Integrating Watershed-Based Image Segmentation with Deep CNN Classification for Automated Brain Tumor Detection in MRI Scans
Aditya pandey
Department of Computer Science and Engineering, Galgotias University, Greater Noida, India
Author
📌 DOI: https://doi.org/10.63920/tjths.290626001
🔑 Keywords: Brain Tumor Detection, Watershed Segmentation, Convolutional Neural Network, MRI Analysis, Hybrid Deep Learning, Dice Coefficient
📅 Publication Date: 04 July 2026
📜 License:
This work is licensed under a Creative Commons Attribution 4.0 International License
- Share — Copy and Redistribute the material
- Adapt — Remix, Transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Abstract:
Intracranial neoplasms carry a disproportionate clinical burden, with survival outcomes strongly correlated to the speed and accuracy of initial identification. Radiologists rely heavily on Magnetic Resonance Imaging (MRI) for tumor localization, yet manual interpretation introduces delays and examiner-dependent inconsistencies that can jeopardize treatment planning. This paper proposes a two-stage computational framework that first isolates suspicious tissue boundaries through morphological watershed image segmentation and subsequently classifies the segmented region as malignant or benign using a purpose-built Convolutional Neural Network (CNN). Unlike single-stage approaches that operate on full MRI frames, the proposed pipeline channels the CNN's attention toward anatomically constrained candidate regions, reducing false positive detections and improving gradient quality during training. The model was evaluated on a publicly sourced, class-balanced dataset of axial, coronal, and sagittal brain MRI scans. Segmentation quality was measured via the Dice Similarity Coefficient, yielding a mean score of 0.87 across the test partition. Classification accuracy reached 94.3% on the training set and 90.1% on the held-out validation split, outperforming a baseline single-stage CNN by approximately 3.5 percentage points. The complete pipeline was encapsulated within a Flask-based web interface, enabling point-and-click diagnostic queries without any programming requirement.
Download Full PDF Paper
📖 How to Cite
Aditya P. (2026). Integrating Watershed-Based Image Segmentation with Deep CNN Classification for Automated Brain Tumor Detection in MRI Scans. TEJAS J. Technol. Humanit. Sci.,, Vol. 05, Issue 03. https://doi.org/10.63920/tjths.290626001
📊 Article Metrics
References
[1] K. Kamnitsas, C. Ledig, V. F. J. Newcombe, J. P. Simpson, A. D. Kane, D. K. Menon, D. Rueckert, and B. Glocker, “Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation,” Medical Image Analysis, vol. 36, pp. 61–78, 2017.
[2] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. Int. Conf. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015, pp. 234–241.
[3] J. Cheng, W. Huang, S. Cao, R. Yang, W. Yang, Z. Yun, Z. Wang, and Q. Feng, “Enhanced performance of brain tumor classification via tumor region augmentation and partition,” PLOS ONE, vol. 10, no. 10, p. e0140381, 2017.
[4] A. Hatamizadeh, Y. Tang, V. Nath, D. Yang, A. Myronenko, B. Landman, H. R. Roth, and D. Xu, “UNETR: Transformers for 3D medical image segmentation,” in Proc. IEEE/CVF Winter Conf. Applications of Computer Vision (WACV), 2022, pp. 574–584.
[5] J. Tompson, R. Goroshin, A. Jain, Y. LeCun, and C. Bregler, “Efficient object localization using convolutional networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2015, pp. 648–656.
[6] I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in Proc. Int. Conf. Learning Representations (ICLR), 2019.
[7] R. Müller, S. Kornblith, and G. Hinton, “When does label smoothing help?” in Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019, pp. 4694–4703.
[8] U. Baid, S. Ghodasara, S. Mohan, M. Bilello, E. Calabrese, E. Colak, et al., “The RSNA-ASNR-MICCAI BRATS 2021 benchmark on brain tumor segmentation and radiogenomic classification,” arXiv preprint arXiv:2107.02314, 2021.
[9] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[10] L. Vincent and P. Soille, “Watersheds in digital spaces: An efficient algorithm based on immersion simulations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583–598, 1991.
[11] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. W. M. van der Laak, B. van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017.
[12] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.