{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:19:46Z","timestamp":1777061986500,"version":"3.51.4"},"reference-count":47,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>This work presents the development and evaluation of Artificial Intelligence (AI) models for the automatic classification of brain tumors in Magnetic Resonance Imaging (MRI) scans. Several deep learning architectures were implemented and compared, including VGG-19, ResNet50, EfficientNetB3, Xception, MobileNetV2, DenseNet201, InceptionV3, Vision Transformer (ViT), and an Ensemble model. The models were developed in Python (version 3.12.4) using the Keras and TensorFlow frameworks and trained on a public Brain Tumor MRI dataset containing 7023 images. Data augmentation and hyperparameter optimization techniques were applied to improve model generalization. The results showed high classification performance, with accuracies ranging from 89.47% to 98.17%. The Vision Transformer achieved the best performance, reaching 98.17% accuracy, outperforming traditional Convolutional Neural Network (CNN) architectures. Explainable AI (XAI) methods Grad-CAM, LIME, and Occlusion Sensitivity were employed to assess model interpretability, showing that the models predominantly focused on tumor regions. The proposed approach demonstrated the effectiveness of AI-based systems in supporting early diagnosis of brain tumors, reducing analysis time and assisting healthcare professionals.<\/jats:p>","DOI":"10.3390\/app16020831","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T09:03:10Z","timestamp":1768381390000},"page":"831","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning Approaches for Brain Tumor Classification in MRI Scans: An Analysis of Model Interpretability"],"prefix":"10.3390","volume":"16","author":[{"given":"Emanuela F.","family":"Gomes","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Institute of Engineering\u2014Polytechnic of Porto (ISEP\/IPP), 4249-015 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7410-8872","authenticated-orcid":false,"given":"Ramiro S.","family":"Barbosa","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Institute of Engineering\u2014Polytechnic of Porto (ISEP\/IPP), 4249-015 Porto, Portugal"},{"name":"GECAD-Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, ISEP\/IPP, 4249-015 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Missaoui, R., Hechkel, W., Saadaoui, W., Helali, A., and Leo, M. (2025). Advanced Deep Learning and Machine Learning Techniques for MRI Brain Tumor Analysis: A Review. Sensors, 25.","DOI":"10.3390\/s25092746"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s10462-025-11151-8","article-title":"Automatic brain MRI tumors segmentation based on deep fusion of weak edge and context features","volume":"58","author":"Xiao","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100571","DOI":"10.1016\/j.array.2025.100571","article-title":"Brain tumor detection, classification and segmentation by deep learning models from MRI images: Recent approaches, challenges and future directions","volume":"28","author":"Fahim","year":"2025","journal-title":"Array"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"110553","DOI":"10.1016\/j.patcog.2024.110553","article-title":"Brain tumor segmentation in MRI with multi-modality spatial information enhancement and boundary shape correction","volume":"153","author":"Zhu","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11517-023-02873-4","article-title":"A survey on brain tumor image analysis","volume":"62","author":"Sailunaz","year":"2024","journal-title":"Med Biol. Eng. Comput."},{"key":"ref_6","first-page":"266","article-title":"A survey of methods for brain tumor segmentation-based MRI images","volume":"10","author":"Mohammed","year":"2023","journal-title":"J. Comput. Des. