Medical volume segmentation by overfitting sparsely annotated data.

Tristan PayerFaraz NizamaniMeinrad BeerMichael GötzTimo Ropinski

Published in: Journal of medical imaging (Bellingham, Wash.) (2023)

We evaluate a method that supports experts during the labeling of 3D medical volumes. Our approach makes it possible to drastically reduce the number of slices that need to be manually labeled. We present a recommendation in which selector predictor combination to use for different tasks and goals.

Keyphrases

healthcare
deep learning
working memory
convolutional neural network
electronic health record
big data
pet imaging
machine learning
mass spectrometry