Tubular tissue-based segmentation of lung lobes from chest MDCT images

Segmentation of lung lobes from MDCT images can provide effective information for functional assessments of each lobe and detection of pulmonary diseases such as the emphysema and lung cancers. Conventional studies have detected pulmonary fissures that located between lung lobes. However, some parts of fissures may disappear in MDCT images because of artifacts or the adhesion between lung lobes. This paper proposes a novel method for segmenting lung lobes based on tubular tissues, which are the peripheral blood vessels and bronchus. Our method estimates the boundary surface between lung lobes by fitting a curved surface. The fitting is performed with fuzzy control, and it searches the boundary where the density of tubular tissues is low. As a result of applying the proposed method to two normal subjects, we could estimate the boundary surface between lung lobes and segment lung lobes successfully.