{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:24:14Z","timestamp":1793042654985,"version":"4.5.0"},"reference-count":38,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T00:00:00Z","timestamp":1737763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Prince Sattam bin Abdulaziz University","award":["PSAU\/2025\/R\/1446"],"award-info":[{"award-number":["PSAU\/2025\/R\/1446"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Breast cancer screening through mammography interpretation is crucial for early detection and improved patient outcomes. However, the manual classification of mammograms using the BIRADS (Breast Imaging-Reporting and Data System) remains challenging due to subtle imaging features, inter-reader variability, and increasing radiologist workload. Traditional computer-aided detection systems often struggle with complex feature extraction and contextual understanding of mammographic abnormalities. To address these limitations, this study proposes MammoViT, a novel hybrid deep learning framework that leverages both ResNet50\u2019s hierarchical feature extraction capabilities and Vision Transformer\u2019s ability to capture long-range dependencies in images. Methods: We implemented a multi-stage approach utilizing a pre-trained ResNet50 model for initial feature extraction from mammogram images. To address the significant class imbalance in our four-class BIRADS dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) to generate synthetic samples for minority classes. The extracted feature arrays were transformed into non-overlapping patches with positional encodings for Vision Transformer processing. The Vision Transformer employs multi-head self-attention mechanisms to capture both local and global relationships between image patches, with each attention head learning different aspects of spatial dependencies. The model was optimized using Keras Tuner and trained using 5-fold cross-validation with early stopping to prevent overfitting. Results: MammoViT achieved 97.4% accuracy in classifying mammogram images across different BIRADS categories. The model\u2019s effectiveness was validated through comprehensive evaluation metrics, including a classification report, confusion matrix, probability distribution, and comparison with existing studies. Conclusions: MammoViT effectively combines ResNet50 and Vision Transformer architectures while addressing the challenge of imbalanced medical imaging datasets. The high accuracy and robust performance demonstrate its potential as a reliable tool for supporting clinical decision-making in breast cancer screening.<\/jats:p>","DOI":"10.3390\/diagnostics15030285","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T06:39:51Z","timestamp":1737959991000},"page":"285","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["MammoViT: A Custom Vision Transformer Architecture for Accurate BIRADS Classification in Mammogram Analysis"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6941-2291","authenticated-orcid":false,"given":"Abdullah G. M.","family":"Al Mansour","sequence":"first","affiliation":[{"name":"Radiology and Medical Imaging Department, College of Applied Medical Sciences, Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1207-2223","authenticated-orcid":false,"given":"Faisal","family":"Alshomrani","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology Technology, College of Applied Medical Science, Taibah University, Medinah 42353, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2773-5544","authenticated-orcid":false,"given":"Abdullah","family":"Alfahaid","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Taibah University, Yanbu 46421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-2806","authenticated-orcid":false,"given":"Abdulaziz T. M.","family":"Almutairi","sequence":"additional","affiliation":[{"name":"Department of Computer, College of Science and Humanities, Shaqra University, Shaqra 11961, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ayana, G., and Choe, S.-W. (2022). BUVITNET: Breast ultrasound detection via vision transformers. Diagnostics, 12.","DOI":"10.3390\/diagnostics12112654"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bonni, S., Brindley, D.N., Chamberlain, M.D., Daneshvar-Baghbadorani, N., Freywald, A., Hemmings, D.G., Hombach-Klonisch, S., Klonisch, T., Raouf, A., and Shemanko, C.S. (2024). Breast Tumor Metastasis and Its Microenvironment: It Takes Both Seed and Soil to Grow a Tumor and Target It for Treatment. Cancers, 16.","DOI":"10.3390\/cancers16050911"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1245\/ASO.2006.03.055","article-title":"Breast cancer diagnosis in women < or = 40 versus 50 to 60 years: Increasing size and stage disparity compared with older women over time","volume":"13","author":"Zabicki","year":"2006","journal-title":"Ann. Surg. