Mert R. Sabuncu

TL;DR: An ensemble learning strategy to combine the predictions from models trained on connectivity data extracted using different parcellations that overcomes the limitations of traditional machine learning models for connectomes that often rely on region-based summary statistics and/or linear models is proposed.

TL;DR: In this paper, a multi-echo sampling pattern optimization block extended from LOUPE-ST is proposed to optimize the k-space sampling patterns along echoes, and a recurrent temporal feature fusion block is proposed and inserted into a backbone deep ADMM network to capture the signal evolution along echo time during reconstruction.

TL;DR: In this paper , a detailed empirical analysis comparing expert neuropathologists and ML models at predicting IDH mutation status in H&E-stained histology slides of infiltrating gliomas, both independently and synergistically, is presented.

TL;DR: It is shown that the surface area method implemented in FreeSurfer corresponds closely to the exact, but computationally more demanding, mass-conservative (pyc-nophylactic) method, provided that images are smoothed, and that NPC analysis is a more sensitive option for studying joint effects on area and thickness, giving equal weight to variation in both of these two morphological features.

TL;DR: This work demonstrates that leveraging gaze information, in the form of attentional masking, can significantly improve brain response prediction accuracy in a neural encoding model, and proposes a novel approach to neural encoding by including a trainable soft-attention module.