| Sumario: | Background: Colorectal cancer ranks third on the list of malignancies, being a significant global health issue. Objective: The main objective of the study represents the imperative need for optimized preoperative staging, using imagistic methods to identify and remove both the main tumor and the positive lymphnodules that radically influence the prognosis among patients, with a strong impact on survival rates. Material and methods: The study is a retrospective one, conducted through the significant collaboration of the Radiology and Medical Imaging Clinic, General Surgery Clinic 1, and the Pathological Anatomy Service within SCJU Tg Mures. The study included patients diagnosed and operated on at General Surgery Clinic 1 between 2019 and 2023 who underwent computed tomography before surgical intervention. Patients with pathologies that could influence inflammatory status were excluded from the study, such as systemic inflammatory diseases, autoimmune diseases, recent trauma within the last 6 months, hematological diseases, other surgical interventions within the last 6 months, synchronous tumors, and septic conditions. Paraclinical investigations required for the research included imaging examinations (CT scans), histopathological reports, laboratory analyses, and surgical protocol. Results: Using machine learning software that allows the analysis of radiomic parameters extracted from CT scans, which incorporates three types of variables: segmented tumors, histopathologic subtypes, and TNM classification, a diagnosis algorithm can be developed with sufficiently good predictive capabilities and widespread applicability.As such, radiomics could serve as an additional tool in identifying, staging, and prognosis of the colorectal cancer patients. Conclusions: By integrating anatomical-imaging data into the multidisciplinary management of patients with colorectal cancer, the study aims to emphasize the importance of synergy among various medical specialties in improving clinical outcomes and increasing survival rates.
|
|---|