{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:46:13Z","timestamp":1777923973211,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012997","name":"Arab Academy for Science, Technology & Maritime Transport","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012997","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Breast cancer is a significant global health challenge, with highest rates of occurrence and mortality worldwide. Early detection is important for the improvement of patient outcomes and the reduction of the overall burden of the disease. Digital breast tomosynthesis (DBT) scans offer three-dimensional images of the breast tissue and is becoming a valuable tool in the detection of breast abnormalities. However, accurately classifying DBT scans is challenging due to the complexity of the anatomy of the breast and the presence of minor abnormalities. This study introduces the MSAE-DL system for the multi-class classification of DBT scans. The system incorporates a novel multi-head self-attention model with a unique ensemble classification model. Features were extracted from the Mod_AlexNet Self-Attention model and fused with histogram of oriented gradients (HOG) descriptors. Subsequently, feature vectors are reduced using three feature selection models. Finally, a novel ensemble classification model is introduced and fuses class and classifier weights for the final prediction using various classifiers. The system demonstrates optimal performance in classifying DBT scans into normal, benign, and malignant classes, achieving an accuracy of 90.13%, precision of 92.77%, and f1-score of 91.03%. The experimental results underscore the potential of this approach in enhancing DBT classification into three different classes, rather than simply binary classification.<\/jats:p>","DOI":"10.1007\/s00521-025-11192-8","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T08:40:59Z","timestamp":1748508059000},"page":"15635-15659","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MSAE-DL: enhancing breast cancer classification through hybrid self-attention integration, feature fusion, and ensemble classification in digital breast tomosynthesis"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8723-9668","authenticated-orcid":false,"given":"Alaa M. Adel","family":"El-Shazli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherin M.","family":"Youssef","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdel Hamid","family":"Soliman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claude","family":"Chibelushi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"11192_CR1","unstructured":"Ferlay J, Ervik M, Lam F, Colombet M, Mery L, Pi\u00f1eros M, Znaor A, Soerjomataram I, Bray F (2021) Global Cancer Observatory: Cancer Today. Lyon, France: International Agency for Research on Cancer. https:\/\/gco.iarc.fr\/today"},{"key":"11192_CR2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n256","author":"I Mittra","year":"2021","unstructured":"Mittra I, Mishra GA, Dikshit RP, Gupta S, Kulkarni VY, Shaikh HK, Shastri SS, Hawaldar R, Gupta S, Pramesh CS, Badwe RA (2021) Effect of screening by clinical breast examination on breast cancer incidence and mortality after 20 years: prospective, cluster randomised controlled trial in Mumbai. BMJ. https:\/\/doi.org\/10.1136\/bmj.n256","journal-title":"BMJ"},{"key":"11192_CR3","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1016\/j.rcl.2010.06.009","volume":"48","author":"MA Helvie","year":"2010","unstructured":"Helvie MA (2010) Digital mammography imaging: breast tomosynthesis and advanced applications. Radiologic Clinics 48:917\u2013929. https:\/\/doi.org\/10.1016\/j.rcl.2010.06.009","journal-title":"Radiologic Clinics"},{"key":"11192_CR4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2016.12.038","volume":"234","author":"W