Synthetic MRI improves radiomics‐based glioblastoma survival prediction

Abstract

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.

Trends and Hotspots in Global Radiomics Research: A Bibliometric Analysis

“…The results demonstrate the wide range of applications of radiomics in various neoplastic disease systems. 45 – 48 …”

Toward deep learning replacement of gadolinium in neuro-oncology: A review of contrast-enhanced synthetic MRI

“…Recently, we have proposed a self-supervised synthetic MRI approach for the computation of T1, T2, and PD parametric maps and the synthesis of non-acquired weighted images from only two acquired weighted images (Moya-Sáez et al, 2022 ). Self-supervised learning allowed us to compute the parametric maps without the need of reference parametric maps for network training.…”

“…Following this method we have performed an experiment aimed at quantifying the reliability of this synthesis methodology; specifically, starting with the data available in Moya-Sáez et al ( 2022 ), we have modified the self-supervised network there described in order to perform the synthesis from only the T1w modality. This way, we can train the network with only the T1w images and the T1, T2, and PD parametric maps could be generated from only that input.…”

Multi-Device Parallel MRI Reconstruction: Efficient Partitioning for Undersampled 5D Cardiac CINE

“…In this scenario, we should also note that the integration of artificial intelligence (AI) and deep learning methods has marked significant advances in MRI reconstruction [ 5 , 6 ], learning from large image datasets to enable faster reconstructions than traditional methods. Classical methods based on optimization, however, still maintain their interest since they can drive physics-informed learning-based solutions.…”