A framework for pulmonary fissure segmentation in 3D CT images using a directional derivative of plate filter

Abstract Imaging pulmonary fissures by CT provides useful information on diagnosis of pulmonary diseases. Automatic segmentation of fissures is a challenging task due to the variable appearance of fissures, such as inhomogeneous intensities, pathological deformation and imaging noise. To overcome these challenges, we propose an anisotropic differential operator called directional derivative of plate (DDoP) filter to probe the presence of fissure objects in 3D space by modeling the profile of a fissure patch with three parallel plates. To reduce the huge computation burden of dense matching with rotated DDoP kernels, a family of spherical harmonics are particularly utilized for acceleration. Additionally, a two-stage post-processing scheme is introduced to segment fissures. The performance of our method was verified in experiments using 55 scans from the publicly available LOLA11 dataset and 50 low-dose CT scans of lung cancer patients from the VIA-ELCAP database. Our method showed superior performance compared to the derivative of sticks (DoS) method and the Hessian-based method in terms of median and mean F 1 − s c o r e . The median F 1 − s c o r e for DDoP, DoS-based and Hessian-based methods on the LOLA11 dataset was 0.899, 0.848 and 0.843, respectively, and the mean F 1 − s c o r e was 0.858 ± 0.103, 0.781 ± 0.165 and 0.747 ± 0.239, respectively.

[1]  Bram van Ginneken,et al.  Automatic Segmentation of the Pulmonary Lobes From Chest CT Scans Based on Fissures, Vessels, and Bronchi , 2013, IEEE Transactions on Medical Imaging.

[2]  Carl-Fredrik Westin,et al.  Automatic Lung Lobe Segmentation Using Particles, Thin Plate Splines, and Maximum a Posteriori Estimation , 2010, MICCAI.

[3]  Margrit Betke,et al.  Pulmonary fissure segmentation on CT , 2006, Medical Image Anal..

[4]  Joost van de Weijer,et al.  Fast Anisotropic Gauss Filtering , 2002, ECCV.

[5]  Qiao Wei,et al.  Automatic recognition of major fissures in human lungs , 2011, International Journal of Computer Assisted Radiology and Surgery.

[6]  Smita Patel,et al.  Normal and accessory fissures of the lung: evaluation with contiguous volumetric thin-section multidetector CT. , 2010, European journal of radiology.

[7]  Heinz-Otto Peitgen,et al.  Automatic segmentation of lung lobes in ct images based on fissures, vessels, and bronchi , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[8]  David J. Hawkes,et al.  Pulmonary Lobe Segmentation With Probabilistic Segmentation of the Fissures and a Groupwise Fissure Prior , 2017, IEEE Transactions on Medical Imaging.

[9]  Johan H. C. Reiber,et al.  Automatic lung lobe segmentation of COPD patients using iterative B-spline fitting , 2012, Medical Imaging.

[10]  Nima Tajbakhsh,et al.  Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-Network , 2018, DLMIA/ML-CDS@MICCAI.

[11]  Tobias Klinder,et al.  Lobar fissure detection using line enhancing filters , 2013, Medical Imaging.

[12]  Bram van Ginneken,et al.  Supervised Enhancement Filters: Application to Fissure Detection in Chest CT Scans , 2008, IEEE Transactions on Medical Imaging.

[13]  Uday Patil,et al.  Lung fissure detection in CT images using global minimal paths , 2010, Medical Imaging.

[14]  Joseph M. Reinhardt,et al.  Anatomy-Guided Lung Lobe Segmentation in X-Ray CT Images , 2009, IEEE Transactions on Medical Imaging.

[15]  Marco Reisert,et al.  Spherical Tensor Algebra: A Toolkit for 3D Image Processing , 2017, Journal of Mathematical Imaging and Vision.

[16]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[17]  Qiao Wei,et al.  Segmentation of Lung Lobes in High-Resolution Isotropic CT Images , 2009, IEEE Transactions on Biomedical Engineering.

