fairfolio
Saved Projects

Identifying Extracellular Action Potentials from Human Brain Organoids on High-Density CMOS Multi-Electrode Arrays in Real-Time to Understand the Electrophysiological Communication Mechanisms of Neurons

CSEF · 2023 Mammalian Biology Second Award

Lim Max · 11

Overview

The development of human brain organoids grown from human-induced pluripotent stem cells enables scientists to study the human brain without the technical and ethical limitations of inserting electric recording devices into patients’ brains to gather data. These studies require high-density CMOS multi-electrode arrays that can simultaneously monitor hundreds of an organoid’s neurons and a real-time closed feedback loop system that can alter the functional connectivities of neurons. This system relies on a flexible method for identifying precisely when neurons generate extracellular action potentials (EAPs) in real time. Unfortunately, no such method exists, especially not for organoids whose EAPs lack the high fidelity of those from real brains. Therefore, this project attempts to develop a waveform-shape based deep learning model that differentiates between EAPs and noise from local field potentials within milliseconds. Six electrophysiological recordings from distinct organoids on separate MEAs were processed with Kilosort2, and average waveform shapes were extracted and curated based on quality-control metrics to generate base templates for the model to distinguish from extracted noise. Through careful data preprocessing, curation, and tuning, the model learned to identify various EAPs, including those that are significantly distorted. It achieves a cross-validation average F1 score of 91.5% across the six electrophysiological recordings and processes 1,020 samples in 1.199 ms. These successful results indicate that experiments involving a real-time closed feedback loop system between a computer and organoid are possible, enabling neuroscientists to study the human brain in ways that were previously deemed impossible.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (2)

Competition history

  • CSEF 2023 Mammalian Biology · Entry S1210

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google