A Review on Enhancing Brain Tumor Diagnosis through Machine Learning and Deep Learning Algorithms

Abstract

Crucially for early detection and efficient treatment planning, the study focusses on enhancing brain tumour classification accuracy by means of modern machine learning (ML) and deep learning (DL) techniques. Combining deep learning architectures like Convolutional Neural Networks (CNNs) with the power of ML models including Support Vector Machines (SVM) and Random Forest, the study intends to solve the difficulties in tumour detection and classification using MRI data. Preprocessing MRI data to guarantee quality, feature extraction via CNN layers, and model evaluation utilising measures like accuracy, precision, recall, and F1-score was a strong approach taken. While DL methods used automated feature extraction, producing more complex and exact outputs, ML models depended on handwritten features for classification. The results showed that DL models—especially CNN-based models—achieved exceptional performance, with classification accuracy well above 95%, greatly exceeding conventional ML techniques. These findings show the transforming power of DL in medical imaging by proving its capacity to manage intricate data patterns and improve diagnosis precision. This study emphasises the critical need of artificial intelligence in transforming medical diagnostics, opening the path for more dependable, effective, scalable solutions for brain tumour classification, therefore enabling personalised treatment plans and better patient care.

Introduction

Brain tumors are among the deadliest diseases, requiring fast and accurate diagnosis to improve treatment and survival. Traditional manual analysis of medical images by radiologists is slow and prone to errors. Machine learning (ML) and deep learning (DL) have revolutionized brain tumor detection and classification by automating feature extraction and improving accuracy. Convolutional Neural Networks (CNNs), along with other DL architectures like transformers and RNNs, excel at analyzing complex imaging data such as MRI scans.

Despite their potential, ML and DL face challenges including limited access to large, annotated datasets, high computational costs, and lack of interpretability (“black box” nature). Ethical and legal concerns around data privacy and bias also affect adoption in medical practice. Emerging solutions like explainable AI and federated learning aim to overcome these issues.

Early detection of brain tumors is critical, leading to better prognosis, more treatment options, fewer complications, reduced costs, and improved quality of life. Several recent studies have developed advanced ML and DL models demonstrating high accuracy in tumor classification and segmentation, helping clinicians make faster, more precise decisions.

Overall, the integration of advanced AI technologies with clinical workflows promises to transform brain tumor diagnosis by enabling early, personalized, and accurate medical care, but challenges in data, computation, and trustworthiness remain to be fully addressed.

Conclusion

By combining machine learning (ML) with deep learning (DL) in brain tumour classification, medical diagnostics has been transformed and major progress over conventional techniques is provided. Though their reliance on hand feature extraction limits scalability, ML models—through feature engineering and algorithms like Support Vector Machines (SVM) and Random Forest—have proven successful in classifying tumour kinds. By automating feature extraction and using vast datasets for improved accuracy and efficiency, deep learning—especially through Convolutional Neural Networks (CNNs)—has exceeded these obstacles. Along with temporal analytic capabilities from Recurrent Neural Networks (RNNs), advanced architectures as ResNet and InceptionNet have enabled exact classification and tracking of tumour progression. [36]–[39]. Faster, more accurate diagnosis guaranteed by these technologies helps doctors make timely, wise decisions—qualities essential for patient outcomes. Notwithstanding their potential, issues include the requirement for large amounts of training data, computational resources, and addressing of model training prejudices still exist. Refining these methods depends on ongoing study and cooperation between the medical and computational sectors, hence increasing their accessibility and dependability in many clinical environments. As ML and DL technologies develop, their importance in brain tumour classification is predicted to grow as they provide even more accuracy and help to promote individualised medicine. These developments ultimately represent a turning point in healthcare, stressing the need of artificial intelligence in raising diagnosis capacity and so improving live[40], [41].

References

[1] P. J. Karim, S. R. Mahmood, and M. Sah, “Brain Tumor Classification using Fine-Tuning based Deep Transfer Learning and Support Vector Machine,” Int. J. Comput. Digit. Syst., vol. 13, no. 1, pp. 83–96, 2023, doi: 10.12785/ijcds/130108. [2] S. M. A. H. Shah et al., “Classifying and Localizing Abnormalities in Brain MRI Using Channel Attention Based Semi-Bayesian Ensemble Voting Mechanism and Convolutional Auto-Encoder,” IEEE Access, vol. 11, no. June, pp. 75528–75545, 2023, doi: 10.1109/ACCESS.2023.3294562. [3] T. Vaiyapuri, J. Mahalingam, S. Ahmad, H. A. M. Abdeljaber, E. Yang, and S. Y. Jeong, “Ensemble Learning Driven Computer-Aided Diagnosis Model for Brain Tumor Classification on Magnetic Resonance Imaging,” IEEE Access, vol. 11, no. August, pp. 91398–91406, 2023, doi: 10.1109/ACCESS.2023.3306961. [4] M. A. Raja, A. H. Lone, M. Kaur, P. Kaur, R. S. Sodhi, and . N., “Exploring Machine Learning Approaches for Predicting Brain Tumors: A Comparative Study,” Int. J. Membr. Sci. Technol., vol. 10, no. 5, pp. 364–374, 2023, doi: 10.15379/ijmst.v10i5.2505. [5] A. Sanchez-Aguilera et al., “Machine learning identifies experimental brain metastasis subtypes based on their influence on neural circuits,” Cancer Cell, vol. 41, no. 9, pp. 1637-1649.e11, 2023, doi: 10.1016/j.ccell.2023.07.010. [6] Y. M. A. Mohammed, S. El Garouani, and I. Jellouli, “A survey of methods for brain tumor segmentation-based MRI images,” J. Comput. Des. Eng., vol. 10, no. 1, pp. 266–293, 2023, doi: 10.1093/jcde/qwac141. [7] F. Putz et al., “The Segment Anything foundation model achieves favorable brain tumor autosegmentation accuracy on MRI to support radiotherapy treatment planning,” arXiv Prepr. , 2023, doi: 10.1007/s00066-024-02313-8. [8] “Brain tumor classification using machine learning - - Image Search results.” https://in.images.search.yahoo.com/yhs/search;_ylt=AwrKBOkMTVFn9zAe4DnnHgx.;_ylu=Y29sbwMEcG9zAzEEdnRpZAMEc2VjA3BpdnM-?p=Brain+tumor+classification+using+machine+learning&vm=r&type=fc_AC934C13286_s58_g_e_d022424_n9998_c999¶m1=7¶m2=eJwtj8tugzAQRX%2FFy0QKMB4%2FwGaXQD%2Bg6qpRFo5xiMVTQEXVr6%2BdVrM5986d0Uzrm2t5e68oABYgr6fbGLRSqggYW4DIkQdh%2F%2FxAfg6IHKjmCkALYahGZRvtBJP6zpjT9qELReO61k0h7ceAXybQMP34vjeZSIEcdj82076ScSMUUihJMCQvybfkR2LmuXe7u3d%2BywTLUybJoXtuQ38ive8caZ3tpiOxz2UaXEYZTSEWWc3DLP5%2FJJ67vn6MB6xuefFFYs7OFSSVBJZQWtfJmReR6NtFhq5SdczbGEZAngAmWHyA1OFDoVLM889fcstZmA%3D%3D&hsimp=yhs-2461&hspart=fc&ei=UTF-8&fr=yhs-fc-2461#id=10&iurl=https%3A%2F%2Fmiro.medium.com%2Fmax%2F1400%2F0*KTBn-EUESlL--Izr.jpg&action=click (accessed Dec. 05, 2024). [9] B. Wang et al., “Quantitative Cerebral Blood Volume Image Synthesis from Standard MRI Using Image-to-Image Translation for Brain Tumors,” Radiology, vol. 308, no. 2, 2023, doi: 10.1148/radiol.222471. [10] S. Virupakshappa, S. Veerashetty, and N. Ambika, “Computer-Aided Diagnosis Applied To Mri Images of Brain Tumor Using Spatial Fuzzy Level Set and Ann Classifier,” Scalable Comput., vol. 23, no. 4, pp. 233–249, 2022, doi: 10.12694/scpe.v23i4.2024. [11] A. Sorte, R. Sathe, S. Yadav, and C. Bhole, “Brain Tumor Classification using Deep Learning,” 5th IEEE Int. Conf. Adv. Sci. Technol. ICAST 2022, vol. 6, no. 7, pp. 440–443, 2022, doi: 10.1109/ICAST55766.2022.10039550. [12] D. Filatov and G. N. A. H. Yar, “Brain Tumor Diagnosis and Classification via Pre-Trained Convolutional Neural Networks,” 2022, [Online]. Available: http://arxiv.org/abs/2208.00768 [13] J. J. Yoo, K. Namdar, and F. Khalvati, “Superpixel