Jorge Cardoso

TL;DR: This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.

TL;DR: A machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies is introduced, using two neurodegenerative disease cohorts.

TL;DR: A patient-specific biomechanical modelling framework for breasts is proposed, based on an open-source graphics processing unit-based, explicit, dynamic, nonlinear finite element (FE) solver, which showed that both the heterogeneity and the anisotropy of soft tissues were essential in predicting large breast deformations under plate compression.

TL;DR: In the HdhQ150 mouse model of HD, in vivo MRI was employed at two time points, before and after the onset of motor signs, to assess brain macrostructure and white matter microstructure, and no white matter abnormalities were detected from the MRI images or electron microscopy images alike.

TL;DR: The proposed protocol provides a rapid and practicable method for generation of patient-specific FE meshes of the human head that are suitable for EIT and could be extended to other body regions and might confer benefits with other imaging techniques such as optical tomography or EEG inverse source imaging.