Synthetic MRI improves radiomics‐based glioblastoma survival prediction

Glioblastoma is an aggressive and fast‐growing brain tumor with poor prognosis. Predicting the expected survival of patients with glioblastoma is a key task for efficient treatment and surgery planning. Survival predictions could be enhanced by means of a radiomic system. However, these systems demand high numbers of multicontrast images, the acquisitions of which are time consuming, giving rise to patient discomfort and low healthcare system efficiency. Synthetic MRI could favor deployment of radiomic systems in the clinic by allowing practitioners not only to reduce acquisition time, but also to retrospectively complete databases or to replace artifacted images. In this work we analyze the replacement of an actually acquired MR weighted image by a synthesized version to predict survival of glioblastoma patients with a radiomic system. Each synthesized version was realistically generated from two acquired images with a deep learning synthetic MRI approach based on a convolutional neural network. Specifically, two weighted images were considered for the replacement one at a time, a T2w and a FLAIR, which were synthesized from the pairs T1w and FLAIR, and T1w and T2w, respectively. Furthermore, a radiomic system for survival prediction, which can classify patients into two groups (survival >480 days and ≤ 480 days), was built. Results show that the radiomic system fed with the synthesized image achieves similar performance compared with using the acquired one, and better performance than a model that does not include this image. Hence, our results confirm that synthetic MRI does add to glioblastoma survival prediction within a radiomics‐based approach. Glioblastoma is a common brain tumor, with poor prognosis. Radiomic systems (RSs) may improve patient care as an aid to predict survival and personalize treatments. Synthetic MRI favors deployment of RSs by reducing acquisition time and curating databases. Whether an RS can reliably work on synthesized images needs verification. We found that an RS fed with a set of images of which one is synthesized performs similarly to one fed with acquired images, and better than one that ignores the synthesized image.