Generation and Clustering for Weakly Supervised Brain Tumor Segmentation in MR Images,” pp. 1–9, 2022, [Online]. Available: http://arxiv.org/abs/2209.09930 [14] A. H. Khan et al., “Intelligent Model for Brain Tumor Identification Using Deep Learning,” Appl. Comput. Intell. Soft Comput., vol. 2022, 2022, doi: 10.1155/2022/8104054. [15] E. M. Senan, M. E. Jadhav, T. H. Rassem, A. S. Aljaloud, B. A. Mohammed, and Z. G. Al-Mekhlafi, “Early Diagnosis of Brain Tumour MRI Images Using Hybrid Techniques between Deep and Machine Learning,” Comput. Math. Methods Med., vol. 2022, 2022, doi: 10.1155/2022/8330833. [16] J. Amin, M. A. Anjum, M. Sharif, S. Jabeen, S. Kadry, and P. Moreno Ger, “A New Model for Brain Tumor Detection Using Ensemble Transfer Learning and Quantum Variational Classifier,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/3236305. [17] H. Kibriya, R. Amin, A. H. Alshehri, M. Masood, S. S. Alshamrani, and A. Alshehri, “A Novel and Effective Brain Tumor Classification Model Using Deep Feature Fusion and Famous Machine Learning Classifiers,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/7897669. [18] Y. M. Roopa, G. N. Kumar, Y. V. S. Harsha, and P. S. Aditya, “Detection of Brain Tumor Types Using Deep Learning,” Proc. 2nd Int. Conf. Artif. Intell. Smart Energy, ICAIS 2022, vol. 6, no. 3, pp. 459–465, 2022, doi: 10.1109/ICAIS53314.2022.9742731. [19] V. Sanjay and P. Swarnalatha, “A Survey on Various Machine Learning Techniques for an Efficient Brain Tumor Detection from MRI Images,” Int. J. Electr. Electron. Res., vol. 10, no. 2, pp. 177–182, 2022, doi: 10.37391/IJEER.100222. [20] T. Rahman and M. S. Islam, “MRI brain tumor detection and classification using parallel deep convolutional neural networks,” Meas. Sensors, vol. 26, no. December 2022, p. 100694, 2023, doi: 10.1016/j.measen.2023.100694. [21] Z. Wang, Y. Liu, and X. Niu, “Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology,” Semin. Cancer Biol., vol. 93, no. April, pp. 83–96, 2023, doi: 10.1016/j.semcancer.2023.04.009. [22] M. I. Mahmud, M. Mamun, and A. Abdelgawad, “A Deep Analysis of Brain Tumor Detection from MR Images Using Deep Learning Networks,” Algorithms, vol. 16, no. 4, pp. 1–19, 2023, doi: 10.3390/a16040176. [23] A. B. Abdusalomov, M. Mukhiddinov, and T. K. Whangbo, “Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging,” Cancers (Basel)., vol. 15, no. 16, 2023, doi: 10.3390/cancers15164172. [24] M. Kaurav et al., “Dendrimer: An update on recent developments and future opportunities for the brain tumors diagnosis and treatment,” Front. Pharmacol., vol. 14, no. March, pp. 1–20, 2023, doi: 10.3389/fphar.2023.1159131. [25] R. Asad, S. ur Rehman, A. Imran, J. Li, A. Almuhaimeed, and A. Alzahrani, “Computer-Aided Early Melanoma Brain-Tumor Detection Using Deep-Learning Approach,” Biomedicines, vol. 11, no. 1, pp. 1–22, 2023, doi: 10.3390/biomedicines11010184. [26] A. M. Rauschecker, J. D. Rudie, L. Xie, J. Wang, and J. C. Gee, “Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI,” Radiology, vol. 00, pp. 1–12, 2020. [27] N. Galldiks et al., “The use of dynamic O-(2-18F-fluoroethyl)-l-tyrosine PET in the diagnosis of patients with progressive and recurrent glioma,” Neuro. Oncol., vol. 17, no. 9, pp. 1293–1300, 2015, doi: 10.1093/neuonc/nov088. [28] R. Nanmaran et al., “Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine,” Comput. Math. Methods Med., vol. 2022, 2022, doi: 10.1155/2022/7137524. [29] “Early Disease