Machine learning with imaging features to predict the expression of ITGAV, which is a poor prognostic factor derived from transcriptome analysis in pancreatic cancer

Radiogenomics has attracted attention for predicting the molecular biological characteristics of tumors from clinical images, which are originally a collection of numerical values, such as computed tomography (CT) scans. A prediction model using genetic information is constructed using thousands of image features extracted and calculated from these numerical values. In the present study, RNA sequencing of pancreatic ductal adenocarcinoma (PDAC) tissues from 12 patients was performed to identify genes useful in evaluating clinical pathology, and 107 PDAC samples were immunostained to verify the obtained findings. In addition, radiogenomics analysis of gene expression was performed by machine learning using CT images and constructed prediction models. Bioinformatics analysis of RNA sequencing data identified integrin αV (ITGAV) as being important for clinicopathological factors, such as metastasis and prognosis, and the results of sequencing and immunostaining demonstrated a significant correlation (r=0.625, P=0.039). Notably, the ITGAV high-expression group was associated with a significantly worse prognosis (P=0.005) and recurrence rate (P=0.003) compared with the low-expression group. The ITGAV prediction model showed some detectability (AUC=0.697), and the predicted ITGAV high-expression group was also associated with a worse prognosis (P=0.048). In conclusion, radiogenomics predicted the expression of ITGAV in pancreatic cancer, as well as the prognosis.