Spatial Semantic-Preserving Latent Space Learning for Accelerated DWI Diagnostic Report Generation
Published in MICCAI, 2020
Recommended citation: Gasimova, A., Seegoolam, G., Chen, L., Bentley, P. and Rueckert, D., 2020, October. "Spatial Semantic-Preserving Latent Space Learning for Accelerated DWI Diagnostic Report Generation." In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 333-342). Springer, Cham.
In light of recent works exploring automated pathological diagnosis, studies have also shown that medical text reports can be generated with varying levels of efficacy. Brain diffusion-weighted MRI (DWI) has been used for the diagnosis of ischaemia in which brain death can follow in immediate hours. It is therefore of the utmost importance to obtain ischaemic brain diagnosis as soon as possible in a clinical setting. Previous studies have shown that MRI acquisition can be accelerated using variable-density Cartesian undersampling methods. In this study, we propose an accelerated DWI acquisition pipeline for the purpose of generating text reports containing diagnostic information. We demonstrate that we can learn a semantic-preserving latent space for minor as well as extremely undersampled MR images capable of achieving promising results on a diagnostic report generation task.