Mastodawn

You’re not going to believe this, but after learning of the #HealthyPi I looked into whether anyone had tried phase-targeting TMS-EEG in real time by eliminating the “hardware delays” inherent to streaming the EEG data to a computer by … not using a computer, and though that the #FPGA:s I’ve heard of being used by #retrogaming folk could fit the bill even better than a #microcontroller.

Guess what they present as a novel approach in this preprint from last week?

https://www.biorxiv.org/content/10.64898/2026.03.26.713979v2.full#ref-20

Show thread

Matti Apr 16

Given my very recent introduction to electronics, feels pretty great to know that my "novel" idea had legs – and the timing is perfect, a week later and I would’ve wasted more than just my time to research what it would take to build a proof-of-concept

Show thread

Matti

In the same vein, the way #CorridorKey was trained using synthetic data reminded me of the technique of using labeled CT scans to create a bunch of digitally rendered radiographs for training a machine learning model to detect regions of interest in 2D thorax xrays.

So I started wondering whether anyone had tried applying this to segmentation, and sure enough, #SynthSeg goes one step further and solves the inherent issue of the applicability of synthetic data by sampling from a generative model