Category Archives: Science

I’m using AI to Change the Game for 3D Microscopy Cell Segmentation

Can you guess how big a single microscopic 3D image of a mouse retina is? It’s about 10 Terabytes! That’s roughly equal to thousands of high-definition movies stored in just one image.

During my time at Siegert Lab, I was fascinated but also concerned when I realized scientists were manually segmenting microglial cells from these massive 3D confocal microscopy images. Imagine the effort, time, and potential for errors involved in manually processing data of this scale.

(Placeholder for photo: Scientists manually segmenting cells)

Introducing trAIce3D: A New AI model for cell segmentation

Motivated by this significant challenge, I developed trAIce3D, a cutting-edge deep-learning model designed specifically for the automatic and precise segmentation of microglial cells.

Continue reading I’m using AI to Change the Game for 3D Microscopy Cell Segmentation

Brian Entrainment using Flickering Light

Over the past few years, my work has mainly focused on developing deep learning architectures, signal processing, and software engineering. However, I’ve always stayed connected to neuroscience through both research and hands-on work. I first applied my signal processing skills to EEG data in 2019, studying the effects of 40 Hz flickering light on both healthy individuals and those with Alzheimer’s. More recently, I conducted a study at Syntropic Medical to examine these effects over a longer time scale and at 60 Hz frequency. It was a nice experience, and it was cool to return to EEG recording sessions and signal processing after 4 years. We found that exposure to 60 Hz light induces strong and widespread entrainment in healthy human brain, and different brain regions get synchronized at this frequency. Also, over course of 3 weeks, the power of entrainment and level of synchrony decreases (Most likely due to plasticity), so it’s very likely that 60 Hz flickering light induces plasticity in the brain which is super cool.

You can check out my latest publication on this topic here. Also, you can listen to an AI generated discussion about the paper: