultrasmedbio.2024.01.012","article-title":"Diagnostic performance of deep learning in video-based ultrasonography for breast cancer: a retrospective multicentre study","volume":"50","author":"Chen","year":"2024","journal-title":"Ultrasound Med. Biol."},{"key":"10.1016\/j.media.2026.103966_bib0016","series-title":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","first-page":"1","article-title":"CNNs based multi-modality classification for AD diagnosis","author":"Cheng","year":"2017"},{"key":"10.1016\/j.media.2026.103966_bib0017","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s10278-016-9929-2","article-title":"Transfer learning with convolutional neural networks for classification of abdominal ultrasound images","volume":"30","author":"Cheng","year":"2017","journal-title":"J. Digit. Imaging"},{"key":"10.1016\/j.media.2026.103966_bib0018","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I., 2019. Generating Long Sequences with Sparse Transformers. ArXiv abs\/1904.10509. https:\/\/doi.org\/10.48550\/arXiv.1904.10509."},{"key":"10.1016\/j.media.2026.103966_bib0019","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.3390\/diagnostics11081384","article-title":"TransMed: transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.media.2026.103966_bib0020","series-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","first-page":"4171","author":"Devlin","year":"2019"},{"key":"10.1016\/j.media.2026.103966_bib0021","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N., 2021. An Image is Worth 16x16 Words: transformers for Image Recognition at S cale, International Conference on Learning Representations, pp. 1\u201322. DOI: 10.48550\/arXiv.2010.11929."},{"key":"10.1016\/j.media.2026.103966_bib0022","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"203","article-title":"X3D: expanding Architectures for Efficient Video Recognition","author":"Feichtenhofer","year":"2020"},{"key":"10.1016\/j.media.2026.103966_bib0023","doi-asserted-by":"crossref","first-page":"20337","DOI":"10.1109\/ACCESS.2023.3244228","article-title":"LCDEiT: a linear complexity data-efficient image transformer for MRI brain tumor classification","volume":"11","author":"Ferdous","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.media.2026.103966_bib0024","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.acra.2020.03.032","article-title":"Clinical applications of superb microvascular imaging in the superficial tissues and organs: a systematic review","volume":"28","author":"Fu","year":"2021","journal-title":"Acad. Radiol."},{"key":"10.1016\/j.media.2026.103966_bib0025","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"836","article-title":"Actor-Transformers for Group Activity Recognition","author":"Gavrilyuk","year":"2020"},{"key":"10.1016\/j.media.2026.103966_bib0027","doi-asserted-by":"crossref","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","article-title":"Deep multimodal representation learning: a survey","volume":"7","author":"Guo","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.media.2026.103966_bib0026","article-title":"Multimodal MRI image decision fusion-based network for glioma classification","volume":"12 - 2022","author":"Guo","year":"2022","journal-title":"Front. Oncol."},{"key":"10.1016\/j.media.2026.103966_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.108660","article-title":"Multi-scale 3D convolution feature-based broad learning system for alzheimer\u2019s disease diagnosis via MRI images","volume":"120","author":"Han","year":"2022","journal-title":"Appl. Soft. Comput."},{"key":"10.1016\/j.media.2026.103966_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2021.108036","article-title":"Multimodal medical image fusion review: theoretical background and recent advances","volume":"183","author":"Hermessi","year":"2021","journal-title":"Signal Process."},{"key":"10.1016\/j.media.2026.103966_bib0030","doi-asserted-by":"crossref","DOI":"10.1155\/2020\/8279342","article-title":"A review of multimodal medical image fusion techniques","author":"Huang","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"10.1016\/j.media.2026.103966_bib0031","first-page":"1","article-title":"Methods for the segmentation and classification of breast ultrasound images: a review","author":"Ilesanmi","year":"2021","journal-title":"J. Ultrasound"},{"key":"10.1016\/j.media.2026.103966_bib0032","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.103966_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2022.103565","article-title":"Multi-modal data Alzheimer\u2019s disease detection based on 3D convolution","volume":"75","author":"Kong","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.media.2026.103966_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106788","article-title":"Multimodal cross enhanced fusion network for diagnosis of Alzheimer\u2019s disease and subjective memory complaints","volume":"157","author":"Leng","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103966_bib0035","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"13381","article-title":"AI Choreographer: music Conditioned 3D Dance Generation with