Generic placeholder image

Current Medical Imaging

Author(s): Muhammad Laiq Ur Rahman Shahid*, Junaid Mir, Furqan Shaukat, Muhammad Khurram Saleem, Muhammad Atiq Ur Rehman Tariq and Ahmed Nouman

DOI: 10.2174/1573405616666201118143935

DownloadDownload PDF Flyer Cite As
Classification of Pharynx from MRI Using a Visual Analysis Tool to Study Obstructive Sleep Apnea

Page: [613 - 622] Pages: 10

  • * (Excluding Mailing and Handling)

Explore Articles
About Journal
For Authors
For Editors
For Reviewers

Abstract

Background: Obstructive sleep apnea (OSA) is a chronic sleeping disorder. The analysis of the pharynx and its surrounding tissues can play a vital role in understanding the pathogenesis of OSA. Classification of the pharynx is a crucial step in the analysis of OSA.

Methods: A visual analysis-based classifier is developed to classify the pharynx from MRI datasets. The classification pipeline consists of different stages, including pre-processing to select the initial candidates, extraction of categorical and numerical features to form a multidimensional features space, and a supervised classifier trained by using visual analytics and silhouette coefficient to classify the pharynx.

Results: The pharynx is classified automatically and gives an approximately 86% Jaccard coefficient by evaluating the classifier on different MRI datasets. The expert’s knowledge can be utilized to select the optimal features and their corresponding weights during the training phase of the classifier.

Conclusion: The proposed classifier is accurate and more efficient in terms of computational cost. It provides additional insight to better understand the influence of different features individually and collectively. It finds its applications in epidemiological studies where large datasets need to be analyzed.

Keywords: Machine learning algorithm, medical image analysis, classification, MRI, visual analysis, multidimensional feature space, OSA.

