• Nidhi Kowshika Jois
• Shilpa B
• Komal Kumari
• Prachi Raut
• Rishu Ray

Hepatocellular Carcinoma (HCC), the most prevalent form of Liver Cancer, presents a major global health issue due to its lack of symptoms and frequent diagnosis at advanced stages. Although current diagnostic techniques are effective, they often suffer from difference in interpretation and observation due to variability . This research presents a sophisticated deep learning framework utilizing 3D Convolutional Neural Networks (3D CNNs) to improve the detection of HCC from MRI scans. In contrast to traditional 2D models, the proposed 3D structure captures spatial and volumetric information with higher accuracy, formulating the distinction between cancerous and normal liver tissue. Comprehensive preprocessing methods—such as intensity normalization, data augmentation, and denoising—boost model performance by addressing data variability and improving generalization. The framework undergoes thorough evaluation against leading methods[1],[2], with performance assessed through metrics like accuracy, sensitivity, specificity, and AUC-ROC. By advancing AI-driven diagnostic imaging, this approach seeks to enhance early detection and decision-making, ultimately promoting precision medicine in liver cancer treatment

Hepatocellular carcinoma, liver cancer, 3D convolutional neural networks, deep learning, MRI, medical imaging, early detection, AI in healthcare, image preprocessing, precision medicine

"Hepatocellular Carcinoma Detection Using 3D CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.m799-m824, April-2025, Available :http://www.jetir.org/papers/JETIR2504C99.pdf

"Hepatocellular Carcinoma Detection Using 3D CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppm799-m824, April-2025, Available at : http://www.jetir.org/papers/JETIR2504C99.pdf