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

TL;DR

This paper presents a fully-automatic pulmonary lobe segmentation method using a 3D U-net with an optimized weighted Dice loss function, improving boundary accuracy across diverse datasets.

Contribution

The study introduces a novel weighted Dice loss function for 3D U-net that enhances lung lobe boundary segmentation accuracy in diverse and challenging cases.

Findings

Weighted Dice loss reduced mean boundary distance to 1.46 mm

Method outperformed two other segmentation approaches

Validated on 49 datasets with diverse pathologies

Abstract

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).