Liu","year":"2017","unstructured":"Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11\u201326. https:\/\/doi.org\/10.1016\/j.neucom.2016.12.038","journal-title":"Neurocomputing"},{"key":"11192_CR5","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1117\/12.2549361","volume":"11312","author":"M Gao","year":"2020","unstructured":"Gao M, Samala RK, Fessler JA, Chan HP (2020) Deep convolutional neural network denoising for digital breast tomosynthesis reconstruction. Medical Imaging 2020: Physics of Medical Imaging. SPIE 11312:173\u2013178. https:\/\/doi.org\/10.1117\/12.2549361","journal-title":"SPIE"},{"key":"11192_CR6","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1109\/tmi.2021.3066896","volume":"40","author":"M Gao","year":"2021","unstructured":"Gao M, Fessler JA, Chan HP (2021) Deep convolutional neural network with adversarial training for denoising digital breast tomosynthesis images. IEEE Trans Med Imaging 40:1805\u20131816. https:\/\/doi.org\/10.1109\/tmi.2021.3066896","journal-title":"IEEE Trans Med Imaging"},{"key":"11192_CR7","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1002\/mp.14779","volume":"48","author":"T Su","year":"2021","unstructured":"Su T, Deng X, Yang J, Wang Z, Fang S, Zheng H, Liang D, Ge Y (2021) DIR-DBTnet: Deep iterative reconstruction network for three-dimensional digital breast tomosynthesis imaging. Med Phys 48:2289\u20132300. https:\/\/doi.org\/10.1002\/mp.14779","journal-title":"Med Phys"},{"key":"11192_CR8","doi-asserted-by":"publisher","unstructured":"Sulaiman SN, Normazli MH, Harron NA, Karim NK, Ahmad KA, Soh ZH (2022) A Convolutional Neural Network Model for Image Enhancement of Extremely Dense Breast Tissue in Digital Breast Tomosynthesis Images. IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE). https:\/\/doi.org\/10.1109\/iccsce54767.2022.9935647","DOI":"10.1109\/iccsce54767.2022.9935647"},{"key":"11192_CR9","doi-asserted-by":"publisher","unstructured":"Saifudin SA, Sulaiman SN, Karim NK, Osman MK, Isa IS, Harron NA (2022) A comparative study of unsharp masking filters for enhancement of digital breast tomosynthesis images. IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE). https:\/\/doi.org\/10.1109\/iccsce54767.2022.9935638","DOI":"10.1109\/iccsce54767.2022.9935638"},{"key":"11192_CR10","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3390\/jimaging9060119","volume":"9","author":"AM Mota","year":"2023","unstructured":"Mota AM, Mendes J, Matela N (2023) Digital Breast Tomosynthesis: Towards Dose Reduction through Image Quality Improvement. Journal of Imaging 9:119. https:\/\/doi.org\/10.3390\/jimaging9060119","journal-title":"Journal of Imaging"},{"key":"11192_CR11","doi-asserted-by":"publisher","first-page":"2299","DOI":"10.1109\/ted.2022.3161402","volume":"69","author":"AK Visvkarma","year":"2022","unstructured":"Visvkarma AK, Sehra K, Laishram R, Malik A, Sharma S, Kumar S, Rawal DS, Vinayak S, Saxena M (2022) Impact of gamma radiations on static, pulsed I-V, and RF performance parameters of AlGaN\/GaN HEMT. IEEE Trans Electron Devices 69:2299\u20132306. https:\/\/doi.org\/10.1109\/ted.2022.3161402","journal-title":"IEEE Trans Electron Devices"},{"key":"11192_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109299","volume":"183","author":"X Chen","year":"2024","unstructured":"Chen X, Lv J, Wang Z, Qin G, Zhou Z (2024) Deep-AutoMO: Deep automated multiobjective neural network for trustworthy lesion malignancy diagnosis in the early stage via digital breast tomosynthesis. Comput Biol Med 183:109299","journal-title":"Comput Biol Med"},{"key":"11192_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2024.103805","volume":"78","author":"Z Shao","year":"2024","unstructured":"Shao Z, Cai Y, Hao Y, Hu C, Yu Z, Shen Y, Lu H (2024) AI-based strategies in breast mass\u2264 2 cm classification with mammography and tomosynthesis. The Breast 78:103805","journal-title":"The