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100164","DOI":"10.1016\/j.modpat.2023.100164","article-title":"Incidence, Clinicopathologic Features, HER2 Fluorescence In Situ Hybridization Profile, and Oncotype DX Results of Human Epidermal Growth Factor Receptor 2-Low Breast Cancers: Experience from a Single Academic Center","volume":"36","author":"Hu","year":"2023","journal-title":"Mod. Pathol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Elshami, M., Al-Slaibi, I., Ghithan, R.J., Alser, M., Shurrab, N.R., Ismail, I.O., Mahfouz, I.I., Fannon, A.A., Qawasmi, M.A., and Hawa, M.R. (2022). Women\u2019s awareness of breast cancer symptoms: A national cross-sectional study from Palestine. BMC Public Health, 22.","DOI":"10.1186\/s12889-022-13224-7"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, W., Jiang, R., Cui, N., Li, Q., Yuan, F., and Xiao, Z. (2022). Semi-supervised vision transformer with adaptive token sampling for breast cancer classification. Front. Pharmacol., 13.","DOI":"10.3389\/fphar.2022.929755"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/RBME.2012.2232289","article-title":"Computer-aided breast cancer detection using mammograms: A review","volume":"6","author":"Ganesan","year":"2012","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Li, J., Guan, X., Fan, Z., Ching, L.-M., Li, Y., Wang, X., Cao, W.-M., and Liu, D.-X. (2020). Non-Invasive Biomarkers for Early Detection of Breast Cancer. Cancers, 12.","DOI":"10.3390\/cancers12102767"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Thigpen, D., Kappler, A., and Brem, R. (2018). The role of ultrasound in screening dense breasts\u2014A review of the literature and practical solutions for implementation. Diagnostics, 8.","DOI":"10.3390\/diagnostics8010020"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.clon.2005.02.009","article-title":"The pathology of breast cancer and the role of the histopathology laboratory","volume":"17","author":"Hanby","year":"2005","journal-title":"Clin. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Houser, M., Barreto, D., Mehta, A., and Brem, R.F. (2021). Current and Future Directions of Breast MRI. J. Clin. Med., 10.","DOI":"10.3390\/jcm10235668"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Washington, I., Palm, R.F., White, J., Rosenberg, S.A., and Ataya, D. (2024). The Role of MRI in Breast Cancer and Breast Conservation Therapy. Cancers, 16.","DOI":"10.3390\/cancers16112122"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1016\/j.measurement.2019.05.083","article-title":"Classification of mammogram for early detection of breast cancer using SVM classifier and Hough transform","volume":"146","author":"Vijayarajeswari","year":"2019","journal-title":"Measurement"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.measurement.2015.04.028","article-title":"A new classifier for breast cancer detection based on Na\u00efve Bayesian","volume":"72","author":"Karabatak","year":"2015","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rohan, T.I., Siddik, A.B., Islam, M., and Yusuf, M.S.U. (2019, January 11\u201312). A Precise Breast Cancer Detection Approach Using Ensemble of Random Forest with AdaBoost. Proceedings of the 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh.","DOI":"10.1109\/IC4ME247184.2019.9036697"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"274","DOI":"10.54254\/2755-2721\/40\/20230666","article-title":"The application and analysis of the KNN algorithm in machine learning for breast cancer prediction","volume":"40","author":"Li","year":"2024","journal-title":"Appl. Comput. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106753","DOI":"10.1016\/j.engappai.2023.106753","article-title":"Data augmentation guided breast tumor segmentation based on generative adversarial neural networks","volume":"125","author":"Kannappan","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1007\/s11045-020-00756-7","article-title":"Diagnosis of breast cancer based on modern mammography using hybrid transfer learning","volume":"32","author":"Khamparia","year":"2021","journal-title":"Multidimens. Syst. Signal Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Piantadosi, G., Sansone, M., and Sansone, C. (2018, January 20\u201324). Breast segmentation in MRI via U-Net deep convolutional neural networks. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China. Available online: https:\/\/ieeexplore.ieee.org\/abstract\/document\/8545327\/.","DOI":"10.1109\/ICPR.2018.8545327"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.eswa.2015.10.015","article-title":"Breast cancer classification using deep belief networks","volume":"46","author":"Eldeib","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, X., Zhou, X., and Liu, S. (2019). Parallel structure deep neural network using CNN and RNN with an attention mechanism for breast cancer histology image classification. Cancers, 11.","DOI":"10.3390\/cancers11121901"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"15555","DOI":"10.1007\/s11042-019-7479-6","article-title":"Detection of breast cancer via deep convolution neural networks using MRI