Abstract
Genetic analysis of cancer tissues is pivotal for understanding tumor biology, identifying actionable mutations, and guiding precision oncology. Traditional manual or semi-automated methods for genomic profiling are time-consuming, labor-intensive, and prone to variability. Artificial Intelligence (AI) offers a transformative approach to automate and enhance genetic analysis by integrating multi-omics data, histopathological imaging, and clinical information. This thesis explores AI-driven automation in cancer genetic analysis, emphasizing computational methodologies, applications in mutation detection, pathway analysis, and biomarker discovery, as well as associated challenges and future perspectives. Automated AI systems improve the accuracy, speed, and reproducibility of genetic profiling, supporting personalized cancer therapies and advancing translational research.
References
This work is licensed under a Creative Commons Attribution 4.0 International License.