Diksha Goyal,
Surendra Kumar Yadav,
Shalini Sharma,
- Research Scholar, Department of Computer Science, JECRC University, Ramchandrapura Industrial Area, Jaipur, Rajasthan, India
- Professor, Department of Computer Science Engineering, JECRC University, Ramchandrapura Industrial Area, Jaipur, Rajasthan, India
- Research Scholar, Department of Computer Science, JECRC University, Ramchandrapura Industrial Area, Jaipur, Rajasthan, India
Abstract
One of the main causes of cancer-related death globally is liver cancer, and improving patient outcomes depends heavily on early detection. However, low contrast, noise, organ similarity, and tumor shape and size variability make it difficult to accurately identify and segment liver tumors from medical imaging. Automated liver cancer diagnosis, segmentation, and prognosis have been greatly improved by recent developments in artificial intelligence (AI), especially deep learning. This work presents a thorough, effective method for liver tumor analysis by combining knowledge from image-processing-based MRI tumor detection, CT-based deep learning segmentation models, and AI-driven diagnostic frameworks. Otsu’s thresholding for image enhancement, marker-controlled watershed and active contor models for MRI-based segmentation, and sophisticated deep networks – including U-Net variants, ResNet hybrids, and graph convolutional networks (GCN) – for CT-based liver and tumor segmentation are among the methods highlighted in this work. Notably, SLIC superpixel clustering in conjunction with GCN architecture has shown state-of-the-art performance with high Dice scores, accuracy, and robustness in noisy environments. Furthermore, new AI systems that combine clinical parameters with multi-modal imaging (CT, MRI, and US) show promise in predicting tumor characteristics and treatment response. Overall, the review emphasizes how AI-powered models outperform conventional techniques in terms of accuracy, consistency, and automation, providing a solid basis for creating dependable computer-aided systems for clinical decision support, tumor segmentation, and early liver cancer detection.
Keywords: Convolutional neural networks, graph convolutional networks, radiomics, CT, MRI, machine learning, deep learning, hepatocellular carcinoma, and liver cancer
[This article belongs to Research and Reviews: Journal of Oncology and Hematology ]
References
- Huang J, Chan PSF, Lok V, Chen X, Ding H, Jin Y, et al. Worldwide burden, risk factors, and temporal trends of ovarian cancer: A global study. Cancers. 2022;14(9):2230.
- Stokowy T, Wojtas B, Fujarewicz K, Jarzab B, Eszlinger M, Paschke R. A two miRNA classifier differentiates follicular thyroid carcinomas from follicular thyroid adenomas. Mol Cell Endocrinol. 2015;399:43–49.
- Zhang R, Huang GB, Sundararajan N, Saratchandran P. Multicategory classification using an extreme learning machine for microarray gene expression cancer diagnosis. IEEE/ACM Trans Comput Biol Bioinform. 2007;4(3):485–494.
- Wang Y, Tetko IV, Hall MA, Frank E, Facius A, Mayer KFX, et al. Gene selection from microarray data for cancer classification—A machine learning approach. Comput Biol Chem. 2005;29(1):37–46.
- Tiwari RG, Arya KV, Chouhan SS. Amalgamating contextual information into recommender system. 2010.
- Trivedi NK, Shukla S, Singh A, Yadav VK, Saini S, Tiwari S, et al. COVID-19 pandemic: Role of machine learning and deep learning methods in diagnosis. Int J Curr Res Rev. 2021;13.
- Chaudhary K, Poirion OB, Lu L, Garmire LX. Deep learning-based multi-omics integration robustly predicts survival in liver cancer. Clin Cancer Res. 2018;24(6):1248–1259.
- Das A, Acharya UR, Panda SS, Sabut S. Deep learning based liver cancer detection using watershed transform and Gaussian mixture model techniques. Cogn Syst Res. 2019;54:165–175.
- Zhen SH, Cheng M, Tao YB, Wang YF, Juengpanich S, Jiang ZY, et al. Deep learning for accurate diagnosis of liver tumor based on MRI and clinical data. Front Oncol. 2020;10:680.
- Hamm CA, Wang CJ, Savic LJ, Ferrante M, Schobert I, Schlachter T, et al. Deep learning for liver tumor diagnosis part I: Development of a convolutional neural network classifier for multi-phasic MRI. Eur Radiol. 2019;29(7):3338–3347.
- Kaggle Dataset. COVID-19 effect on liver cancer. 2022.
- Manoharan A, Sharma S, Balamurugan S, Maity T, Sanjeevikumar P, Holm-Nielsen JB, et al. Artificial neural networks, gradient boosting and SVMs for electric vehicle battery state estimation. J Energy Storage. 2022;55.
- Tiwari RG, Chouhan SS, Arya KV. Identifying microscopic augmented images using pre-trained CNNs. 2021.
- Chhajer P, Shah V, Kshirsagar D, Dhabliya D, Gupta S, Sharma A, et al. Applications of ANN, SVM, and LSTM for stock market prediction. Decis Anal J. 2022.
- Feng X, Zhao Y, Li N, Zhang C, Wang Y. Prediction of slope stability using naive Bayes classifier. KSCE J Civ Eng. 2018.
- Yang FJ. An implementation of naive Bayes classifier. In: Proceedings of the International Conference on Computational Science and Computational Intelligence (CSCI); 2018. p. 301–306.
- Goswami M, Sebastian NJ. Performance analysis of ML models for healthcare applications during COVID-19. Lect Notes Data Eng Commun Technol. 2022;96:645–658.
- Uddin S, Khan A, Hossain ME, Moni MA. Comparative performance analysis of KNN and its variants for disease prediction. Sci Rep. 2022;12:6256.
- Cunningham P, Delany SJ. k-Nearest neighbour classifiers – a tutorial. ACM Comput Surv. 2021;54(6):1–25.
- Ketkar N. Stochastic gradient descent. In: Deep Learning with Python. Berkeley (CA): Apress; 2017.
- Yacouby R, Axman D. Probabilistic extension of precision, recall, and F1 score. In: Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP); 2020. p. 79–91.
Research and Reviews: Journal of Oncology and Hematology
| Volume | 15 | |
| Issue | 02 | |
| Received | 18/03/2026 | |
| Accepted | 10/06/2026 | |
| Published | 31/08/2026 | |
| Publication Time | 166 Days |