Potential Role of T2-Weighted Kurtosis in Improving Response Prediction of Locally Advanced Rectal Cancer as Additional Tool Gained from Standard MRI Examination

<b>Background:</b> Reliable and accurate prediction of treatment response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) is usually demanding and continues to pose a challenge. Kurtosis as a histogram parameter calculated on T2-weighted MRI sequences might be an additional tool, as it represents a quantitative biomarker for response prediction. It is defined as a measure of distributions' tails relative to the center of the distribution curve, which reflects tissue heterogeneity. The aim of the study was to evaluate the added value of T2-weighted kurtosis in predicting pathological response to nCRT in patients with LARC. <b>Methods:</b> a single-center cohort study included 71 patients with LARC who underwent both initial and post-nCRT MRI examinations followed by surgical resection in the form of the total mesorectal excision (TME). Histogram analysis was performed using software MIPAV (Medical Image Processing, Analysis, and Visualization, version 11.3.2, developed by the National Institutes of Health, Bethesda, MD, USA) on T2-weighted sequences, extracting kurtosis along with other histogram parameters. Pathological tumor regression grade (pTRG) in accordance with Mandard classification was considered the gold standard. Patients were classified as responders (pTRG 1-2) or non-responders (pTRG 3-5). <b>Results:</b> while other histogram parameters did not show statistically significant differences between groups, post-treatment values of kurtosis were significantly higher in responders compared to non-responders (4.28 ± 0.73 vs. 3.01 ± 0.17, <i>p</i> = 0.024). The F1 score as a classification metric (0.821) indicates an improvement in classification performance following therapy. <b>Conclusions:</b> T2-weighted kurtosis might be a significant tool in predicting pathological response to nCRT, representing a potentially valuable quantitative biomarker that could improve treatment response assessment.