Hi, I am a biomedical imaging and visualization researcher who investigates how the study of brain connectivity and machine perception can help advance the understanding of biologically inspired artificial intelligence.
Due 3/1 !
Images are 2D Arrays!
it's all numb3rs but you need to figure out the conventions...
Input > 200
everything < 200 set to 0
everything < 247 set to 0
How to segment the tumor?
Binary segmentation mask
means dividing up an image into different structures
foreground vs. background
each identified structure has a unique ID
Comparison of Segmentation Techniques
Automatic Segmentation is a hard problem!
so much variability across subjects!
user places seeds
Manual Segmentation or Expert Segmentation is the "Groundtruth"
2 Experts worked on this for 6 months
Registration / Alignment
mapping one subject to a standard space
mapping one image modality to a standard space
once in standard space, we can apply knowledge or compare
CS480 Lecture 13
By Daniel Haehn