Breast"},{"key":"11192_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2024.103071","volume":"24","author":"OO Oladimeji","year":"2024","unstructured":"Oladimeji OO, Ayaz H, McLoughlin I, Unnikrishnan S (2024) Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis. Results in Engineering 24:103071. https:\/\/doi.org\/10.1016\/j.rineng.2024.103071","journal-title":"Results in Engineering"},{"key":"11192_CR15","doi-asserted-by":"publisher","unstructured":"Farangis Sajadi Moghadam and Rashidi S (2024) Novel feature extraction based on DCTDOS features for classification of Digital Breast Tomosynthesis images into benign and malignant tumors. Research Square. https:\/\/doi.org\/10.21203\/rs.3.rs-3931625\/v1","DOI":"10.21203\/rs.3.rs-3931625\/v1"},{"key":"11192_CR16","doi-asserted-by":"publisher","unstructured":"Du Y, Hooley RJ, Lewin J, Dvornek NC (2024) SIFT-DBT: Self-supervised Initialization and Fine-Tuning for Imbalanced Digital Breast Tomosynthesis Image Classification. arXiv. https:\/\/doi.org\/10.48550\/arxiv.2403.13148","DOI":"10.48550\/arxiv.2403.13148"},{"key":"11192_CR17","doi-asserted-by":"publisher","first-page":"398","DOI":"10.3390\/tomography9010032","volume":"9","author":"J Mendes","year":"2023","unstructured":"Mendes J, Matela N, Garcia N (2023) Avoiding Tissue Overlap in 2D Images: Single-Slice DBT Classification Using Convolutional Neural Networks. Tomography 9:398\u2013412. https:\/\/doi.org\/10.3390\/tomography9010032","journal-title":"Tomography"},{"key":"11192_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102825","volume":"71","author":"D Muduli","year":"2022","unstructured":"Muduli D, Dash R, Majhi B (2022) Automated diagnosis of breast cancer using multi-modal datasets: A deep convolution neural network based approach. Biomed Signal Process Control 71:102825. https:\/\/doi.org\/10.1016\/j.bspc.2021.102825","journal-title":"Biomed Signal Process Control"},{"key":"11192_CR19","doi-asserted-by":"publisher","unstructured":"Bai J, Jin A, Jin A, Wang T, Yang C, Nabavi S (2022) Applying graph convolution neural network in digital breast tomosynthesis for cancer classification. In Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics 1\u201310. https:\/\/doi.org\/10.1145\/3535508.3545549","DOI":"10.1145\/3535508.3545549"},{"key":"11192_CR20","doi-asserted-by":"publisher","unstructured":"Nogay HS, Akinci TC, Yilmaz M (2021) Comparative experimental investigation and application of five classic pre-trained deep convolutional neural networks via transfer learning for diagnosis of breast cancer. Advances in Science and Technology Research Journal 15:1\u20138. https:\/\/doi.org\/10.12913\/22998624\/137964","DOI":"10.12913\/22998624\/137964"},{"key":"11192_CR21","unstructured":"Buda M, Saha A, Walsh R, Ghate S, Li N, \u015awi\u0119cicki A, Lo JY, Mazurowski MA (2020) Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep learning model. arXiv. https:\/\/arxiv.org\/abs\/2011.07995"},{"key":"11192_CR22","doi-asserted-by":"publisher","first-page":"5736","DOI":"10.3390\/app12115736","volume":"12","author":"AM El-Shazli","year":"2022","unstructured":"El-Shazli AM, Youssef SM, Soliman AH (2022) Intelligent Computer-aided model for efficient diagnosis of digital breast tomosynthesis 3D imaging using Deep Learning. Appl Sci 12:5736. https:\/\/doi.org\/10.3390\/app12115736","journal-title":"Appl Sci"},{"key":"11192_CR23","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems 20. https:\/\/doi.org\/10.1109\/TPAMI.2005.159","DOI":"10.1109\/TPAMI.2005.159"},{"key":"11192_CR24","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","volume":"27","author":"H Peng","year":"2005","unstructured":"Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27:1226\u20131238. https:\/\/doi.org\/10.1109\/TPAMI.2005.159","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11192_CR25","doi-asserted-by":"publisher","first-page":"143","DOI":"10.11613\/BM.2013.018","volume":"23","author":"ML