AIST++","author":"Li","year":"2021"},{"key":"10.1016\/j.media.2026.103966_bib0037","first-page":"8518","article-title":"Scheduled sampling in vision-language pretraining with decoupled encoder-decoder network","volume":"35","author":"Li","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.media.2026.103966_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108635","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":"10.1016\/j.media.2026.103966_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2023.102001","article-title":"Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study","volume":"60","author":"Liao","year":"2023","journal-title":"EClinicalMedicine"},{"key":"10.1016\/j.media.2026.103966_bib0039","unstructured":"Lin, J., Yang, A., Zhang, Y., Liu, J., Zhou, J., Yang, H., 2020. InterBERT: vision-and-Language Interaction for Multi-modal Pretraining. ArXiv abs\/2003.13198."},{"key":"10.1016\/j.media.2026.103966_bib0040","article-title":"Bidirectional Mapping of Brain MRI and PET With 3D Reversible GAN for the Diagnosis of Alzheimer\u2019s Disease","volume":"15 - 2021","author":"Lin","year":"2021","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.media.2026.103966_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3202","article-title":"Video Swin Transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.media.2026.103966_bib0042","article-title":"ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0043","doi-asserted-by":"crossref","first-page":"7786","DOI":"10.1016\/j.eswa.2008.11.029","article-title":"Finding out general tendencies in speckle noise reduction in ultrasound images","volume":"36","author":"Mateo","year":"2009","journal-title":"Expert. Syst. Appl."},{"key":"10.1016\/j.media.2026.103966_bib0044","article-title":"Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks","volume":"190","author":"Moon","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.media.2026.103966_bib0045","doi-asserted-by":"crossref","first-page":"1058","DOI":"10.1016\/j.ultrasmedbio.2013.12.021","article-title":"Intra-observer reproducibility and diagnostic performance of breast shear-wave elastography in asian women","volume":"40","author":"Park","year":"2014","journal-title":"Ultrasound Med. Biol."},{"key":"10.1016\/j.media.2026.103966_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127433","article-title":"SparseSwin: swin transformer with sparse transformer block","volume":"580","author":"Pinasthika","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.media.2026.103966_bib0047","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1038\/s41551-021-00711-2","article-title":"Prospective assessment of breast cancer risk from multimodal multiview ultrasound images via clinically applicable deep learning","volume":"5","author":"Qian","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.media.2026.103966_bib0050","series-title":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","first-page":"1","article-title":"Two-Dimensional Attentive Fusion for Multi-Modal Learning of Neuroimaging and Genomics Data","author":"Rahaman","year":"2022"},{"key":"10.1016\/j.media.2026.103966_bib0049","first-page":"9774","article-title":"TriBERT: human-centric Audio-visual Representation Learning","author":"Rahman","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0048","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1002\/jemt.23597","article-title":"Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture","volume":"84","author":"Rehman","year":"2021","journal-title":"Microsc. Res. Tech"},{"key":"10.1016\/j.media.2026.103966_bib0051","unstructured":"Shi, B., Hsu, W.-N., Lakhotia, K., Mohamed, A.-r., 2022. Learning audio-visual speech representation by masked multimodal cluster prediction. ArXiv abs\/2201.02184."},{"key":"10.1016\/j.media.2026.103966_bib0052","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0054","doi-asserted-by":"crossref","first-page":"109","DOI":"10.2214\/ajr.170.1.9423610","article-title":"Analysis of sonographic features in the differentiation of fibroadenoma and invasive ductal carcinoma","volume":"170","author":"Skaane","year":"1998","journal-title":"AJR Am. J. Roentgenol."},{"key":"10.1016\/j.media.2026.103966_bib0053","article-title":"An effective multimodal image fusion method using MRI and PET for Alzheimer's disease diagnosis","volume":"3 - 2021","author":"Song","year":"2021","journal-title":"Front. Digit. Health"},{"key":"10.1016\/j.media.2026.103966_bib0056","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7463","article-title":"VideoBERT: a Joint Model for Video and Language Representation Learning","author":"Sun","year":"2019"},{"key":"10.1016\/j.media.2026.103966_bib0057","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","author":"Tancik","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0058","article-title":"Attention is All you Need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103966_bib0059","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1109\/JBHI.2021.3099817","article-title":"Multi-scale binary pattern encoding network for cancer classification in pathology