[18]  Changyan Xiao,et al.  An oriented derivative of stick filter and post-processing segmentation algorithms for pulmonary fissure detection in CT images , 2018, Biomed. Signal Process. Control..

[19]  Heinz-Otto Peitgen,et al.  Lung lobe segmentation by anatomy-guided 3D watershed transform , 2003, SPIE Medical Imaging.

[20]  Luc Vincent,et al.  Morphological Area Openings and Closings for Grey-scale Images , 1994 .

[21]  Max A. Viergever,et al.  Automatic Segmentation of Pulmonary Lobes Robust Against Incomplete Fissures , 2010, IEEE Transactions on Medical Imaging.

[22]  David Gur,et al.  A Computational Geometry Approach to Automated Pulmonary Fissure Segmentation in CT Examinations , 2009, IEEE Transactions on Medical Imaging.

[23]  Shuang Liu,et al.  Large-scale image region documentation for fully automated image biomarker algorithm development and evaluation , 2017, Journal of medical imaging.

[24]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[25]  Noboru Niki,et al.  Extraction of pulmonary fissures from thin-section CT images using calculation of surface-curvatures and morphology filters , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[26]  Adam P. Harrison,et al.  Pathological Pulmonary Lobe Segmentation from CT Images Using Progressive Holistically Nested Neural Networks and Random Walker , 2017, DLMIA/ML-CDS@MICCAI.

[27]  Eric A. Hoffman,et al.  Atlas-driven lung lobe segmentation in volumetric X-ray CT images , 2006, IEEE Transactions on Medical Imaging.

[28]  David Gavaghan,et al.  Review of automatic pulmonary lobe segmentation methods from CT , 2015, Comput. Medical Imaging Graph..

[29]  David Gur,et al.  Identification of pulmonary fissures using a piecewise plane fitting algorithm , 2012, Comput. Medical Imaging Graph..

[30]  Changyan Xiao,et al.  Pulmonary Fissure Detection in CT Images Using a Derivative of Stick Filter , 2016, IEEE Transactions on Medical Imaging.

[31]  Thomas Bülow,et al.  Unsupervised extraction of the pulmonary interlobar fissures from high resolution thoracic CT data , 2005 .

[32]  Bernard De Baets,et al.  Unsupervised ridge detection using second order anisotropic Gaussian kernels , 2015, Signal Process..

[33]  Xiangrong Zhou,et al.  Automatic segmentation and recognition of anatomical lung structures from high-resolution chest CT images , 2006, Comput. Medical Imaging Graph..

[34]  David Gur,et al.  Computerized assessment of pulmonary fissure integrity using high resolution CT. , 2010, Medical physics.

[35]  Gary E. Christensen,et al.  FissureNet: A Deep Learning Approach For Pulmonary Fissure Detection in CT Images , 2019, IEEE Transactions on Medical Imaging.

[36]  Hao Tang,et al.  Automatic Pulmonary Lobe Segmentation Using Deep Learning , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[37]  Nicolai Petkov,et al.  Edge and line oriented contour detection: State of the art , 2011, Image Vis. Comput..

[38]  A. Aziz,et al.  High Resolution CT Anatomy of the Pulmonary Fissures , 2004, Journal of thoracic imaging.

[39]  Shouliang Qi,et al.  Automatic pulmonary fissure detection and lobe segmentation in CT chest images , 2014, BioMedical Engineering OnLine.

[40]  Peng-Lang Shui,et al.  Noise-robust edge detector combining isotropic and anisotropic Gaussian kernels , 2012, Pattern Recognit..

[41]  Joseph M. Reinhardt,et al.  Pulmonary Lobe Segmentation Using A Sequence of Convolutional Neural Networks For Marginal Learning , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[42]  Qiang Li,et al.  Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. , 2003, Medical physics.

[43]  Noboru Niki,et al.  An algorithm for the extraction of pulmonary fissures from low-dose multislice CT image , 2006 .

[44]  Anthony P. Reeves,et al.  Local noise estimation in low-dose chest CT images , 2013, International Journal of Computer Assisted Radiology and Surgery.

[45]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..