About
Ayodeji Ijishakin is a machine learning and medical imaging researcher conducting PhD research at University College London, with published work in machine learning venues. He previously led a spinout company from UCL before founding Mecha Health, which develops automated radiology reporting tools.
Ayodeji Ijishakin @aijishakin
Our results demonstrate our consistency across the preservation of known and unknown variance, image quality and site effect removal. Whereas previous approaches sacrifice performance in one of these areas for gains in others. Read the full paper here: https://t.co/83fnaXg72o https://t.co/O3j4ZpbkkO
Aug 29, 2024 · ♥ 1
Ayodeji Ijishakin @aijishakin
Whilst previous approaches produce blurry counterfactual images (VAEs), fail to remove site effects (ComBat) or have unstable training dynamics (GANs), our approach is easy to train and produces high quality images. https://t.co/KkynPv4kJ2
Aug 29, 2024 · ♥ 3
Ayodeji Ijishakin @aijishakin
We explicitly separate the conditioning of a diffusion autoncoder, into known (age, sex, data collection site, etc.) and unknown variables (cortical thickness, ventricular volume, risk of disease, etc.). Allowing for greater control over counterfactual MRI generation. https://t.co/fKn5BwoMX6
Aug 29, 2024
Founder at Mecha HealthYC W25
Intro paths
Ayodeji went through Y Combinator (Winter 2025) — any YC alum in your network can reach them through the YC community.
In turn, Ayodeji can intro founders to Mecha Health's investors below.
