Citation :

P. Saravanan, S. Saravanakumar, "A Lightweight and Robust CNN Model for the Early Brain Tumour Detection: Novel Optimization and Feature Engineering Strategies," International Journal of Engineering Trends and Technology (IJETT), vol. 73, no. 12, pp. 135-150, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I12P111

Abstract

The Brain Tumor detection is one of the critical and risky tasks in medical imaging, which demands high accuracy and computational efficiency for early diagnosis. The traditional deep learning models often suffer from excessive complexity, making real-time deployment very challenging. Here, a lightweight and robust Convolutional Neural Network (CNN) model is presented for efficient brain tumor detection. This approach combines novel optimization techniques and advanced feature engineering to enhance the classification that is performed while reducing the computational overhead. The model leverages the depth-wise separable convolutions, attention mechanisms, and optimized hyperparameters to enhance the classification accuracy and feature extraction. The evaluation of the model was done on an openly available Brain MRI dataset, by demonstrating the highest performance in terms of precision, accuracy, recall, and F1-score, which is compared to existing CNN-based approaches. Added to this, the model proposed exhibits significantly lower inference time and memory consumption, making it appropriate for implementation in resource-limited environments such as edge devices. The results highlight the potential of the proposed approach in early and efficient brain tumor diagnosis, by contributing to improved clinical decision-making and patient outcomes.

Keywords

Brain Tumor Detection, Convolutional Neural Networks (CNN), Lightweight Deep Learning, Medical Image Analysis, Feature Engineering, Optimization, Edge Computing, MRI Classification, and Early Diagnosis.

References

[1] Jincan Zhang et al., “EFF_D_SVM: A Robust Multi-Type Brain Tumor Classification System,” Frontiers in Neuroscience, vol. 17, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[2] El-Sayed A. El-Dahshan, and Mahmoud M. Bassiouni, “Computational Intelligence Techniques for Human Brain MRI Classification,” International Journal of Imaging Systems and Technology, vol. 28, no. 2, pp. 132-148, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Sounak Chakraborty, “Simultaneous Cancer Classification and Gene Selection with Bayesian Nearest Neighbor Method: An Integrated Approach,” Computational Statistics and Data Analysis, vol. 53, no. 4, pp. 1462-1474, 2009.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Pallavi Tiwari et al., “CNN based Multiclass Brain Tumor Detection Using Medical Imaging,” Computational Intelligence and Neuroscience, vol. 2022, no. 1, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Siyuan Lu, Zhihai Lu, and Yu-Dong Zhang, “Pathological Brain Detection based on Alexnet and Transfer Learning,” Journal of Computational Science, vol. 30, pp. 41-47, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Karen Simonyan, and Andrew Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv Preprint, pp. 1-14, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Christian Szegedy et al., “Rethinking the Inception Architecture for Computer Vision,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826, 2016.
[Google Scholar] [Publisher Link]

[9] Chao Huang et al., “Long-Term Effects of Fire and Harvest on Carbon Stocks of Boreal Forests in Northeastern China,” Annals of Forest Science, vol. 75, no. 2, pp. 1-15, 2018. 
[CrossRef] [Google Scholar] [Publisher Link]

[10] David M. Howard et al., “Genome-Wide Meta-Analysis of Depression Identifies 102 Independent Variants and Highlights the Importance of the Prefrontal Brain Regions,” Nature Neuroscience, vol. 22, no. 3, pp. 343-352, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Xiangyu Zhang et al., “Shufflenet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6848-6856, 2018.
[Google Scholar] [Publisher Link]