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rios Piedra, E.A., Taira, R.K., El-Saden, S., Ellingson, B.M., Bui, A.A.T., and Hsu, W. (2016, January 24\u201327). Assessing variability in brain tumor segmentation to improve volumetric accuracy and characterization of change. Proceedings of the 2016 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA.","DOI":"10.1109\/BHI.2016.7455914"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rajeyyagari, S., Hung, B.T., and Chakrabarti, P. (2022, January 23\u201325). Applications of Artificial Intelligence in Biomedical Image Processing. Proceedings of the Proceedings of the Second International Conference on Artificial Intelligence and Smart Energy (ICAIS-2022), Coimbatore, India.","DOI":"10.1109\/ICAIS53314.2022.9742773"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.inffus.2022.09.031","article-title":"Medical Image Segmentation Using Deep Semantic-based Methods: A Review of Techniques, Applications and Emerging Trends","volume":"90","author":"Qureshi","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"125543","DOI":"10.1109\/ACCESS.2023.3330465","article-title":"An Explainable AI System for Medical Image Segmentation With Preserved Local Resolution: Mammogram Tumor Segmentation","volume":"11","author":"Farrag","year":"2023","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s10462-025-11221-x","article-title":"Explainable AI and vision transformers for detection and classification of brain tumor: A comprehensive survey","volume":"58","author":"Hosny","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_13","first-page":"1","article-title":"Deep Learning in Medical Image Analysis: A Survey","volume":"1","author":"Agneya","year":"2024","journal-title":"BMS Coll. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3147","DOI":"10.1016\/j.jer.2024.11.003","article-title":"Optimized Deep Learning Model for Medical Image Diagnosis","volume":"13","author":"Samma","year":"2024","journal-title":"J. Eng. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"129182","DOI":"10.1016\/j.neucom.2024.129182","article-title":"Optimized Deep Learning Model for Comprehensive Medical Image Analysis Across Multiple Modalities","volume":"619","author":"Khan","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1016\/j.aej.2025.01.090","article-title":"Evaluating Pre-processing and Deep Learning Methods in Medical Imaging: Combined Effectiveness Across Multiple Modalities","volume":"119","author":"Hung","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_17","unstructured":"Rashed, B.M., and Popescu, N. (2021, January 18\u201319). Machine Learning Techniques for Medical Image Processing. Proceedings of the 9th IEEE International Conference on e-Health and Bioengineering (EHB), Iasi, Romania."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105154","DOI":"10.1016\/j.rineng.2025.105154","article-title":"The Role of Advanced Machine Learning in COVID-19 Medical Imaging: A Technical Review","volume":"26","author":"Fayyaz","year":"2025","journal-title":"Results Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.csbj.2024.12.033","article-title":"Machine Learning Methods for Histopathological Image Analysis: Updates in 2024","volume":"27","author":"Komura","year":"2025","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review","volume":"48","author":"Takahashi","year":"2024","journal-title":"J. Med Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105609","DOI":"10.1016\/j.chemolab.2025.105609","article-title":"Comparative evaluation of lightweight convolutional neural network and vision transformer models for multi-class brain tumor classification using merged large MRI datasets","volume":"269","author":"Attallah","year":"2025","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_22","unstructured":"(2025, April 21). AI Solutions for Radiology. Available online: https:\/\/www.aidoc.com."},{"key":"ref_23","unstructured":"Health, G. (2025, April 21). Health Solutions. Available online: https:\/\/health.google."},{"key":"ref_24","unstructured":"(2025, April 21). AI-Powered Pathology Solutions. Available online: https:\/\/www.pathai.com."},{"key":"ref_25","unstructured":"Viz.ai (2025, April 21). Viz 3D CTATM. Available online: https:\/\/www.viz.ai\/large-vessel-occlusion."},{"key":"ref_26","unstructured":"(2025, April 21). Tempus Pixel Lung. Available online: https:\/\/www.tempus.com\/radiology\/tempus-pixel-lung\/."},{"key":"ref_27","unstructured":"Qure.ai (2025, April 21). Qure.ai. Available online: https:\/\/www.qure.ai."},{"key":"ref_28","unstructured":"(2025, April 21). AI-powered Cancer Screening and Treatment Solutions. Available online: https:\/\/www.lunit.io\/en."},{"key":"ref_29","unstructured":"(2025, May 08). Annotated Ultrasound Liver Images Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/orvile\/annotated-ultrasound-liver-images-dataset."