Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function

Bianca Lassen-Schmidt, Alessa Denise Hering, Stefan Krass, Hans Meine


Fully-automatic lung lobe segmentation is challenging due to anatomical variations, pathologies, and incomplete fissures. We trained a 3D u-net for pulmonary lobe segmentation on 49 mainly publically available datasets and introduced a weighted Dice loss function to emphasize the lobar boundaries. To validate the performance of the proposed method we compared the results to two other methods. The new loss function improved the mean distance to 1.46 mm (compared to 2.08 mm for simple loss function without weighting).

Original languageEnglish
Publication statusPublished - 29.05.2020
EventMedical Imaging with Deep Learning 2020 - Montréal, Montréal, Canada
Duration: 06.07.202009.07.2020


ConferenceMedical Imaging with Deep Learning 2020
Abbreviated titleMIDL 2020
Internet address

Cite this