CT texture analysis to predict response to target therapy of hepatic metastases from colorectal cancer

Introduction Colorectal cancer (CRC), the 2nd cause of cancer death worldwide, is an indolent disease with 50% of patients eventually developing liver metastases (mCRC). Repeated cycles of different chemotherapies, combined with surgery in oligo-metastatic cases, are the therapeutic standard in mCRC. However, this strategy is resolutive in less than 15% of cases. Differentiating non- and short-term responders from potentially “cured” patients will spare patients needless toxicity and allow alternative treatments earlier, with conceivable cost and life savings. In this study we aimed to use CT texture analysis (CTTA) to identify specific imaging biomarkers of hepatic metastases, able to predict patient’s response to therapy and overall survival. Methods We exploited the imaging data-set of the HERACLES trial (NCT03225937): 23 patients with amplified Human Epidermal growth factor Receptor 2 (HER2) mCRC were included in the study. All had received anti HER2 treatment, and underwent CT examination every 8 weeks, until disease progression. CT scans were semi-automatically segmented to extract for each patient all liver metastases. Texture analysis was performed on each segmented area, computing for each lesion 34 quantitative parameters. Both mono-parametric and multi-parametric analysis were assessed to identify features most correlated to therapy response. We also performed a correlative survival (OS) analysis, considering subjects with good survival those with OS > 9 months. Results In 23 patients we found 124 metastases, 55 of which were classified as responding and 69 as non-responding. Nine parameters reached statistical significance in the mono-parametric analysis (best AUC=0.67, p=0.001), while in the multivariate regression ten parameters were used in the model, achieving and AUC equal to 0.82, with sensitivity of 82% and specificity 72%. For OS analysis, 12 patients were “good” and 11 “poor” survivors. In the mono-parametric analysis “cluster prominence” and “sum entropy” predicted OS with AUC equal to 0.78 and 0.83, respectively. The regression model with two variables (“cluster prominence” and “dissimilarity”) reached a sensitivity of 83% and a specificity of 82%. Conclusions Our study demonstrated CTTA as a potential biomarker to predict response of hepatic metastases to chemotherapy treatment, possibly saving patients predicted as non-responder from toxicity. Moreover, CTTA could give indications on patients OS, without the need for additional tests