Many people who have cancerous tumors can get better with surgery. Since multimodality treatment has been linked to promising outcomes in some types of cancer, more attention has been paid to the combination of surgery and chemotherapy. Despite these findings, there is still clinical disagreement regarding the ideal patient selection and timing for neo-adjuvant or adjuvant strategies. By assisting in the prediction of tumor behavior and response to therapy, the emerging field of radiomics, which involves the extraction of advanced features from radiographic images, has the potential to revolutionize oncologic treatment and advance personalized therapy. Predicting prognosis, recurrence, survival, and therapeutic response for various cancer types using radiomics and machine learning in patients who have received neo-adjuvant and/or adjuvant chemotherapy is the focus of this review. Although neoadjuvant and adjuvant studies show above average accuracy in predicting progression free survival and overall survival, widespread application of this technology faces numerous obstacles. The inclusion and rapid adoption of radiomics in prospective clinical studies has been hampered by the absence of autosegmentation, limited data sharing, and standardization of common procedures for analyzing radiomics.
HTML PDFShare this article
Archives of Surgical Oncology received 37 citations as per Google Scholar report
