Abstract: Hepatocellular Carcinoma (HCC), the primary liver cancer, is a global health concern linked to cirrhosis from hepatitis infections and excessive alcohol consumption. Early detection is vital but often occurs at advanced stages, compromising treatment and survival. Traditional diagnostic methods like biopsy and PET scans are invasive and expensive, making them unsuitable for cirrhotic patients. We propose an AI-powered diagnostic system integrating MRI images and blood biomarkers for a non-invasive, efficient, and potentially more accurate alternative. To develop a solution to detect cancer in cirrhotic liver using Random Forest and Convolutional Neural Network (CNN), our objectives encompass creating a multi-modal data integration framework with greater accuracy, ensuring user-friendliness, and reducing the burden on healthcare professionals. This feasibility study underscores the technical readiness for this project and highlights the pressing need for a reliable diagnostic system. By utilizing diverse datasets, integrating deep learning and traditional algorithms, and employing score ensembles, we aim to provide a unified platform for cirrhotic liver cancer diagnosis, leading to improved accuracy, early detection, efficient clinical workflow, and the potential for valuable research insights.
Keywords: Hepatocellular Carcinoma detection, Cirrhosis detection, Multi-modal data integration, Blood biomarkers data analysis, Image based analysis, Random Forest, Convolutional Neural Network.
Cite:
Raksha Nayak, Sankalp S Naik, Sannidhi B M, Tejaswini Peeru Gouda, Mr. Vijayananda V Madlur, "A Deep Learning Approach to Detect Cancer in Cirrhotic Liver", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13358.
|
DOI:
10.17148/IJARCCE.2024.13358
