Needed size of dataset
Depends on the problem dependet on structure variability, background variabilty, intensity profile
Segmentation - Challenges in reallity
Ambiguity in labeling
Missing data in multimodal cases
Images may come from different domaines
Segmentation - Cost function
Sorenson Dice Coefficient
Problem: Small structures are dominated by larger ones
DSC=1 if sets perfectly overlap, 0 when no overlap
Softmax non-linear activation
UNet for segmentation
Problem: Details get lost because of too many pooling operations
How to use contextual information and retain high resolution?
Solution 1: Combination from different scales to retain resolution
Solution 2: Unet
Encoding part (reduction in size)
Decoding part (upscaling)
Skip connection to retain high resolution information
Restoration - Cost function
MSE or derived loss function —> not capture what makes images perceptually similar
Advanced loss function: Measure distance between deep features going beyond simple pixel wise difference
—> MSE
Restoration - GANs
Discriminator identifies whether the input image is real or not
This image is generated by a generatot network
Arhcitecture fully connected or Unet structures
Synthesis
Syntheszising target image from source imahe
Challenges: Labels and features may not be paired
Archtitecture for npaired prblem:
Last changeda year ago
