{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T01:16:54Z","timestamp":1791940614265,"version":"4.3.4"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002744","name":"Bar-Ilan University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002744","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Glioma, pituitary tumors, and meningiomas constitute the major types of primary brain tumors. The challenge in achieving a definitive diagnosis stem from the brain\u2019s complex structure, limited accessibility for precise imaging, and the resemblance between different types of tumors. An alternative and promising solution is the application of artificial intelligence (AI), specifically through deep learning models. We developed multiple lightweight deep learning models ResNet-18 (both pretrained on ImageNet and trained from scratch), ResNet-34, ResNet-50, and a custom CNN to classify glioma, meningioma, pituitary tumor, and no tumor MRI scans. A dataset of 7023 images was employed, split into 5712 for training and 1311 for validation. Each model was evaluated via accuracy, area under the curve (AUC), sensitivity, specificity, and confusion matrices. We compared our models to SOTA methods such as SAlexNet and TumorGANet, highlighting computational efficiency and classification performance. ResNet pretrained achieved 98.5\u201399.2% accuracy and near-perfect validation metrics, with an overall AUC of 1.0 and average sensitivity and specificity both exceeding 97% across the four classes. In comparison, ResNet-18 trained from scratch and the custom CNN achieved 91.99% and 87.03% accuracy, respectively, with AUCs ranging from 0.94 to 1.00. Error analysis revealed moderate misclassification of meningiomas as gliomas in non-pretrained models. Learning rate optimization facilitated stable convergence, and loss metrics indicated effective generalization with minimal overfitting. Our findings confirm that a moderately sized, transfer-learned network (ResNet-18) can deliver high diagnostic accuracy and robust performance for four-class brain tumor classification. This approach aligns with the goal of providing efficient, accurate, and easily deployable AI solutions, particularly for smaller clinical centers with limited computational resources. Future studies should incorporate multi-sequence MRI and extended patient cohorts to further validate these promising results.<\/jats:p>","DOI":"10.1007\/s10278-025-01686-1","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T16:00:09Z","timestamp":1758297609000},"page":"2309-2318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Lightweight Transfer Learning Models for Multi-Class Brain Tumor Classification: Glioma, Meningioma, Pituitary Tumors, and No Tumor MRI Screening"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7542-8608","authenticated-orcid":false,"given":"Alon","family":"Gorenshtein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Liba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avner","family":"Goren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"1686_CR1","doi-asserted-by":"publisher","unstructured":"Ostrom QT, Cioffi G, Waite K, Kruchko C, Barnholtz-Sloan JS. CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2014\u20132018.\u00a0Neuro Oncol. 2021;23(12 Suppl 2):iii1-iii105. https:\/\/doi.org\/10.1093\/neuonc\/noab200","DOI":"10.1093\/neuonc\/noab200"},{"key":"1686_CR2","doi-asserted-by":"publisher","unstructured":"Ellingson BM, Bendszus M, Boxerman J, et al. Consensus recommendations for a standardized Brain Tumor Imaging Protocol in clinical trials.\u00a0Neuro Oncol. 2015;17(9):1188-1198. https:\/\/doi.org\/10.1093\/neuonc\/nov095","DOI":"10.1093\/neuonc\/nov095"},{"key":"1686_CR3","doi-asserted-by":"publisher","unstructured":"Yan PF, Yan L, Zhang Z, et al. Accuracy of conventional MRI for preoperative diagnosis of intracranial tumors: A retrospective cohort study of 762 cases.\u00a0Int J Surg. 2016;36(Pt A):109-117. https:\/\/doi.org\/10.1016\/j.ijsu.2016.10.023","DOI":"10.1016\/j.ijsu.2016.10.023"},{"key":"1686_CR4","doi-asserted-by":"publisher","unstructured":"Khalighi S, Reddy K, Midya A, Pandav KB, Madabhushi A, Abedalthagafi M. Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment.\u00a0NPJ Precis Oncol. 2024;8(1):80. Published 2024 Mar 29. https:\/\/doi.org\/10.1038\/s41698-024-00575-0","DOI":"10.1038\/s41698-024-00575-0"},{"key":"1686_CR5","doi-asserted-by":"publisher","unstructured":"Carrete LR, Young JS, Cha S. Advanced Imaging Techniques for Newly Diagnosed and Recurrent Gliomas.\u00a0Front Neurosci. 2022;16:787755. Published 2022 Feb 23. https:\/\/doi.org\/10.3389\/fnins.2022.787755","DOI":"10.3389\/fnins.2022.787755"},{"key":"1686_CR6","doi-asserted-by":"publisher","unstructured":"Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI.\u00a0Z Med Phys. 2019;29(2):102-127. https:\/\/doi.org\/10.1016\/j.zemedi.2018.11.002","DOI":"10.1016\/j.zemedi.2018.11.002"},{"key":"1686_CR7","doi-asserted-by":"publisher","unstructured":"Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis.\u00a0Med Image Anal. 2017;42:60-88. https:\/\/doi.org\/10.1016\/j.media.2017.07.005","DOI":"10.1016\/j.media.2017.07.005"},{"key":"1686_CR8","doi-asserted-by":"publisher","unstructured":"Ardalan Z, Subbian V. Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review.\u00a0Front Artif Intell. 2022;5:780405. Published 2022 Feb 21. https:\/\/doi.org\/10.3389\/frai.2022.780405","DOI":"10.3389\/frai.2022.780405"},{"key":"1686_CR9","doi-asserted-by":"publisher","unstructured":"Valverde JM, Imani V, Abdollahzadeh A, et al. Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review.\u00a0J Imaging. 2021;7(4):66. Published 2021 Apr 1. https:\/\/doi.org\/10.3390\/jimaging7040066","DOI":"10.3390\/jimaging7040066"},{"key":"1686_CR10","doi-asserted-by":"publisher","unstructured":"Kim HE, Cosa-Linan A, Santhanam N, Jannesari M, Maros ME, Ganslandt T. Transfer learning for medical image classification: a literature review.\u00a0BMC Med Imaging. 2022;22(1):69. Published 2022 Apr 13. https:\/\/doi.org\/10.1186\/s12880-022-00793-7","DOI":"10.1186\/s12880-022-00793-7"},{"key":"1686_CR11","doi-asserted-by":"publisher","unstructured":"Qurat-ul-ain Chaudhary, Shahzad Ahmad Qureshi, Touseef Sadiq, Anila Usman, Ambreen Khawar, Syed Taimoor Hussain Shah, Aziz ul Rehman, SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification, Results in Engineering, Volume 25, 2025, 104025, ISSN 2590\u20131230, https:\/\/doi.org\/10.1016\/j.rineng.2025.104025.","DOI":"10.1016\/j.rineng.2025.104025"},{"key":"1686_CR12","doi-asserted-by":"publisher","unstructured":"A. Nag et al., \"TumorGANet: A Transfer Learning and Generative Adversarial Network- Based Data Augmentation Model for Brain Tumor Classification,\" in IEEE Access, vol. 12, pp. 103060-103081, 2024, https:\/\/doi.org\/10.1109\/ACCESS.2024.3429633.","DOI":"10.1109\/ACCESS.2024.3429633"},{"key":"1686_CR13","doi-asserted-by":"publisher","unstructured":"Qureshi, S. A., Raza, S. E. A., Hussain, L., Malibari, A. A., Nour, M. K., Rehman, A. u., Al-Wesabi, F. N., & Hilal, A. M. (2022). Intelligent Ultra-Light Deep Learning Model for Multi-Class Brain Tumor Detection. Applied Sciences, 12(8), 3715. https:\/\/doi.org\/10.3390\/app12083715","DOI":"10.3390\/app12083715"},{"key":"1686_CR14","doi-asserted-by":"publisher","unstructured":"Haque R, Hassan MM, Bairagi AK, Shariful Islam SM. NeuroNet19: an explainable deep neural network model for the classification of brain tumors using magnetic resonance imaging data.\u00a0Sci Rep. 2024;14(1):1524. Published 2024 Jan 17. https:\/\/doi.org\/10.1038\/s41598-024-51867-1","DOI":"10.1038\/s41598-024-51867-1"},{"key":"1686_CR15","doi-asserted-by":"publisher","unstructured":"Ullah\u00a0N,\u00a0Hassan\u00a0M,\u00a0Khan\u00a0JA,\u00a0Anwar\u00a0MS,\u00a0Aurangzeb\u00a0K.\u00a0Enhancing explainability in brain tumor detection: A novel DeepEBTDNet model with LIME on MRI images.\u00a0Int J Imaging Syst Technol.\u00a02024;\u00a034(1):e23012. https:\/\/doi.org\/10.1002\/ima.23012","DOI":"10.1002\/ima.23012"},{"key":"1686_CR16","doi-asserted-by":"publisher","unstructured":"Ullah, N., Javed, A., Alhazmi, A., Hasnain, S. M., Tahir, A., & Ashraf, R. (2023). TumorDetNet: A unified deep learning model for brain tumor detection and classification.