Innovative Deep Learning Models for Accurate Segmentation and Classification in Oncological Diagnosis Data
Archana R
Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur-603 203, Chengalpattu, Tamil Nadu, India.
Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur-603 203, Chengalpattu, Tamil Nadu, India.
Accurate identification and classification of tumours are essential for effectively diagnosing and treating hepatocellular carcinoma and metastatic disease. However, the heterogeneous nature of tumours, characterized by irregular boundaries and variations in shape, size, and location, poses significant challenges for precise and automated segmentation and classification. With recent advances in artificial intelligence, deep learning has emerged as a powerful tool for medical image analysis. Although current clinical methods offer baseline performance in tumour classification, there is still considerable scope for improving diagnostic accuracy. This research proposes an innovative deep-learning framework to enhance the segmentation and classification of tumours. The approach begins by enhancing image contrast using histogram equalization and reducing noise via a median filter, regions are then accurately segmented from abdominal CT images using Mask R-CNN, a state-of-the-art model based on region-based convolutional neural networks. The segmented outputs are further processed using an Enhanced Swin Transformer to mitigate overfitting and boost classification performance. Experimental results demonstrate that the proposed model achieves superior accuracy and robustness across diverse CT image datasets, exhibiting strong performance even in noise.
Keywords
Segmentation, Deep Learning, RCNN Classification, CT Image, Mask R-CNN.
E. Sert, F. Özyurt, and A. Doğantekin, “A new approach for brain tumor diagnosis system: Single image super resolution based maximum fuzzy entropy segmentation and convolutional neural network,” Medical Hypotheses, vol. 133, p. 109413, Dec. 2019, doi:10.1016/ j. mehy.2019.109413.
G. Wan and L. Yao, “LMFRNet: A Lightweight Convolutional Neural Network Model for Image Analysis,” Electronics, vol. 13, no. 1, p.129, Dec. 2023, doi: 10.3390/electronics13010129.
R. Krishnan and S. Durairaj, “Reliability and performance of resource efficiency in dynamic optimization scheduling using multi-agent microservice cloud-fog on IoT applications,” Computing, vol. 106, no. 12, pp. 3837–3878, Jun. 2024, doi: 10.1007/s00607-024-01301-1.
H. Gunduz and S. Gunal, “A lightweight convolutional neural network (CNN) model for diatom classification: DiatomNet,” PeerJ Computer Science, vol. 10, p. e1970, Mar. 2024, doi: 10.7717/peerj-cs.1970.
F. Hu, H. Hu, H. Xu, J. Xu, and Q. Chen, “Dilated Heterogeneous Convolution for Cell Detection and Segmentation Based on Mask R-CNN,”Sensors, vol. 24, no. 8, p. 2424, Apr. 2024, doi: 10.3390/s24082424.
S. Vani, P. Malathi, V. J. Ramya, B. Sriman, M. Saravanan, and R. Srivel, “An efficient black widow optimization-based faster R-CNN for classification of COVID-19 from CT images,” Multimedia Systems, vol. 30, no. 2, Apr. 2024, doi: 10.1007/s00530-024-01281-4.
A. M. Hendi, M. A. Hossain, N. A. Majrashi, S. Limkar, B. M. Elamin, and M. Rahman, “Adaptive Method for Exploring Deep Learning Techniques for Subtyping and Prediction of Liver Disease,” Applied Sciences, vol. 14, no. 4, p. 1488, Feb. 2024, doi: 10.3390/app14041488.
A. Kesana, J. Nallola, R. T. Bootapally, S. Amaraneni, and G. V. Subba Reddy, “Brain Tumor Detection Using YOLOv5 and Faster R-CNN,” 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), pp.1–6, May 2023, doi: 10.1109/vitecon58111.2023.10157773.
R. Khan, L. Su, A. Zaman, H. Hassan, Y. Kang, and B. Huang, “Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification,” Heliyon, vol. 10, no. 10, p. e30528, May 2024, doi: 10.1016/j.heliyon.2024.e30528.
B. Olimov, S.-J. Koh, and J. Kim, “AEDCN-Net: Accurate and Efficient Deep Convolutional Neural Network Model for Medical Image Segmentation,” IEEE Access, vol. 9, pp. 154194–154203, 2021, doi: 10.1109/access.2021.3128607.
M. Ahmad et al., “A Lightweight Convolutional Neural Network Model for Liver Segmentation in Medical Diagnosis,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1–16, Mar. 2022, doi: 10.1155/2022/7954333.
Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9992–10002, Oct. 2021, doi: 10.1109/iccv48922.2021.00986.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, doi: 10.1109/cvpr.2016.90.
M. Tan and Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proc. of the 36th International Conference on Machine Learning (ICML), 2019, pp. 6105-6114.
G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, doi: 10.1109/cvpr.2017.243.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,” Computer Vision – ECCV 2018, pp. 833–851, 2018, doi: 10.1007/978-3-030-01234-2_49.
H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid Scene Parsing Network,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, doi: 10.1109/cvpr.2017.660.
J. Zhang, J. Yang, and M. Zhao, “Automatic Segmentation Algorithm of Magnetic Resonance Image in Diagnosis of Liver Cancer Patients under Deep Convolutional Neural Network,” Scientific Programming, vol. 2021, pp. 1–13, Sep. 2021, doi: 10.1155/2021/4614234.
R. M, S. Durairaj, S. S, and A. alias B. S, “Hybrid key management WSN protocol to enhance network performance using ML techniques for IoT application in cloud environment,” Peer-to-Peer Networking and Applications, vol. 18, no. 4, May 2025, doi: 10.1007/s12083-025-01967-0.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Archana R and Anand L;
Methodology: Anand L;
Visualization: Archana R;
Investigation: Archana R and Anand L;
Supervision: Anand L;
Validation: Archana R;
Writing- Reviewing and Editing: Archana R and Anand L;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Author(s) thanks to Dr. Anand L for this research completion and support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Anand L
Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur-603 203, Chengalpattu, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Archana R and Anand L, “Innovative Deep Learning Models for Accurate Segmentation and Classification in Oncological Diagnosis Data”, Journal of Machine and Computing, vol.5, no.3, pp. 1417-1426, July 2025, doi: 10.53759/7669/jmc202505112.