Integration of Radiomics and Deep Learning for Advanced MRI-Based Brain Tumor Characterization

Tonmoy Kanti Shaha; Sampad Ghosh; Shamsul Enam Faruquei; Md Jafrul Hasan

doi:10.38032/scse.2026.4.131

Authors

Tonmoy Kanti Shaha Department of Electrical and Electronic Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh
Sampad Ghosh Department of Electrical and Electronic Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh
Shamsul Enam Faruquei Department of Electrical and Electronic Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh
Md Jafrul Hasan Torrens University, Melbourne, Australia

DOI:

https://doi.org/10.38032/scse.2026.4.131

Keywords:

Brain Tumor Classification, Radiomics-Deep Learning Fusion, MRI-Based Diagnosis

Abstract

Accurate brain tumor classification is critical for early diagnosis and effective treatment planning. This study proposes a hybrid framework that integrates handcrafted radiomics descriptors with deep learning features extracted from MRI scans using MobileNetV2. Three models were systematically evaluated: a radiomics-only model, a deep-only model, and a fusion model combining both feature sets. The radiomics-only approach achieved moderate performance with 84.5% accuracy, an F1-score of 0.84, and an AUC of 0.97 on the test set. The deep learning model markedly improved results, attaining 95.9% accuracy, an F1-score of 0.96, and an AUC of 0.996. The proposed fusion model delivered the best outcomes, with 97.1% accuracy, an F1-score of 0.97, and an AUC of 0.998, confirming its robustness and superior discriminative power. These findings demonstrate that combining radiomics with deep representations enhances classification stability and reliability compared to single-modality models. Future research should focus on multi-center validation, integration of clinical data, and explainable AI techniques to advance clinical adoption.

Downloads

PDF

Downloads

Download data is not yet available.

References

[1] X. Huang, X. Huang, K. Wang, H. Bai, X. Lu, and G. Jin, 2025. 2.5D deep learning radiomics and clinical data for predicting occult lymph node metastasis in lung adenocarcinoma. BMC Med Imaging, 25(1). DOI: https://doi.org/10.1186/s12880-025-01759-1

[2] W. Wang, H. Yang, W. Hu, G. Shan, W. Ding, C. Yu, B. Wang, X. Wang, Q. Xu, 2010. Clinical Study of the Necessity of Replanning Before the 25th Fraction During the Course of Intensity-Modulated Radiotherapy for Patients with Nasopharyngeal Carcinoma. International Journal of Radiation Oncology*Biology*Physics, 77(2). DOI: https://doi.org/10.1016/j.ijrobp.2009.08.036

[3] D. Hui, X. Wang, L. Xie, F. Chen, Y. Guo, Y. Luo, and X. He, 2025. Automatic differentiation of Parkinson’s disease motor subtypes based on deep learning and radiomics. Frontiers in Neurology, 16. DOI: https://doi.org/10.3389/fneur.2025.1650985

[4] https://www.researchgate.net/ publication/ 394524847 [Date of access: 18 September 2025]

[5] R. Wang, X. Tian, Z. Wei, Q. Sun and P. Wang, 2025. Fully distributed energy management strategy for DC bus charging stations with three charging modes. Scientific Reports, 15(1009). DOI: https://doi.org/10.1038/s41598-024-84412-1

[6] Z. Lu, B. Zhu, H. Ling and X. Chen, 2025. Deep learning radiomics based on MRI for differentiating tongue cancer T – staging. BMC Cancer, 25(1358). DOI: https://doi.org/10.1186/s12885-025-14627-6

[7] Y. Liang, M. He, W. Chen, L. Li, Y. Dong, G. Liang, H. Huangfu, Z. Jiang and S. He, 2025. Deep learning radiomics nomogram predicts lymph node metastasis in laryngeal squamous cell carcinoma Frontiers in Oncology, 15. DOI: https://doi.org/10.3389/fonc.2025.1573687

[8] L. Zhong, L. Shi, X. Liu, Y. Zhao, L. Gu, W. Bai and Y. Zheng, 2025. Development and validation of a prediction model for lymph node metastasis in thyroid cancer: integrating deep learning and radiomics features from intra- and peri-tumoral regions. Gland Surgery, 14(7), pp. 1272–1282. DOI: https://doi.org/10.21037/gs-2025-50

[9] L. Zhang, L. Hu, L. Tan, Z. Zhang, M. Chen, W. Gan, L. Chen, Y. Zou, S. Wang, Y. Pang, Z. Fan and J. Liu, 2025. The dysbiosis of gut microbiota and dysregulation of metabolites in IgA nephropathy and membranous nephropathy. Frontiers in Medicine, 12. DOI: https://doi.org/10.3389/fmed.2025.1618947

[10] B. Yu, Y. Luo, S. Tan, L. Cui, X. Liu and Q. Zhou, 2025. Postoperative Anxiety in Childbearing-Age Women with PTMC: Comparison Between Traditional Surgery and Thermal Ablation. Cancer Management and Research, 17, pp. 2143-2152. DOI: https://doi.org/10.2147/CMAR.S538777

[11] A. M. Bejar et al., 2025. Multi-center evaluation of radiomics and deep learning to stratify malignancy risk of IPMNs. Research Square. DOI: https://doi.org/10.21203/rs.3.rs-6622868/v1