/* ---- Google Analytics Code Below */

Wednesday, July 05, 2017

Filling in Missing Data in Brain Scans

Intriguing work that looks specifically at data from after-stroke brain scans.   And an example of how this method can be used more broadly.   Having AI based methods fill in plausible data is a natural next step.  Not a difficult thing to test in other domains.   Statistically can be used to augment the original data.  A related project under way.

In MIT News: 
" ... The new approach involves essentially filling in the data that is missing from each patient scan. This can be done by taking information from the entire set of scans and using it to recreate anatomical features that are missing from other scans.

“The key idea is to generate an image that is anatomically plausible, and to an algorithm looks like one of those research scans, and is completely consistent with clinical images that were acquired,” Golland says. “Once you have that, you can apply every state-of-the-art algorithm that was developed for the beautiful research images and run the same analysis, and get the results as if these were the research images.”  ... " 

No comments: