DeSmoke-LAP: improved unpaired image-to-image translation for desmoking in laparoscopic surgery.

Yirou PanSophia BanoFrancisco VasconcelosHyun ParkTaikyeong Ted JeongDanail Stoyanov

Published in: International journal of computer assisted radiology and surgery (2022)

DeSmoke-LAP outperformed existing methods and generated smoke-free images without applying ground truths (paired images) and atmospheric scattering model. This shows distinctive achievement in dehazing in surgery, even in scenarios with partial inhomogenenous smoke. Our code and hysterectomy dataset will be made publicly available at https://www.ucl.ac.uk/interventional-surgical-sciences/weiss-open-research/weiss-open-data-server/desmoke-lap .

Keyphrases

deep learning
minimally invasive
laparoscopic surgery
convolutional neural network
artificial intelligence
climate change
machine learning
big data
optical coherence tomography
electronic health record
particulate matter
coronary artery bypass
cross sectional
data analysis
small molecule
carbon dioxide