eISSN: 3087-4289 editor@aimjournals.com
All Journals
Submit your article

International Journal of Modern Computer Science and IT Innovations

Open Access Peer Review International
Open Access

A Hybrid Deep Learning Framework for Automated Liver Tumor Segmentation and Malignancy Prediction from CT Imaging Data

DOI https://doi.org/10.55640/ijmcsit-v03i07-01
PDF
Dr. Aarav Sharma 1 , Ms. Priya Nair 1 ,
4 Department of Computer Science, Indian Institute of Advanced Technology, Bengaluru, India
4 School of Information Technology, National Tech University, New Delhi, India, Research Interests: Data Science, IoT Systems, Cybersecurity

Abstract

Liver cancer remains one of the most fatal malignancies worldwide, with high mortality rates largely attributed to late-stage diagnosis and limited accuracy in conventional imaging-based interpretation. Recent advances in deep learning have significantly improved the capabilities of automated medical image analysis, particularly in tumor segmentation and classification tasks. This study proposes a hybrid deep learning framework designed for automated liver tumor segmentation and malignancy prediction using computed tomography (CT) imaging data. The framework integrates convolutional neural networks (CNNs) for spatial feature extraction with deep belief networks (DBNs) and multi-classifier systems for enhanced diagnostic reasoning. Drawing upon established architectures such as U-Net and deep CNN variants, the proposed system emphasizes precision segmentation and robust classification under variable imaging conditions. The study critically synthesizes prior research in medical image analysis and demonstrates how hybridization improves diagnostic performance compared to single-model approaches. Experimental insights suggest that combining feature-rich segmentation networks with probabilistic classification models enhances sensitivity and specificity in tumor detection. The framework is further evaluated in the context of clinical decision support systems, highlighting its potential to assist radiologists in early liver cancer detection and malignancy grading. Limitations such as dataset variability and computational complexity are also discussed, alongside future directions for multi-modal integration.

Keywords

Liver cancer, CT imaging, deep learning

References

Abdel-Zaher, A.M.; Eldeib, A.M. Breast cancer classification using deep belief networks. Expert Syst. Appl. 2016, 46, 139–144.
Al-Antari, M.A.; Al-Masni, M.A.; Park, S.-U.; Park, J.; Metwally, M.K.; Kadah, Y.M.; Han, S.-M.; Kim, T.-S. An automatic computer-aided diagnosis system for breast cancer in digital mammograms via deep belief network. J. Med. Biol. Eng. 2018, 38, 443–456.
Anand, D.; Arulselvi, G.; Balaji, G.; Chandra, G.R. A Deep Convolutional Extreme Machine Learning Classification Method to Detect Bone Cancer from Histopathological Images. Int. J. Intell. Syst. Appl. Eng. 2022, 10, 39–47.
Beevi, K.S.; Nair, M.S.; Bindu, G.R. A Multi-Classifier System for Automatic Mitosis Detection in Breast Histopathology Images Using Deep Belief Networks. IEEE J. Transl. Eng. Health Med. 2017, 5, 4300211.
Esteva, A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.
Fu’adah, Y.N.; Pratiwi, N.K.C.; Pramudito, M.A.; Ibrahim, N. Convolutional Neural Network (CNN) for Automatic Skin Cancer Classification System. IOP Conf. Ser. Mater. Sci. Eng. 2020, 982, 012005.
JICET, 2024, Vol:4, No.2
Jiang, Xiaoyan, Zuojin Hu, Shuihua Wang, and Yudong Zhang. 2023. "Deep Learning for Medical Image-Based Cancer Diagnosis" Cancers 15, no. 14: 3608.
Kumar, T.S.; Arun, C.; Ezhumalai, P. An approach for brain tumor detection using optimal feature selection and optimized deep belief network. Biomed. Signal Process. Control 2022, 73, 103440.
Litjens, G., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88.
Liu, F., et al. (2019). Deep learning in medical ultrasound analysis: A review. Engineering, 5(2), 261–275.
Liu, F., et al. (2019). Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour. European Radiology, 29(3), 1985–1996.
Liu, W.; Wang, Z.; Liu, X.; Zeng, N.; Liu, Y.; Alsaadi, F.E. A survey of deep neural network architectures and their applications. Neurocomputing 2017, 234, 11–26.
Ning, Z., et al. (2020). Deep learning for automatic segmentation of liver tumors on computed tomography images. Frontiers in Oncology, 10, 84.
Raiko, T.; Valpola, H.; Lecun, Y. Deep Learning Made Easier by Linear Transformations in Perceptrons. In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, La Palma, Canary Islands, 21–23 April 2012; Neil, D.L., Mark, G., Eds.; PMLR, Proceedings of Machine Learning Research: Cambridge, MA, USA, 2012; pp. 924–932.
Ronneberger, O., et al. (2015). U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 234–241.
Shahweli, Z.N. Deep belief network for predicting the predisposition to lung cancer in TP53 gene. Iraqi J. Sci. 2020, 61, 171–177.
S. K. Zhou et al., "A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises," in Proceedings of the IEEE, vol. 109, no. 5, pp. 820–838, May 2021.
World Health Organization. (2024). Liver cancer: Global health estimates and strategies for prevention.
Yan, K., et al. (2018). Deep learning for liver tumor diagnosis part I: Development of a convolutional neural network classifier for multi-phasic MRI. European Radiology, 28(10), 4088–4097.
Yao, J., et al. (2021). Deep learning in medical imaging and radiation therapy. Medical Physics, 48(3), e206–e214.

Similar Articles

11-20 of 64

You may also start an advanced similarity search for this article.