Photo Credit: Mohammed Haneefa Nizamudeen

The following is a summary of “An MRI radiomics-based model for prediction of pelvic lymph node metastasis in cervical cancer,” published in the February 2024 issue of Surgery by Wang et al.

Cervical cancer (CC) poses a significant health concern among women, necessitating accurate preoperative prediction of lymph node metastasis (LNM). In this study, the researchers aimed to develop and validate a magnetic resonance imaging (MRI) radiomics-based model for detecting LNM in CC patients. 

The study group conducted a retrospective analysis involving 86 patients for training and 38 patients for testing. Radiomics features were extracted from MRI T2WI, T2WI-SPAIR, and axial apparent diffusion coefficient (ADC) sequences. Selected features were used to construct a radiomics scoring model, incorporating LNM-related risk factors identified through logistic regression analyses. The model was then validated in an independent testing cohort. 

Sixteen features were chosen for model construction, with worse differentiation, advanced International Federation of Gynecology and Obstetrics (FIGO) stages, and higher radiomics scores correlating with increased LNM risk. The predictive model’s equation included differentiation level, FIGO stage, and combined sequence radiomics score. The model demonstrated superior performance in the training cohort with an area under the curve (AUC) of 0.923, outperforming individual MRI sequence-based radiomics scores. This trend was similarly observed in the testing cohort, with an AUC of 0.82 for the predictive model. Overall, the MRI radiomics-based model exhibited promising accuracy in predicting LNM in CC patients, emphasizing its potential clinical utility compared to single MRI sequence-based approaches.

Source: wjso.biomedcentral.com/articles/10.1186/s12957-024-03333-5