McHugh","year":"2013","unstructured":"McHugh ML (2013) The chi-square test of independence. Biochemia medica 23:143\u2013149","journal-title":"Biochemia medica"},{"key":"11192_CR26","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4694567","author":"H Nasiri","year":"2022","unstructured":"Nasiri H, Alavi SA (2022) A novel framework based on deep learning and ANOVA feature selection method for diagnosis of COVID-19 cases from chest X-ray images. Comput Intell Neurosci. https:\/\/doi.org\/10.1155\/2022\/4694567","journal-title":"Comput Intell Neurosci"},{"key":"11192_CR27","unstructured":"El-Shazli AM, Youssef SM, Soliman AH, Chibelushi C (2024) An Enhanced Framework Employing Feature Fusion for Effective Classification of Digital Breast Tomosynthesis Scans. In 2024 International Conference on Machine Intelligence and Smart Innovation (ICMISI). IEEE"},{"key":"11192_CR28","doi-asserted-by":"crossref","unstructured":"Tardy M, Mateus D (2021) Trainable summarization to improve breast tomosynthesis classification. International Conference on Medical Image Computing and Computer-Assisted Intervention 140\u2013149","DOI":"10.1007\/978-3-030-87234-2_14"},{"key":"11192_CR29","doi-asserted-by":"publisher","unstructured":"Adhikesaven S, Kapoor A, Khowaja AS, Li V, Sabhanayakam K, McMahan L (2022) Predicting the Instance of Breast Cancer within Patients using a Convolutional Neural Network. Journal of Emerging Investigators. https:\/\/doi.org\/10.59720\/22-061","DOI":"10.59720\/22-061"},{"key":"11192_CR30","doi-asserted-by":"publisher","first-page":"3654","DOI":"10.1002\/mp.15598","volume":"49","author":"J Bai","year":"2022","unstructured":"Bai J, Jin A, Wang T, Yang C, Nabavi S (2022) Feature fusion Siamese network for breast cancer detection comparing current and prior mammograms. Med Phys 49:3654\u20133669. https:\/\/doi.org\/10.1002\/mp.15598","journal-title":"Med Phys"},{"key":"11192_CR31","unstructured":"Fogleman S, Otsap J, Cho S (2021) Clinical Diagnosis Support with Convolutional Neural Network by Transfer Learning. SMU Data Science Review 5"},{"key":"11192_CR32","doi-asserted-by":"crossref","unstructured":"Hassan L, Abdel-Nasser M, Saleh A, Puig D (2022) Breast Tumor Classification in Digital Tomosynthesis Based on Deep Learning Radiomics. In Artificial Intelligence Research and Development 269\u2013278","DOI":"10.3233\/FAIA220348"},{"key":"11192_CR33","doi-asserted-by":"publisher","first-page":"619","DOI":"10.3390\/make6010029","volume":"6","author":"L Hassan","year":"2024","unstructured":"Hassan L, Abdel-Nasser M, Saleh A, Puig D (2024) Classifying Breast Tumors in Digital Tomosynthesis by Combining Image Quality-Aware Features and Tumor Texture Descriptors. Machine Learning and Knowledge Extraction 6:619\u2013641","journal-title":"Machine Learning and Knowledge Extraction"},{"key":"11192_CR34","doi-asserted-by":"crossref","unstructured":"Moghadam FS, Rashidi S (2023) Classification of benign and malignant tumors in Digital Breast Tomosynthesis images using Radiomic-based methods. In 2023 13th International Conference on Computer and Knowledge Engineering (ICCKE) 203\u2013208. IEEE","DOI":"10.1109\/ICCKE60553.2023.10326283"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11192-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11192-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11192-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:06:52Z","timestamp":1751886412000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11192-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":34,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11192"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11192-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,29]]},"assertion":[{"value":"14 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}