Pulmonary Fissure Detection in CT Images Using a Derivative of Stick Filter

Abstract

Pulmonary fissures are important landmarks for recognition of lung anatomy. In CT images, automatic detection of fissures is complicated by factors like intensity variability, pathological deformation and imaging noise. To circumvent this problem, we propose a derivative of stick (DoS) filter for fissure enhancement and a post-processing pipeline for subsequent segmentation. Considering a typical thin curvilinear shape of fissure profiles inside 2D cross-sections, the DoS filter is presented by first defining nonlinear derivatives along a triple stick kernel in varying directions. Then, to accommodate pathological abnormality and orientational deviation, a [Formula: see text] cascading and multiple plane integration scheme is adopted to form a shape-tuned likelihood for 3D surface patches discrimination. During the post-processing stage, our main contribution is to isolate the fissure patches from adhering clutters by introducing a branch-point removal algorithm, and a multi-threshold merging framework is employed to compensate for local intensity inhomogeneity. The performance of our method was validated in experiments with two clinical CT data sets including 55 publicly available LOLA11 scans as well as separate left and right lung images from 23 GLUCOLD scans of COPD patients. Compared with manually delineating interlobar boundary references, our method obtained a high segmentation accuracy with median F1-scores of 0.833, 0.885, and 0.856 for the LOLA11, left and right lung images respectively, whereas the corresponding indices for a conventional Wiemker filtering method were 0.687, 0.853, and 0.841. The good performance of our proposed method was also verified by visual inspection and demonstration on abnormal and pathological cases, where typical deformations were robustly detected together with normal fissures.

Pulmonary Lobe Segmentation With Probabilistic Segmentation of the Fissures and a Groupwise Fissure Prior

“…We used the method presented by Xiao et al [34] to evaluate our fissure segmentation. We did not define a volume of interest (VoI) using a 40mm width band around each reference as this ignores potential false positives in the validation.…”

“…The magnitude of F 1 reflects the similarity between the segmentation and the reference. Precision and Recall are defined respectively as TP 1 /( TP 1 + FP ) and TP 2 /( TP 2 + FN ) [34]. Precision was quantified by considering the overlap of the binary result (𝒮) with the reference.…”

“…Precision was quantified by considering the overlap of the binary result (𝒮) with the reference. A 3mm tolerance band was defined around the reference segmentation as performed by Xiao et al [34]. Voxels of 𝒮 are classified as true positive ( TP 1 ) if they fall within the 3mm band and false positive ( FP ) if otherwise.…”

SurfCut: Surfaces of Minimal Paths from Topological Structures

“…Each image has size 512 × 512 × Z, where Z varies between 300 and 700, depending on the patient. Our goal is to segment lung fissures (e.g., [44], [45]), which are the boundaries between sections of the lung. They are very thin, subtle structures, and form free-boundary surfaces.…”

Efficient Segmentation of Lung Using FIDRM Filter and Successive Peak Quantization Transform

“…As an advancement, 3D images from multiple detector Computed Tomography (MDCT) to be taken for the further classification. This method [30] extracts the fissure by applying the derivative of stick filter for the fissure enhancement and the post processing of lobe segmentation is carried out. The merits are typical abnormalities including thickened fissure, orientation deviations and the step deformation are well preserved with a distinct non-linear derivatives combination and shape description.…”