Liver Tumor Classification and Segmentation Using Ai Techniques
Author(s): 1. Dr.K.Dharmarajan, 2. Dr.K. Abirami, 3. T Haripriya
Authors Affiliations:
1. Professor
2. Assistant Professor
3. Research Scholar
School of Computing Sciences, VISTAS, Chennai, India
DOIs:10.2017/IJRCS/202506011 | Paper ID: IJRCS202506011Cancer is one of the deadly cells while affect the human body. Liver is one of the most essential part of the body. It is used to circulate and stores blood cells, and it is mainly used for the removing toxins like harmful substances from the blood. Liver cancer is the abnormal growth of the unwanted cells by affecting the part of abdomen. It is a most common deadly diseases and affected the people in worldwide. It is responsible for various metabolic and detoxification processes, becomes vulnerable to malignant transformations due to chronic liver diseases such as hepatitis B and C infections, cirrhosis, non-alcoholic fatty liver disease (NAFLD), and excessive alcohol consumption. Hepatocellular carcinoma (HCC), the most common primary liver cancer, accounts for approximately 75% of liver cancer cases, followed by intrahepatic cholangiocarcinoma and other rare tumors. The rising incidence of liver cancer is particularly alarming in regions with limited access to early diagnosis and effective treatment. Treatment strategies for liver cancer depend on the stage of the disease, liver function, and overall health status of the patient. Early stage of liver cancer may be managed with curative options like surgical resection, liver transplantation, or local ablative therapies such as radiofrequency ablation. Intermediate and advanced stages often require systemic therapies including chemotherapy, targeted therapy and immunotherapy. Despite recent advancements in treatment, the prognosis for liver cancer remains poor, with five year survival rates being significantly lower compared to other cancers. Emerging research in molecular biology, artificial intelligence, and precision medicine has opened new avenues for early detection, personalized treatment, and better prognosis of liver cancer. Techniques like machine learning and deep learning based imaging analysis, genomic profiling, and liquid biopsies are showing promise in identifying liver cancer at an earlier and more treatable stage. Integrating clinical data with medical imaging through AI-driven platforms is expected to transform the landscape of liver cancer diagnosis and management.
Dr.K.Dharmarajan, Dr.K. Abirami, T Haripriya (2025); Liver Tumor Classification and Segmentation Using Ai Techniques, International Journal of Research Culture Society, ISSN(O): 2456-6683, Volume – 9, Issue – 6, Pp.81-88. Available on – https://ijrcs.org/
1. T. Haripriya and K. Dharmarajan, “An Innovative Research of Liver Fibrosis Imaging Using DCNN Neural Network,” 2024 International Conference on IoT, Communication and Automation Technology (ICICAT), Gorakhpur, India, 2024, pp. 248-252, doi: 10.1109/ICICAT62666.2024.10923378.
2. T. Haripriya and K. Dharmarajan, “Exploring a Novel Neuroplexus Learning Framework (NLF) Approach for MRI Image Analysis,” 2024 International Conference on IoT, Communication and Automation Technology (ICICAT), Gorakhpur, India, 2024, pp. 1022-1026, doi: 10.1109/ICICAT62666.2024.10923452.
3. Zhang, Y., Li, M., & Chen, X. (2025). Deep hybrid models for liver cancer classification using multi-modal data. IEEE Transactions on Medical Imaging, 44(2), 220–231. https://doi.org/10.1109/TMI.2025.1234567.
4. Swathi, H. P., & Kumar, S. (2025). A multimodal framework for liver tumor detection using clinical and imaging data fusion. Journal of Biomedical Informatics, 136, 104413. https://doi.org/10.1016/j.jbi.2025.104413.
5. Nguyen, T., & Patel, R. (2024). Automated liver tumor segmentation using attention-guided UNet++. Computers in Biology and Medicine, 157, 106015. https://doi.org/10.1016/j.compbiomed.2024.106015
6. Wang, L., Zhao, J., & Sun, H. (2025). Explainable AI models for liver cancer diagnosis: From deep learning to decision support. Artificial Intelligence in Medicine, 144, 102547. https://doi.org/10.1016/j.artmed.2025.102547
7. El-Sayed, M., & Hassan, M. (2024). Transfer learning-based classification of liver tumors using ResNet variants. Expert Systems with Applications, 236, 120145. https://doi.org/10.1016/j.eswa.2024.120145
8. Alqahtani, A., & Alshahrani, M. (2025). Comparative analysis of segmentation algorithms for liver cancer: Classical vs. deep learning approaches. Medical Image Analysis, 87, 102920. https://doi.org/10.1016/j.media.2025.102920
9. Kumar, D., & Bansal, R. (2024). U-Net and its optimized variants for liver lesion segmentation: A survey. International Journal of Computer Vision and Image Processing, 14(3), 75–89. https://doi.org/10.4018/IJCVIP.20240701.oa5
10. Singh, R., & Thomas, A. (2025). Real-time liver tumor classification using CNN and LSTM networks. Sensors, 25(2), 678. https://doi.org/10.3390/s25020678
11. Liu, J., & He, Q. (2024). Enhancing liver cancer detection with federated learning: A privacy-aware approach. IEEE Journal of Biomedical and Health Informatics, 28(1), 103–112. https://doi.org/10.1109/JBHI.2024.123456
12. Rahman, F., & Zhang, W. (2024). Liver segmentation in CT images using deep residual attention UNet. Computers in Medical Imaging and Graphics, 104, 102210. https://doi.org/10.1016/j.compmedimag.2024.102210.