\u00a0PloS one,\u00a018(9), e0291200. https:\/\/doi.org\/10.1371\/journal.pone.0291200","DOI":"10.1371\/journal.pone.0291200"},{"key":"1686_CR17","doi-asserted-by":"publisher","unstructured":"Msoud Nickparvar. (2021). Brain Tumor MRI Dataset . Kaggle. https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/2645886","DOI":"10.34740\/KAGGLE\/DSV\/2645886"},{"key":"1686_CR18","doi-asserted-by":"publisher","unstructured":"Ullah, N., Khan, J. A., De Falco, I., & Sannino, G. (2024). Explainable Artificial Intelligence: Importance, Use Domains, Stages, Output Shapes, and Challenges. ACM Computing Surveys, 57(4), 1\u201336. Article 94. https:\/\/doi.org\/10.1145\/3705724","DOI":"10.1145\/3705724"},{"key":"1686_CR19","doi-asserted-by":"publisher","unstructured":"Zuhal Y. Hamd, Eyas G. Osman, Amal I. Alorainy, Aljazi F. Alqahtani, Noor R. Alshammari, Omaymah Bajamal, Sawsan H. Alruwaili, Shahad S. Almohsen, Reema I. Almusallam, Mayeen Uddin Khandaker, The role of machine learning in detecting primary brain tumors in Saudi pediatric patients through MRI images, Journal of Radiation Research and Applied Sciences, Volume 17, Issue 3, 2024, 100956, ISSN 1687\u20138507, https:\/\/doi.org\/10.1016\/j.jrras.2024.100956.","DOI":"10.1016\/j.jrras.2024.100956"},{"key":"1686_CR20","doi-asserted-by":"publisher","unstructured":"Xu W, Fu YL, Zhu D. ResNet and its application to medical image processing: Research progress and challenges.\u00a0Comput Methods Programs Biomed. 2023;240:107660. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107660","DOI":"10.1016\/j.cmpb.2023.107660"},{"key":"1686_CR21","doi-asserted-by":"publisher","unstructured":"K. He, X. Zhang, S. Ren and J. Sun, \"Deep Residual Learning for Image Recognition,\" 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1686_CR22","doi-asserted-by":"crossref","unstructured":"Soto-Romero, G., Escriba, C., Acco, P., Campo, E., & Fourniols, J. Y. (2018). Artificial Intelligence for Health: Towards more intelligence or more artificial medicine?. Current Trends in Biomedical Engineering & Biosciences, 16(5), 555947.","DOI":"10.19080\/CTBEB.2018.16.555947"},{"key":"1686_CR23","doi-asserted-by":"publisher","unstructured":"Patel M, Nguyen HS, Doan N, Gelsomino M, Shabani S, Mueller W. Glioblastoma Mimicking Meningioma: Report of 2 Cases.\u00a0World Neurosurg. 2016;95:624.e9-624.e13. https:\/\/doi.org\/10.1016\/j.wneu.2016.08.048","DOI":"10.1016\/j.wneu.2016.08.048"},{"key":"1686_CR24","doi-asserted-by":"publisher","unstructured":"Wahl B, Cossy-Gantner A, Germann S, Schwalbe NR. Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings?.\u00a0BMJ Glob Health. 2018;3(4):e000798. Published 2018 Aug 29. https:\/\/doi.org\/10.1136\/bmjgh-2018-000798","DOI":"10.1136\/bmjgh-2018-000798"},{"key":"1686_CR25","doi-asserted-by":"publisher","unstructured":"Jalloul M, Miranda-Schaeubinger M, Noor AM, et al. MRI scarcity in low- and middle-income countries.\u00a0NMR Biomed. 2023;36(12):e5022. https:\/\/doi.org\/10.1002\/nbm.5022","DOI":"10.1002\/nbm.5022"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01686-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-025-01686-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01686-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:04:23Z","timestamp":1780391063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-025-01686-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":25,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["1686"],"URL":"https:\/\/doi.org\/10.1007\/s10278-025-01686-1","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"2 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The present study was deemed exempt from the Institutional Review Board (IRB) approval as it only utilized a publicly available dataset and did not involve human subjects. The dataset employed for this research was gathered from openly accessible sources, ensuring complete anonymity and confidentiality of any personal information. Therefore, no ethical concerns regarding human subject involvement were applicable to this investigation, allowing us to proceed without the need for IRB approval.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"All authors have read and approved the final manuscript and consent to its publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}