Artificial intelligence for radiomics; diagnostic biomarkers for neuro-oncology

Abstract

Recent advances in medical image analysis have been made to improve our understanding of how disease develops, behaves, and responds to treatment. Magnetic resonance imaging (MRI) and positron emission tomography (PET) advanced imaging strategies provide structural and functional phenotypic biomarkers that correlate with key disease processes. Through radiomics and radiogenomics, ML-medical imaging has opened up new perspectives in high-grade glioma diagnosis. As a result, non-invasive and in vivo biomarkers for patient survival, tumor recurrence, and genomics are identified. Tumor genomic imaging signatures can help identify patients who benefit from targeted therapies. Molecular characterization of gliomas and prediction of their evolution would allow treatment optimization. Radiomics-based biomarkers allow for a more in-depth analysis of pathophysiologic processes and insights into diagnosing better, classifying, stratifying, and prognosticating brain tumors and assessing their response to therapy. Radiomics is a new data-driven approach that can help answer clinical questions like diagnosis, prognosis, and treatment response. With encouraging outcomes in brain tumor patients, radiomics and deep learning are still not widely used in clinical practice, requiring more extensive and practical clinical studies.