[12] Mingxing Tan, and Quoc Le, “Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks,” International Conference on Machine Learning, PMLR, pp. 6105-6114, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Forrest N. Iandola et al., “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size,” arXiv Preprint, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Ashfaq Hussain et al., “An Analysis of Transfer Learning Model for Deep Neural Network-based Automated Brain Tumor Diagnosis from MR Images,” Proceedings of the International Conference on Signal Processing and Computer Vision (SIPCOV-2023), pp. 207-217, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Romany F. Mansour et al., “Artificial Intelligence with Big Data Analytics-Based Brain Intracranial Hemorrhage E-Diagnosis using Ct Images,” Neural Computing and Applications, vol. 35, no. 22, pp. 16037-16049, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Laksh Kadyan et al., “Machine Learning and Clinical Insights Analysis of BMI Dataset Predictive Models,” 2024 4^th International Conference on Data Engineering and Communication Systems (ICDECS), Bangalore, India, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Janjhyam Venkata Naga Ramesh et al., “Application of Convolutional Neural Networks for Cervical Cancer Detection in Women’s Uterus,” 2024 2^nd International Conference on Networking, Embedded and Wireless Systems (ICNEWS), Bangalore, India, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Ashish Vaswani et al., “Attention Is All You Need,” Proceedings of the 31st International Conference on Neural Information Processing Systems, USA, 2017.
[Google Scholar] [Publisher Link]

[19] Jin Liu et al., “A Survey of MRI-Based Brain Tumor Segmentation Methods,” Tsinghua Science and Technology, vol. 19, no. 6, pp. 578-595, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Takowa Rahman, and Md Saiful Islam, “MRI Brain Tumor Classification using Deep Convolutional Neural Network,” 2022 International Conference on Innovations in Science, Engineering and Technology (ICISET), Chittagong, Bangladesh, pp. 451-456, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Supriti Maji et al., “Cotton Crop Certainty Identification Using Deep Learning Techniques,” 2023 14^th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Kamireddy Rasool Reddy, and Ravindra Dhuli, “A Novel Lightweight CNN Architecture for the Diagnosis of Brain Tumors Using MR Images,” Diagnostics, vol. 13, no. 2, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] K.K. Baseer et al., “Analysing Various Regression Models for Data Processing,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 8, pp. 731-736, 2019.
[Google Scholar] [Publisher Link]

[24] G. Swapnal et al., Brain Tumour Detection using MRI Images in CNN, 1^st ed., Advances in Science, Engineering and Technology, CRC Press, pp. 127-132, 2025.
[Google Scholar] [Publisher Link]

[25] Abdullah A. Asiri et al., “Exploring the Power of Deep Learning: Fine-Tuned Vision Transformer for Accurate and Efficient Brain Tumor Detection in MRI Scans,” Diagnostics, vol. 13, no. 12, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[26] C. Sivaraj et al., “Prediction and Comparative Analysis of the Stress Level of Humans by using the Machine Learning Algorithms,” 2024 4^th International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, pp. 942-947, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[27] David N. Louis et al., “The 2021 WHO Classification of Tumors of the Central Nervous System: A Summary,” Neuro-Oncology, vol. 23, no. 8, pp. 1231-1251, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Fabian Isensee et al., “nnU-Net: A Self-Adapting Framework for U-Net-Based Medical Image Segmentation,” Nature Methods, vol. 18, no. 2, pp. 203-211, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Rabeya Bashri Sumona et al., “An Integrated Deep Learning Approach for Enhancing Brain Tumor Diagnosis,” Healthcare Analytics, vol. 8, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[30] François Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 1800-1807, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Barret Zoph et al., “Learning Transferable Architectures for Scalable Image Recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp. 8697-8710, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Saravanan Srinivasan et al., “A Hybrid Deep CNN Model for Brain Tumor Image Multi-Classification,” BMC Med Imaging, vol. 24, no. 1, pp. 1-21, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Geert Litjens et al., “A Survey on Deep Learning in Medical Image Analysis,” Medical Image Analysis, vol. 42, pp. 60-88, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Mark Sandler et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510-4520, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[35] S. Annamalai et al., “Application Domains of Federated Learning,” Model Optimization Methods for Efficient and Edge AI: Federated Learning Architectures, Frameworks and Applications, pp. 127-144, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Hao Dong et al., “Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks,” Medical Image Understanding and Analysis, Springer, Cham, pp. 506-514, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Palani Thanaraj Krishnan et al., “Enhancing Brain Tumor Detection in MRI with a Rotation Invariant Vision Transformer,” Frontiers in Neuroinformatics, vol. 18, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]