2025, Vol. 8, Issue 3, Part C

Author(s)
Ishaan Bakshi

Abstract
Artificial intelligence (AI) has rapidly emerged as a transformative tool in oncological imaging, particularly when integrated with radiomics. By extracting high-dimensional quantitative features from medical images, radiomics enables the characterization of tumor heterogeneity beyond visual assessment. Incorporating AI-driven analytics into this process offers a unique opportunity to optimize treatment planning and predict clinical outcomes more accurately. This study reviews recent advances in AI-assisted radiomics for treatment planning and outcome prediction. We highlight data acquisition, feature extraction, model development, and validation frameworks that integrate imaging biomarkers with clinical and molecular profiles. The strengths and limitations of machine learning and deep learning models in personalized treatment analysis are critically evaluated. Evidence demonstrates that AI-enhanced radiomics can improve prognostic modeling, stratify patients into risk categories, and guide individualized treatment decisions. Models combining radiomics with genomic and clinical data consistently outperform conventional prognostic methods. Despite promising results, challenges such as data standardization, reproducibility, and clinical translation remain. AI-driven radiomics holds substantial potential to advance precision medicine by personalizing treatment strategies and predicting outcomes with higher accuracy. Future efforts should focus on multi-institutional validation, explainable AI frameworks, and integration into clinical workflows to ensure widespread adoption.

DOI: https://doi.org/10.33545/26644436.2025.v8.i3c.487

Pages: 146-149 | Views: 338 | Downloads: 173