images","volume":"26","author":"Vuong","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.media.2026.103966_bib0061","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10941","article-title":"Multi-Modality Cross Attention Network for Image and Sentence Matching","author":"Wei","year":"2020"},{"key":"10.1016\/j.media.2026.103966_bib0063","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.106164","article-title":"Self-supervised multi-modal fusion network for multi-modal thyroid ultrasound image diagnosis","volume":"150","author":"Xiang","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103966_bib0064","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"11196","article-title":"DeepChange: a Long-Term Person Re-Identification Benchmark with Clothes Change","author":"Xu","year":"2023"},{"key":"10.1016\/j.media.2026.103966_bib0065","doi-asserted-by":"crossref","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","article-title":"Multimodal Learning With Transformers: a Survey","volume":"45","author":"Xu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.103966_bib0066","doi-asserted-by":"crossref","first-page":"82688","DOI":"10.1109\/ACCESS.2020.2990683","article-title":"A temporal Sequence dual-branch network for classifying hybrid ultrasound data of breast cancer","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.media.2026.103966_bib0067","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1120\/jacmp.v9i4.2741","article-title":"A novel algorithm for initial lesion detection in ultrasound breast images","volume":"9","author":"Yap","year":"2008","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"10.1016\/j.media.2026.103966_bib0068","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-22984-6","article-title":"DeepPDT-Net: predicting the outcome of photodynamic therapy for chronic central serous chorioretinopathy using two-stage multimodal transfer learning","volume":"12","author":"Yoo","year":"2022","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2026.103966_bib0070","doi-asserted-by":"crossref","first-page":"437","DOI":"10.7863\/ultra.33.3.437","article-title":"Shear wave elastography for liver stiffness measurement in clinical sonographic examinations evaluation of intraobserver reproducibility, technical failure, and unreliable stiffness measurements","volume":"33","author":"Yoon","year":"2014","journal-title":"J. Ultrasound Med."},{"key":"10.1016\/j.media.2026.103966_bib0069","first-page":"12226","article-title":"D-vlog: multimodal vlog dataset for depression detection","volume":"36","author":"Yoon","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.media.2026.103966_bib0073","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"13577","article-title":"VidTr: video Transformer Without Convolutions","author":"Zhang","year":"2021"},{"key":"10.1016\/j.media.2026.103966_bib0072","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1016\/j.ultrasmedbio.2016.05.010","article-title":"Application of a novel microvascular imaging technique in breast lesion evaluation","volume":"42","author":"Zhao","year":"2016","journal-title":"Ultrasound Med. Biol."},{"key":"10.1016\/j.media.2026.103966_bib0071","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejrad.2023.110885","article-title":"Deep learning-based classification of breast lesions using dynamic ultrasound video","volume":"165","author":"Zhao","year":"2023","journal-title":"Eur. J. Radiol."},{"key":"10.1016\/j.media.2026.103966_bib0074","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4273","article-title":"MMVP: motion-Matrix-Based Video Prediction","author":"Zhong","year":"2023"},{"key":"10.1016\/j.media.2026.103966_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106959","article-title":"Deep learning methods for medical image fusion: a review","volume":"160","author":"Zhou","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103966_bib0076","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1038\/s41598-023-27518-2","article-title":"Prediction of pathologic complete response to neoadjuvant systemic therapy in triple negative breast cancer using deep learning on multiparametric MRI","volume":"13","author":"Zhou","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2026.103966_bib77","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1109\/TMI.2025.3599487","article-title":"Adaptive sequential bayesian iterative learning for myocardial motion estimation on cardiac image sequences","volume":"45","author":"Zhuang","year":"2026","journal-title":"IEEE Trans. Med. Imag."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000356?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000356?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:03:42Z","timestamp":1783422222000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526000356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":73,"alternative-id":["S1361841526000356"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.103966","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal sparse fusion transformer network with spatio-temporal decoupling for breast tumor classification","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.103966","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103966"}}