Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
Neural motion trackers routinely accumulate drift over repetitive biological cycles; pairing persistent cross-window memory tokens with cyclic teacher-student supervision forces trajectories to close naturally without sacrificing frame-to-frame precision.
Synthesizing more realistic echocardiographic data lets deep learning models beat the clinical standard for myocardial strain estimation, a key biomarker for early diagnosis.
Standard ComBat harmonization methods fall apart when applied to dMRI data containing neurological disorders, but a simple MLP-based outlier compensation fixes the problem.
