Three Braincells in a Labcoat
mathijsdeboer.bsky.social
Three Braincells in a Labcoat
@mathijsdeboer.bsky.social
It’s a lie, I don’t even wear a labcoat.

PhD candidate at the University Medical Centre Utrecht. Does things with AI and medical imaging.
🧪 Excited to share our research on improving neurosurgical precision! Our team developed an automated method for EVD planning using CT/MRI scans. This tech enhances precision, reduces operation times, and improves outcomes. Check it out! 👇

doi.org/10.3171/2025...

🙌 Big thanks to all collaborators!
doi.org
July 4, 2025 at 2:28 PM
🧪 My co-author, Elisa Colombo, and I got an AI to segment the brain's arteries, in combination with aneurysms for surgical planning purposes. This will allow us to give high-quality pre-operative planning suggestions to neurosurgeons, reducing operation times!

Read it here:
doi.org/10.3174/ajnr...
Accuracy of an nnUNet neural network for the automatic segmentation of intracranial aneurysms, their parent vessels and major cerebral arteries from magnetic resonance imaging-Time of flight (MRI-TOF)
BACKGROUND AND PURPOSE: To develop a new machine-learning algorithm for fully automatic identification of cerebral arteries and intracranial aneurysms (IAs) based on a manually segmented magnetic reso...
doi.org
December 3, 2024 at 6:52 PM
In Feb 2024 my coauthors and I published an article on automatic segmentation of neuroanatomy. We used the popular nnU-Net framework and compared it to an existing method.

We found that we could generate excellent quality segmentations in a short amount of time

Read it here
doi.org/10.1007/s007...
NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans - Acta Neurochirurgica
Purpose This study evaluates the nnU-Net for segmenting brain, skin, tumors, and ventricles in contrast-enhanced T1 (T1CE) images, benchmarking it against an established mesh growing algorithm (MGA). ...
doi.org
November 24, 2024 at 9:34 PM
Bluesky now has over 10 million users, and I was #6,406,820!
September 19, 2024 at 10:50 AM