Detection - - Image Search results.” https://in.images.search.yahoo.com/yhs/search;_ylt=Awrx_pa3TFFnNjEe31PnHgx.;_ylu=Y29sbwMEcG9zAzEEdnRpZAMEc2VjA3BpdnM-?p=Early+Disease+Detection&vm=r&type=fc_AC934C13286_s58_g_e_d022424_n9998_c999¶m1=7¶m2=eJwtj8tugzAQRX%2FFy0QKMB4%2FwGaXQD%2Bg6qpRFo5xiMVTQEXVr6%2BdVrM5986d0Uzrm2t5e68oABYgr6fbGLRSqggYW4DIkQdh%2F%2FxAfg6IHKjmCkALYahGZRvtBJP6zpjT9qELReO61k0h7ceAXybQMP34vjeZSIEcdj82076ScSMUUihJMCQvybfkR2LmuXe7u3d%2BywTLUybJoXtuQ38ive8caZ3tpiOxz2UaXEYZTSEWWc3DLP5%2FJJ67vn6MB6xuefFFYs7OFSSVBJZQWtfJmReR6NtFhq5SdczbGEZAngAmWHyA1OFDoVLM889fcstZmA%3D%3D&hsimp=yhs-2461&hspart=fc&ei=UTF-8&fr=yhs-fc-2461#id=2&iurl=https%3A%2F%2Fadmin.binariks.com%2Fstorage%2F2023-09%2Fbin-picture-080923-v03-main.webp&action=click (accessed Dec. 05, 2024). [30] J. Amin, M. Sharif, A. Haldorai, M. Yasmin, and R. S. Nayak, “Brain tumor detection and classification using machine learning: a comprehensive survey,” Complex Intell. Syst., vol. 8, no. 4, pp. 3161–3183, 2022, doi: 10.1007/s40747-021-00563-y. [31] S. Chatterjee, F. A. Nizamani, A. Nürnberger, and O. Speck, “Classification of brain tumours in MR images using deep spatiospatial models,” Sci. Rep., vol. 12, no. 1, pp. 1–11, 2022, doi: 10.1038/s41598-022-05572-6. [32] N. Noreen, S. Palaniappan, A. Qayyum, I. Ahmad, M. Imran, and M. Shoaib, “A Deep Learning Model Based on Concatenation Approach for the Diagnosis of Brain Tumor,” IEEE Access, vol. 8, pp. 55135–55144, 2020, doi: 10.1109/ACCESS.2020.2978629. [33] D. H. Tran et al., “Quantitation of Tissue Resection Using a Brain Tumor Model and 7-T Magnetic Resonance Imaging Technology,” World Neurosurg., vol. 148, pp. e326–e339, 2021, doi: 10.1016/j.wneu.2020.12.141. [34] F. Hamami and I. A. Dahlan, “Classification of Tomato Disease using Convolutional Neural Network,” IOP Conf. Ser. Earth Environ. Sci., vol. 1038, no. 1, pp. 18–23, 2022, doi: 10.1088/1755-1315/1038/1/012032. [35] G. Garg and R. Garg, “Brain Tumor Detection and Classification based on Hybrid Ensemble Classifier,” no. 3, pp. 1–18, 2021, [Online]. Available: http://arxiv.org/abs/2101.00216 [36] T. Zhou, S. Canu, P. Vera, and S. Ruan, “Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalities,” IEEE Trans. Image Process., vol. 30, no. April, pp. 4263–4274, 2021, doi: 10.1109/TIP.2021.3070752. [37] Y. Wang et al., “Modality-Pairing Learning for Brain Tumor Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12658 LNCS, pp. 230–240, 2021, doi: 10.1007/978-3-030-72084-1_21. [38] X. Zhang, L. Yao, X. Wang, J. Monaghan, D. Mcalpine, and Y. Zhang, “A survey on deep learning-based non-invasive brain signals: recent advances and new frontiers,” J. Neural Eng., vol. 18, no. 3, 2021, doi: 10.1088/1741-2552/abc902. [39] P. Saxena, A. Maheshwari, and S. Maheshwari, “Predictive Modeling of Brain Tumor: A Deep Learning Approach,” Adv. Intell. Syst. Comput., vol. 1189, pp. 275–285, 2021, doi: 10.1007/978-981-15-6067-5_30. [40] B. Baheti et al., “The Brain Tumor Sequence Registration Challenge: Establishing Correspondence between Pre-Operative and Follow-up MRI scans of diffuse glioma patients,” pp. 1–6, 2021, [Online]. Available: http://arxiv.org/abs/2112.06979 [41] D. Zhang, G. Huang, Q. Zhang, J. Han, J. Han, and Y. Yu, “Cross-modality deep feature learning for brain tumor segmentation,” Pattern Recognit., vol. 110, 2021, doi: 10.1016/j.patcog.2020.107562.

Copyright

Copyright © 2025 Sumit Rajak, Unmukh Datta. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.