A fast and accurate automatic lung segmentation and volumetry method for MR data used in epidemiological studies

In modern epidemiological population-based studies a huge amount of magnetic resonance imaging (MRI) data is analysed. This requires reliable automatic methods for organ extraction. In the current paper, we propose a fast and accurate automatic method for lung segmentation and volumetry. Our approach follows a "coarse-to-fine" segmentation strategy. First, we extract the lungs and trachea excluding the main pulmonary vessels. This step is executed very fast and allows for measuring the volume of both structures. Thereafter, we start a refinement procedure that consists of three main stages: trachea extraction, lung separation, and filling the cavities on the final lung masks. After the trachea extraction step the volumes of both lungs without the main vessels can be measured. The final segmentation step results in the volumes of the left and right lungs including the vessels. The method has been tested by processing MR datasets from ten healthy participants. We compare our results with manually produced masks and obtain high agreement between the expert reading and our method: the True Positive Volume Fraction is more than 95%. The proposed automatic approach is fast and accurate enough to be applied in clinical routine for processing of thousands of participants.