Contrast Stretching-Based Unwanted Artifacts Removal from CT Images

This paper presents a contrast stretching-based image enhancement technique to remove unwanted artifacts, such as flesh and to enhance bony regions from Computed Tomographic (CT) images. Our technique is based on enhancing the dynamic range of the image by linear contrast stretching through histogram modeling and intensity transformation function. The intensity range: low and high-intensity values are heuristically computed, and squared shape mask is moved to clean the image further. Experiments are carried out on several patient-specific CT images (source: Prism Medical Diagnostics lab, Chhatrapati Shivaji Maharaj Sarvopachar Ruganalay and Ashwini Hospital, India). Our results show that the technique provides the reliable promising results. Besides, the tool is simple, faster and easy to implement.

[1]  W. Rand,et al.  Quantitative evaluation of bone density using the Hounsfield index. , 2006, The International journal of oral & maxillofacial implants.

[2]  Maxime Descoteaux,et al.  Bone enhancement filtering: Application to sinus bone segmentation and simulation of pituitary surgery , 2006, Computer aided surgery : official journal of the International Society for Computer Aided Surgery.

[3]  Jiing-Yih Lai,et al.  Algorithm for segmentation and reduction of fractured bones in computer-aided preoperative surgery , 2016, ICBBE '16.

[4]  Manoj Kumar,et al.  CT image noise reduction based on adaptive wiener filtering with Wavelet packet thresholding , 2014, 2014 International Conference on Parallel, Distributed and Grid Computing.

[5]  Félix Paulano,et al.  3D segmentation and labeling of fractured bone from CT images , 2014 .

[6]  J. Anitha,et al.  Image Pre-processing and Feature Extraction Techniques for Magnetic Resonance Brain Image Analysis , 2012, FGIT-FGCN/DCA.

[7]  Gábor Székely,et al.  Semi-automatic Segmentation of Fractured Pelvic Bones for Surgical Planning , 2010, ISMBS.

[8]  Ravindra Hegadi,et al.  Automated Fractured Bone Segmentation and Labeling from CT Images , 2019, J. Medical Syst..

[9]  Partha Pratim Roy,et al.  Arrow detection in biomedical images using sequential classifier , 2018, Int. J. Mach. Learn. Cybern..

[10]  Zheng Lin,et al.  Unseeded Region Growing for 3D Image Segmentation , 2000, VIP.

[11]  J F Heautot,et al.  CT-scan images preprocessing and segmentation to improve bioprosthesis leaflets morphological analysis. , 2013, Medical hypotheses.

[12]  Yan Kang,et al.  A new accurate and precise 3-D segmentation method for skeletal structures in volumetric CT data , 2003, IEEE Transactions on Medical Imaging.

[13]  Mohammed M. Abdelsamea.  An Automatic Seeded Region Growing for 2D Biomedical Image Segmentation , 2014, ArXiv.

[14]  Isaac N. Bankman,et al.  Handbook of medical image processing and analysis , 2009 .

[15]  Laurent Wendling,et al.  Overlaid Arrow Detection for Labeling Regions of Interest in Biomedical Images , 2016, IEEE Intelligent Systems.

[16]  G. Hounsfield.  Computed Medical Imaging , 1980, Science.

[17]  Benoit M. Macq,et al.  Segmentation using a region-growing thresholding , 2005, IS&T/SPIE Electronic Imaging.

[18]  Kenneth A. Egol,et al.  Comprar Handbook of Fractures | Kenneth J. Koval | 9781451193626 | Lippincott Williams & Wilkins , 2014 .

[19]  Li Ke,et al.  Multiscale Wiener filtering method for low-dose CT images , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[20]  Ravindra Hegadi,et al.  A Systematic Review on Orthopedic Simulators for Psycho-Motor Skill and Surgical Procedure Training , 2018, Journal of Medical Systems.

[21]  K. Najarian,et al.  Automated bone segmentation from Pelvic CT images , 2008, 2008 IEEE International Conference on Bioinformatics and Biomeidcine Workshops.

[22]  Andrew R. Willis,et al.  3D reconstruction of highly fragmented bone fractures , 2007, SPIE Medical Imaging.