},{"key":"ref_30","unstructured":"(2025, May 08). Human Bone Fractures Image Dataset (HBFMID). Available online: https:\/\/www.kaggle.com\/datasets\/orvile\/human-bone-fractures-image-dataset-hbfmid."},{"key":"ref_31","unstructured":"Oza, P., Oza, U., Oza, R., Sharma, P., Patel, S., Kumar, P., and Gohel, B. (2025, May 08). Digital Mammography Dataset for Breast Cancer Diagnosis Research (DMID)\u2014Breast Cancer Mammography Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/orvile\/dmid-breast-cancer-mammography-dataset?select=ROI+Masks."},{"key":"ref_32","unstructured":"Gonz\u00e1lez, J.L. (2025, May 10). Tumores Cerebrales\u2014MRI Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/gonzajl\/tumores-cerebrales-mri-dataset."},{"key":"ref_33","unstructured":"Mooney, P. (2025, May 10). Chest X-Ray Images (Pneumonia) Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/paultimothymooney\/chest-xray-pneumonia."},{"key":"ref_34","unstructured":"Heller, N., Sathianathen, N., Kalapara, A., Walczak, E., Moore, K., Kaluzniak, H., Rosenberg, J., Blake, P., Rengel, Z., and Oestreich, M. (2025, May 10). KiTS19-Kidney Tumor Segmentation Challenge Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/orvile\/kits19-png-zipped."},{"key":"ref_35","unstructured":"Tschandl, P., Rosendahl, C., and Kittler, H. (2025, May 12). HAM10000: Human Against Machine with 10,000 Training Images\u2014A Large Collection of Multi-Source Dermatoscopic Images of Pigmented Skin Lesions. Available online: https:\/\/www.kaggle.com\/datasets\/kmader\/skin-cancer-mnist-ham10000."},{"key":"ref_36","unstructured":"Soares, E., Angelov, P., Biaso, S., Fr\u00f3es, M.H., and Abe, D.K. (2025, May 10). SARS-CoV-2 CT-Scan Dataset: A Large Dataset of Real Patients CT Scans for SARS-CoV-2 Identification. Available online: https:\/\/www.kaggle.com\/datasets\/plameneduardo\/sarscov2-ctscan-dataset."},{"key":"ref_37","unstructured":"(2025, May 10). DRIVE\u2014Digital Retinal Images for Vessel Extraction. Available online: https:\/\/www.kaggle.com\/datasets\/andrewmvd\/drive-digital-retinal-images-for-vessel-extraction."},{"key":"ref_38","unstructured":"Daithal, N. (2025, May 10). ImageOASIS Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/ninadaithal\/imagesoasis."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"200:1","DOI":"10.1145\/3505244","article-title":"Transformers in Vision: A Survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"M\u00fcller, D., Soto-Rey, I., and Kramer, F. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Res. Notes, 15.","DOI":"10.1186\/s13104-022-06096-y"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tiwari, R., and Agrawal, R. (2024, January 19\u201320). Unmasking VGG16: LIME Visualizations for Brain Tumor Diagnosis. Proceedings of the 2024 International Conference on Computer Vision and Machine Intelligence (CVMI), Prayagraj, India.","DOI":"10.1109\/CVMI61877.2024.10781708"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"100270","DOI":"10.1016\/j.health.2023.100270","article-title":"Transfer learning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging","volume":"4","author":"Islam","year":"2023","journal-title":"Healthc. Anal."},{"key":"ref_44","unstructured":"Nickparvar, M. (2025, July 19). Brain Tumor MRI Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/masoudnickparvar\/brain-tumor-mri-dataset?select=Training."},{"key":"ref_45","unstructured":"Chollet, F. (2018). Deep Learning with Python, Manning Publications."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1002\/wics.182","article-title":"Bootstrap","volume":"3","author":"Hesterberg","year":"2011","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"ref_47","unstructured":"Draelos, R.L., and Carin, L. (2020). Use HIRE-SCAM instead of Grad-CAM for faithful explanations of convolutional neural networks. arXiv."}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/16\/2\/831\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T09:26:52Z","timestamp":1768382812000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/16\/2\/831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["app16020831"],"URL":"https:\/\/doi.org\/10.3390\/app16020831","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]}}}