Graphical Abstract

[1]
Pack AI. Sleep apnea: Pathogenesis, diagnosis and treatment. (2nded.), CRC Press. 2012.
[2]
Lowe AA, Fleetham JA, Adachi S, Ryan CF. Cephalometric and computed tomographic predictors of obstructive sleep apnea severity. Am J Orthod Dentofacial Orthop 1995; 107(6): 589-95.
[http://dx.doi.org/10.1016/S0889-5406(95)70101-X] [PMID: 7771363]
[3]
Shaw JE, Punjabi NM, Wilding JP, Alberti KG, Zimmet PZ. International Diabetes Federation Taskforce on Epidemiology and Prevention. Sleep-disordered breathing and type 2 diabetes: a report from the International Diabetes Federation Taskforce on Epidemiology and Prevention. Diabetes Res Clin Pract 2008; 81(1): 2-12.
[http://dx.doi.org/10.1016/j.diabres.2008.04.025] [PMID: 18544448]
[4]
Shahid MLUR, Chitiboi T, Ivanovska T, Molchanov V, Völzke H, Linsen L. Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification. BMC Med Imaging 2017; 17(1): 15.
[http://dx.doi.org/10.1186/s12880-017-0179-7] [PMID: 28196476]
[5]
Ivanovska T, Laqua R, Shahid ML, Linsen L, Hegenscheid K, Völzke H. Automatic pharynx segmentation from MRI data for analysis of sleep related disorders. Int J Artif Intell Tools 2015; 24(4): 1550018.
[http://dx.doi.org/10.1142/s0218213015500189]
[6]
Ivanovska T, Dober J, Laqua R, Hegenscheid K, Völzke H. Pharynx segmentation from MRI data for analysis of sleep related disoders. Advances in Visual Computing. . Springer 2013; pp.. 20-9.
[http://dx.doi.org/10.1007/978-3-642-41914-0_3]
[7]
Khan SU, Ullah N, Ahmed I, Ahmad I, Mahsud MI. MRI imaging, comparison of MRI with other modalities, noise in MRI images and machine learning techniques for noise removal: A review. Curr Med Imaging Rev 2019; 15(3): 243-54.
[http://dx.doi.org/10.2174/1573405614666180726124952] [PMID: 31989876]
[8]
Wee A, Liew C, Yan H. Current methods in the automatic tissue segmentation of 3D magnetic resonance brain images. Curr Med Imaging Rev 2006; 2(1): 91-103.
[9]
Ivanovska T, Buttke E, Laqua R, Volzke H, Beule A. Automatic trachea segmentation and evaluation from MRI data using intensity pre-clustering and graph cuts. Image and Signal Processing and Analysis (ISPA). 513-8.
[10]
Kandogan E. Visualizing multi-dimensional clusters, trends, and outliers using Star Coordinates. Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 107-6.
[http://dx.doi.org/10.1145/502512.502530]
[11]
Friendly M. Mosaic displays for multi-way contingency tables. J Am Stat Assoc 1994; 89(425): 190-200.
[http://dx.doi.org/10.1080/01621459.1994.10476460]
[12]
Rousseeuw PJ. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 1987; 20: 53-65.
[http://dx.doi.org/10.1016/0377-0427(87)90125-7]
[13]
Schwab RJ, Pasirstein M, Pierson R, et al. Identification of upper airway anatomic risk factors for obstructive sleep apnea with volumetric magnetic resonance imaging. Am J Respir Crit Care Med 2003; 168(5): 522-30.
[http://dx.doi.org/10.1164/rccm.200208-866OC] [PMID: 12746251]
[14]
Andrysiak R, Frank-Piskorska A, Krolicki L, Mianowicz J, Krasum M, Ruszczynska M. MRI estiamtion of upper airway in patients with obstructive sleep apnea and its correlation with body mass index. The proceeding of 87th scientific assemly and annual meeting. 245.
[15]
Liu J, Udupa JK, Odhnera D, McDonough JM, Arens R. System for upper airway segmentation and measurement with MR imaging and fuzzy connectedness. Acad Radiol 2003; 10(1): 13-24.
[http://dx.doi.org/10.1016/S1076-6332(03)80783-3] [PMID: 12529024]
[16]
Shahid MLUR, Chitiboi T, Ivanovska T, et al. Automatic pharynx segmentation from MRI data for obstructive sleep apnea analysis. VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings. 599-608.
[http://dx.doi.org/10.5220/0005315905990608]
[17]
Ning J, Zhang L, Zhang D, Wu C. Interactive image segmentation by maximal similarity based region merging. Pattern Recognit 2010; 43(2): 445-56.
[http://dx.doi.org/10.1016/j.patcog.2009.03.004]
[18]
Cevikalp H, Verbeek J, Jurie F, Klaser A, Semi AK, Kläser A. Semi-supervised dimensionality reduction using pairwise equivalence constraints. 2008; 1.
[19]
Saad A, Möller T, Hamarneh G. ProbExplorer: Uncertainty-guided exploration and editing of probabilistic medical image segmentation. Comput Graph Forum 2010; 29(3): 1113-22.
[http://dx.doi.org/10.1111/j.1467-8659.2009.01691.x]
[20]
Shaukat F, Javed K, Raja G, Mir J, Shahid MLUR. Automatic lung nodule detection in CT images using convolutional neural networks. IEICE Trans Fundam Electron Commun Comput Sci 2019; 102(10): 109-19.
[http://dx.doi.org/10.1587/transfun.E102.A.1364]
