Title : The role of texture analysis of MRI in prediction of local recurrence and distant metastasis in locally advanced Rectal Cancer
Abstract:
Aim: Locally advanced rectal cancer (LARC) is treated by neoadjuvant chemoradiotherapy (NCRT) followed by surgery after restaging with magnetic resonance imaging (MRI). Texture analysis (TA) is an imaging biomarker that could assess MRIs heterogeneity by measuring grey-level intensities distribution. This study hypothesizes that TA can predict local recurrence and distant metastasis.
Method: This is a retrospective analysis of LARC patients after NCRT. From the posttreatment MRI scans, the tumor’s Region of interest (ROI) was determined on T2 MRI images. Six texture parameters were systematically extracted and were examined to predict local recurrence and distant metastases through Kaplan-Meier survival curves and log-rank tests.
Results: From 113 patients with LARC , two texture parameters significantly predicted local recurrence: Entropy (p=0.033) and mean of positive pixels (MPP) (p=0.045). Meanwhile, five parameters predicted distant metastases: SD(p=0.015), entropy(p=0.017), MPP(p=0.005), skewness (p=0.046), and Kurtosis (P=0.019). Kaplan-Meier Log rank test showed that entropy and skewness independently predicted distant metastases.
Conclusions: MRI textural features are potentially significant imaging biomarkers in predicting local recurrence and distant metastases in LARC treated with NCRT.
