In the NIST lab we develop computer vision image processing algorithms for analysis of medical images that are focused on registration and segmentation. These techniques are applied to different research projects that include:
  • image guided neurosurgery
  • disease diagnosis, and
  • prognosis and quantification for diseases such as multiple sclerosis, epilepsy, schizophrenia and degenerative diseases such as Alzheimer’s dementia.

Non-linear registration has many uses, including patient-to-image alignment for image guided surgery. Can such mapping be trusted? My student Josh Bierbrier wrote an extensive literature review on estimating uncertainty in medical image registration.
https://authors.elsevier.com/sd/article/S1361-8415(22)00178-5

As Dr. Feindel was a great mentor to me, it was a great honour to be nominated to give the William Feindel Lecture at the 2022 @rbiq_qbin conference in June.
the talk: https://youtu.be/bg027PTAcww
the interview: https://tinyurl.com/36u66ftc
@TheNeuro_MNI @bic_mni @McGillBME @NistLab

QC of individual image processing steps is key to accurate neuroimaging results, but manual QC is very time consuming. The publicly available DARQ tool automates QC of the ubiquitous stereotaxic registration step.
@VFonov @DadarMahsa @TheNeuro_MNI @NistLab #OpenScience https://twitter.com/vfonov/status/1524542839383801856

Vladimir S. FONOV @vfonov

DARQ paper is out!
https://doi.org/10.1016/j.neuroimage.2022.119266#.YnxQqGVrsq0.twitter

Load More…
YouTube-logo-full_color