Segmentation

Automatic segmentation of lungs in a severe case of ARDS

We use deep learning techniques to delineate the lungs and vascular trees despite contrast changes due to pathological conditions.

Penarrubia L., Verstraete A., Orkisz M., Dávila Serrano E.E., Boussel L., Yonis H., Mezidi M., Dhelft F., Danjou W., Bazzani A., Sigaud F., Bayat S., Terzi N., Girard M., Bitker L., Roux E., and Richard J.-C., "Precision of CT-derived alveolar recruitment assessed by human observers and a machine learning algorithm in moderate and severe ARDS ", Intensive Care Medicine Experimental, 2023, 11, 8. DOI: 10.1186/s40635-023-00495-6.

Penarrubia L., et al. “Improving motion-mask segmentation in thoracic CT with multi-planar U-nets”, Medical Physics, 49, 420-431, 2022, DOI: 10.1002/mp.15347.

Back to FILM page