Extraction of GGO Candidate Regions on Thoracic CT Images using SuperVoxel-Based Graph Cuts for Healthcare Systems

In this paper, we propose a method to reduce artifacts on temporal difference images by improving the conventional method using a non-rigid registration method for ground glass opacification (GGO), which is light in concentration and difficult to detect early. In this method, global matching, local matching, and 3D elastic matching are performed on the current image and past image, and an initial temporal difference image is generated. After that, we use an Iris filter, which is the gradient vector concentration degree filter, to determine the initial GGO candidate regions and perform segmentation using SuperVoxel and Graph Cuts in which a superpixel is extended to three dimensions for each region of interest. For each extracted region, a support vector machine (SVM) is used to reduce the over-segmentation. Finally, in the method that greatly reduces artifacts other than the remaining GGO candidate regions, Voxel Matching is applied to generate the final temporal difference image, emphasizing the GGO regions while reducing the artifact. The resulting ratio of artifacts to lung volume is 0.101 with an FWHM of 28.3, which is an improvement over the conventional method and shows the proposed method’s effectiveness.

[1]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Kido Shoji,et al.  A Temporal Subtraction Technique for 3-D Non-rigid Warping Method Based on Free Form Deformation from Thoracic MDCT Image , 2012 .

[3]  Francisco Herrera,et al.  Cognitive Computing: Architecture, Technologies and Intelligent Applications , 2018, IEEE Access.

[4]  M. Giger,et al.  Digital image subtraction of temporally sequential chest images for detection of interval change. , 1994, Medical physics.

[5]  Huimin Lu,et al.  Detection of abnormal candidate regions on temporal subtraction images based on DCNN , 2017, 2017 17th International Conference on Control, Automation and Systems (ICCAS).

[6]  Kim Hyoungseop,et al.  A Method for Reducing of Subtraction Artifacts in Temporal Subtraction Image Based on Voxel Matching Method , 2008 .

[7]  Joo Kooi Tan,et al.  Detection of Lung Nodule on Temporal Subtraction Images Based on Artificial Neural Network , 2012, Int. J. Fuzzy Log. Intell. Syst..

[8]  Joo Kooi Tan,et al.  Segmentation of Phalange Regions and Image Registration Method for Detection of Temporal Changes in CR Image , 2014 .

[9]  Hidefumi Kobatake,et al.  From One-Dimensional to Two- and Three-Dimensional Signal Processing , 2006 .

[10]  Michiharu Takemoto,et al.  An Implementation of Service Composition Function on a Cellular Phone , 2005 .

[11]  Min Chen,et al.  SPHA: Smart Personal Health Advisor Based on Deep Analytics , 2018, IEEE Communications Magazine.

[12]  Joo Kooi Tan,et al.  Three-dimensional non-rigid registration of thoracic CT image based on finite element method , 2014, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS).

[13]  Shimizu Akinobu,et al.  Improvement of Computer-aided detection system using a pair of whole body FDG-PET and CT images , 2006 .

[14]  Christos Davatzikos,et al.  Spatial Transformation and Registration of Brain Images Using Elastically Deformable Models , 1997, Comput. Vis. Image Underst..

[15]  Wei Li,et al.  Edge cognitive computing based smart healthcare system , 2018, Future Gener. Comput. Syst..

[16]  Michael I. Miller,et al.  Deformable templates using large deformation kinematics , 1996, IEEE Trans. Image Process..

[17]  Kyungnam Kim,et al.  Rapid 3D registration using local subtree caching in iterative closest point (ICP) algorithm , 2017, Optical Engineering + Applications.

[18]  Ricardo A. M. Valentim,et al.  Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy , 2016, BioMedical Engineering OnLine.

[19]  Hidefumi Kobatake,et al.  A convergence index filter for vector fields and its application to medical image processing , 2006 .

[20]  Nobuhiro Oda,et al.  Usefulness of computerized method for lung nodule detection on digital chest radiographs using similar subtraction images from different patients. , 2012, European journal of radiology.

[21]  Huimin Lu,et al.  Automatic classification of lung nodules on MDCT images with the temporal subtraction technique , 2017, International Journal of Computer Assisted Radiology and Surgery.

[22]  Jin Dong Song,et al.  Enhanced characteristics of In_ Ga_ As Quantum Dot Infrared Photo detector with Hydrogen Plasma Treatment , 2007 .

[23]  Pere J Riu.  Book review of “Biomagnetics: Principles and Applications of Biomagnetic Stimulation and Imaging” edited by Shoogo Ueno and Masaki Sekino , 2016, Biomedical engineering online.

[24]  Kunio Doi,et al.  A new registration method with voxel-matching technique for temporal subtraction images , 2008, SPIE Medical Imaging.

[25]  Jing Zhang,et al.  5G-Smart Diabetes: Toward Personalized Diabetes Diagnosis with Healthcare Big Data Clouds , 2018, IEEE Communications Magazine.

[26]  Yamoto Shigetsune.  A Research of Capability for Producing Popular TV Program , 2013 .