[21]
Inbarani HH, Azar AT. Leukemia image segmentation using a hybrid histogram-based soft covering rough K-means clustering algorithm. Electronics (Basel) 2020; 9(1): 188.
[http://dx.doi.org/10.3390/electronics9010188]
[22]
Rokach L, Maimon O. Data Mmning with decision trees. World Scientific. 2007; Vol. 69.
[http://dx.doi.org/10.1142/6604]
[23]
Yegnanarayana B. Artificial neural networks. Prentice-Hall of India. 1999.
[24]
Gajowniczek K, Grzegorczyk I, Ząbkowski T, Bajaj C. Weighted random forests to improve arrhythmia classification. Electronics (Basel) 2020; 9(1): 99.
[http://dx.doi.org/10.3390/electronics9010099] [PMID: 32051761]
[25]
Noble WS. What is a support vector machine? Nat Biotechnol 2006; 24(12): 1565-7.
[http://dx.doi.org/10.1038/nbt1206-1565] [PMID: 17160063]
[26]
Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 580-7.
[http://dx.doi.org/10.1109/CVPR.2014.81]
[27]
LeCun Y, Boser B, Denker JS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput 1989; 1(4): 541-51.
[http://dx.doi.org/10.1162/neco.1989.1.4.541]
[28]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations. 1409-556.
[29]
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. 234-41.
[http://dx.doi.org/10.1007/978-3-319-24574-4_28]
[30]
Sarfraz M, Ed. Exploring Critical Approaches of Evolutionary Computation. IGI Global. 2019.
[http://dx.doi.org/10.4018/978-1-5225-5832-3]
[31]
Mohammed M, Pathan A-SK. Automatic defense against zero-day polymorphic worms in communication networks. CRC Press. 2013.
[32]
Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion. Pattern Anal Mach Intell IEEE Trans 1990; 12(7): 629-39.
[http://dx.doi.org/10.1109/34.56205]
[33]
Liao P-S, Chen T-S, Chung P-C. A fast algorithm for multilevel thresholding. J Inf Sci Eng 2001; 17.
[34]
Daniel MM, Lorenzi MC, da Costa Leite C, Lorenzi-Filho G. Pharyngeal dimensions in healthy men and women. Clinics (São Paulo) 2007; 62(1): 5-10.
[http://dx.doi.org/10.1590/S1807-59322007000100002] [PMID: 17334543]
[35]
Yang M, Kpalma K, Ronsin J. A survey of shape feature extraction techniques. Pattern Recognit 2008; 43-90.
[36]
Burger W, Burge MJ. Principles of digital image processing. Springer. 2009.
[37]
Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat 2010; 2(4): 433-59.
[http://dx.doi.org/10.1002/wics.101]
[38]
Shahid MLUR, Molchanov V, Mir J, Shaukat F, Linsen L. Interactive visual analytics tool for multidimensional quantitative and categorical data analysis. Inf Vis 2020; 19(3): 234-46.
[http://dx.doi.org/10.1177/1473871620908034]
[39]
Molchanov V, Linsen L. Interactive Design of Multidimensional Data Projection Layout 2014.
[40]
Teoh ST, Ma K-L. Interactive Visual Classification Using Star Coordinates 2003; 178-85 .
[41]
Bordignon AL, Castro R, Lopes H, Lewiner T, Tavares G. Exploratory visualization based on multidimensional transfer functions and star coordinates. Brazilian Symp Comput Graph Image Process. 273-80.
[http://dx.doi.org/10.1109/SIBGRAPI.2006.17]
[42]
Lehmann DJ, Theisel H. Orthographic star coordinates. IEEE Trans Vis Comput Graph 2013; 19(12): 2615-24.
[http://dx.doi.org/10.1109/TVCG.2013.182] [PMID: 24051828]
[43]
Molchanov V, Chitiboi T, Linsen L. Visual analysis of medical image segmentation feature space for interactive supervised classification. In: Bühler K, Linsen L, John NW, Eds. Eurographics Workshop on Visual Computing for Biology and Medicine.
[44]
Gonçalves PJS, Lourenço B, Santos S, Barlogis R, Misson A. Computer vision intelligent approaches to extract human pose and its activity from image sequences. Electronics (Basel) 2020; 9(1): 159.
[http://dx.doi.org/10.3390/electronics9010159]
[45]
Niwattanakul S, Singthongchai J, Naenudorn E, Wanapu S. Using of Jaccard coefficient for keywords similarity. Proceedings of the international multiconference of engineers and computer scientists. 380-4.
[46]
Cervantes-Sanchez F, Cruz-Aceves I, Hernandez-Aguirre A, Hernandez-Gonzalez MA, Solorio-Meza SE. Automatic segmentation of coronary arteries in X-ray angiograms using multiscale analysis and artificial neural networks. Appl Sci (Basel) 2019; 9(24): 5507.
[http://dx.doi.org/10.3390/app9245507]
[47]
Koyejo O, Natarajan N, Ravikumar P, Dhillon IS. Consistent binary classification with generalized performance metrics. 2014.
[48]
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27(8): 861-74.
[http://dx.doi.org/10.1016/j.patrec.2005.10.010]
[49]
Rish I, Rish I. An empirical study of the naive Bayes classifier. IJCAI 2001 Work Empir methods. Artif Intell 2001; 3(22): 41-6.