images","volume":"79","author":"Yurttakal","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Al-Hejri, A.M., Al-Tam, R.M., Fazea, M., Sable, A.H., Lee, S., and Al-antari, M.A. (2023). ETECADx: Ensemble Self-Attention Transformer Encoder for Breast Cancer Diagnosis Using Full-Field Digital X-ray Breast Images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13010089"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"119024","DOI":"10.1016\/j.eswa.2022.119024","article-title":"CSwin-PNet: A CNN-Swin Transformer combined pyramid network for breast lesion segmentation in ultrasound images","volume":"213","author":"Yang","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5897","DOI":"10.1002\/mp.15156","article-title":"Automatic breast lesion detection in ultrafast DCE-MRI using deep learning","volume":"48","author":"Ayatollahi","year":"2021","journal-title":"Med. Phys."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.mri.2020.03.001","article-title":"A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI","volume":"69","author":"Feng","year":"2020","journal-title":"Magn. Reson. Imaging"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.mri.2020.10.003","article-title":"Deep-learning approach with convolutional neural network for classification of maximum intensity projections of dynamic contrast-enhanced breast magnetic resonance imaging","volume":"75","author":"Fujioka","year":"2021","journal-title":"Magn. Reson. Imaging"},{"key":"ref_28","first-page":"249","article-title":"IB-TransUNet: Combining information bottleneck and transformer for medical image segmentation","volume":"35","author":"Li","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Moon, W.K., Lee, Y.-W., Ke, H.-H., Lee, S.H., Huang, C.-S., and Chang, R.-F. (2020). Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks. Comput. Methods Programs Biomed., 190.","DOI":"10.1016\/j.cmpb.2020.105361"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, Y., Jiang, W., Wang, T., and Lei, B. (2021, January 1\u20135). 3D deep attentive u-net with transformer for breast tumor segmentation from automated breast volume scanner. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Virtual.","DOI":"10.1109\/EMBC46164.2021.9629523"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"8317","DOI":"10.1007\/s00500-022-07235-0","article-title":"Joint Transformer and Multi-scale CNN for DCE-MRI Breast Cancer Segmentation","volume":"26","author":"Qin","year":"2022","journal-title":"Soft Comput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Elaziz, M.A., Dahou, A., Aseeri, A.O., Ewees, A.A., Al-qaness, M.A.A., and Ibrahim, R.A. (2024). Cross vision transformer with enhanced Growth Optimizer for breast cancer detection in IoMT environment. Comput. Biol. Chem., 111.","DOI":"10.1016\/j.compbiolchem.2024.108110"},{"key":"ref_33","first-page":"67","article-title":"Vision transformer-convolution for breast cancer classification using mammography images: A comparative study","volume":"20","author":"Abimouloud","year":"2024","journal-title":"Int. J. Hybrid Intell. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ibrahim, N.M., Ali, B., Al Jawad, F., Al Qanbar, M., Aleisa, R.I., Alhmmad, S.A., Alhindi, K.R., Altassan, M., Al-Muhanna, A.F., and Algofari, H.M. (2023). Breast cancer detection in the equivocal mammograms by AMAN method. Appl. Sci., 13.","DOI":"10.3390\/app13127183"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Nadkarni, S., and Noronha, K. (2023, January 22\u201323). Classification of Mammographic Images using Convolutional Neural Networks. Proceedings of the 2023 IEEE Engineering Informatics, Melbourne, Australia.","DOI":"10.1109\/IEEECONF58110.2023.10520562"},{"key":"ref_36","first-page":"4833","article-title":"Breast cancer detection in Saudi Arabian women using hybrid machine learning on mammographic images","volume":"72","author":"Almalki","year":"2022","journal-title":"Comput. Mater. Contin."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Tsai, K.-J., Chou, M.-C., Li, H.-M., Liu, S.-T., Hsu, J.-H., Yeh, W.-C., Hung, C.-M., Yeh, C.-Y., and Hwang, S.-H. (2022). A high-performance deep neural network model for BI-RADS classification of screening mammography. Sensors, 22.","DOI":"10.3390\/s22031160"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Boumaraf, S., Liu, X., Ferkous, C., and Ma, X. (2020). A new computer-aided diagnosis system with modified genetic feature selection for BI-RADS classification of breast masses in mammograms. BioMed Res. Int., 2020.","DOI":"10.1155\/2020\/7695207"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/3\/285\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:36:15Z","timestamp":1759919775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/3\/285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,25]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["diagnostics15030285"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15030285","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,25]]}}}