BACKGROUND

Rectal cancer represents a major cause of mortality in the United States. Management strategies are highly individualized, depending on patient-specific factors and tumor characteristics. The therapeutic landscape is rapidly evolving, with notable advancements in response rates to both radiotherapy and chemotherapy. For locally advanced rectal cancer (LARC, defined as up to T3-4 N+), the standard of care involves total mesorectal excision (TME) following neoadjuvant chemoradiotherapy (nCRT). Magnetic resonance imaging (MRI) has emerged as the gold standard for local tumor staging and is increasingly pivotal in post-treatment restaging.

AIM

In our study, we proposed an MRI-based radiomic model to identify characteristic features of peritumoral mesorectal fat in two patient groups: good responders and poor responders to neoadjuvant therapy. The aim was to assess the potential presence of predictive factors for favorable or unfavorable responses to neoadjuvant chemoradiotherapy, thereby optimizing treatment management and improving personalized clinical decision-making.

METHODS

We conducted a retrospective analysis of adult patients with LARC who underwent pre- and post-nCRT MRI scans. Patients were classified as good responders (Group 0) or poor responders (Group 1) based on MRI findings, including tumor volume reduction, signal intensity changes on T2-weighted and diffusion-weighted imaging (DWI), and alterations in the circumferential resection margin (CRM) and extramural vascular invasion (EMVI) status. Classification criteria were based on the established literature to ensure consistency. Key clinical and imaging parameters, such as age, TNM stage, CRM involvement, and EMVI presence, were recorded. A radiomic model was developed using the LASSO algorithm for feature selection and regularization from 107 extracted radiomic features.

RESULTS

We included 44 patients (26 males and 18 females) who, following nCRT, were categorized into Group 0 (28 patients) and Group 1 (16 patients). The pre-treatment MRI analysis identified significant features (out of 107) for each sequence based on the Mann-Whitney test and -test. The LASSO algorithm selected three features (shape_Sphericity, shape_Maximum2DDiameterSlice, and glcm_Imc2) for the construction of the radiomic logistic regression model, and ROC curves were subsequently generated for each model (AUC: 0.76).

CONCLUSIONS

We developed an MRI-based radiomic model capable of differentiating and predicting between two groups of rectal cancer patients: responders and non-responders to neoadjuvant chemoradiotherapy (nCRT). This model has the potential to identify, at an early stage, lesions with a high likelihood of requiring surgery and those that could potentially be managed with medical treatment alone.