Radiomic analysis, coupled with machine learning techniques, has emerged as a promising approach in the field of medical imaging for disease diagnosis, prognosis, and treatment planning. Radiomic studies often involve the extraction of hundreds or even thousands of features from medical images. The selection of relevant and informative features remains a significant challenge, as it can impact model performance and interpretability. Furthermore, radiomic models often lack interpretability, making it challenging for clinicians to trust and integrate them into clinical practice. Bridging the gap between technical advancements and clinical utility remains a significant hurdle. In this talk we will discuss the current issues of radiomic applications, analyzing real case studies and trying to provide hints about their possible solutions.
In conclusion, we will see a novel approach to enrich the standard radiomic analysis, aiming to bring the complex network theory to the medical image field.
