Teacher-student approach for lung tumor segmentation from mixed-supervised datasets.

Vemund FredriksenSvein Ole M SevleAndré Pedersen Thomas LangøGabriel KissFrank Lindseth

Published in: PloS one (2022)

Our results demonstrate the potential of utilizing teacher-student designs to reduce the annotation load, as less supervised annotation schemes may be performed, without any real degradation in segmentation accuracy.

Keyphrases

deep learning
machine learning
convolutional neural network
rna seq
medical education
medical students
single cell
high school
human health
risk assessment