Skip to main content
Top
Published in: International Journal of Computer Assisted Radiology and Surgery 9/2015

01-09-2015 | Original Article

Ultrasound texture-based CAD system for detecting neuromuscular diseases

Authors: Tim König, Johannes Steffen, Marko Rak, Grit Neumann, Ludwig von Rohden, Klaus D. Tönnies

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 9/2015

Login to get access

Abstract

Purpose

Diagnosis of neuromuscular diseases in ultrasonography is a challenging task since experts are often unable to discriminate between healthy and pathological cases. A computer-aided diagnosis (CAD) system for skeletal muscle ultrasonography was developed and tested for myositis detection in ultrasound images of biceps brachii.

Methods

Several types of features were extracted from rectangular and polygonal image regions-of-interest (ROIs), including first-order statistics, wavelet-based features, and Haralick’s features. Features were chosen that are sensitive to the change in contrast and structure for pathological ultrasound images of neuromuscular diseases. The number of features was reduced by applying different sequential feature selection strategies followed by a supervised principal component analysis. For classification, two linear approaches were investigated: Fisher’s classifier and the linear support vector machine (SVM) as well as the nonlinear \(k\)-nearest neighbor approach. The CAD system was benchmarked on datasets of 18 subjects, seven of which were healthy, while 11 were affected by myositis. Three expert radiologists provided pre-classification and testing interpretations.

Results

Leave-one-out cross-validation on the training data revealed that the linear SVM was best suited for discriminating healthy and pathological muscle tissue, achieving 85/87 % accuracy, 90 % sensitivity, and 83/85 % specificity, depending on the radiologist.

Conclusion

A muscle ultrasonography CAD system was developed, allowing a classification of an ultrasound image by one-click positioning of rectangular ROIs with minimal user effort. The applicability of the system was demonstrated with the challenging example of myositis detection, showing highly accurate results that were robust to imprecise user input.
Literature
1.
go back to reference Asvestas P, Golemati S, Matsopoulos GK, Nikita KS, Nicolaides AN (2002) Fractal dimension estimation of carotid atherosclerotic plaques from B-mode ultrasound: a pilot study. Ultrasound Med Biol 28:1129–1136CrossRefPubMed Asvestas P, Golemati S, Matsopoulos GK, Nikita KS, Nicolaides AN (2002) Fractal dimension estimation of carotid atherosclerotic plaques from B-mode ultrasound: a pilot study. Ultrasound Med Biol 28:1129–1136CrossRefPubMed
2.
go back to reference Awad J, Krasinski A, Parraga G, Fenster A (2010) Texture analysis of carotid artery atherosclerosis from three-dimensional ultrasound images. Med Phys 37:1382–1391CrossRefPubMed Awad J, Krasinski A, Parraga G, Fenster A (2010) Texture analysis of carotid artery atherosclerosis from three-dimensional ultrasound images. Med Phys 37:1382–1391CrossRefPubMed
3.
go back to reference Basset O, Sun Z, Mestas J, Gimenez G (1993) Texture analysis of ultrasonic images of the prostate by means of co-occurrence matrices. Ultrason Imaging 15:218–237CrossRefPubMed Basset O, Sun Z, Mestas J, Gimenez G (1993) Texture analysis of ultrasonic images of the prostate by means of co-occurrence matrices. Ultrason Imaging 15:218–237CrossRefPubMed
4.
go back to reference Basset O, Duboeuf F, Delhay B, Brusseau E, Cachard C, Tasu J (2008) Texture analysis of ultrasound liver images with contrast agent to characterize the fibrosis stage. In: Proceedings of IEEE ultrasonics symposium, pp 24–27 Basset O, Duboeuf F, Delhay B, Brusseau E, Cachard C, Tasu J (2008) Texture analysis of ultrasound liver images with contrast agent to characterize the fibrosis stage. In: Proceedings of IEEE ultrasonics symposium, pp 24–27
5.
go back to reference Chang RF, Wu WJ, Moon W, Chen DR (2005) Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat 89:179–185CrossRefPubMed Chang RF, Wu WJ, Moon W, Chen DR (2005) Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat 89:179–185CrossRefPubMed
6.
go back to reference Chen DR, Chang RF, Huang YL (1999) Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 213:407–412CrossRefPubMed Chen DR, Chang RF, Huang YL (1999) Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 213:407–412CrossRefPubMed
7.
go back to reference Chen L, Seidel G, Mertins A (2010) Multiple feature extraction for early Parkinson risk assessment based on transcranial sonography image. In: Proceedings of international conference on image processing, pp 2277–2280 Chen L, Seidel G, Mertins A (2010) Multiple feature extraction for early Parkinson risk assessment based on transcranial sonography image. In: Proceedings of international conference on image processing, pp 2277–2280
8.
go back to reference Christodoulou C, Pattichis C, Pantziaris M, Nicolaides A (2003) Texture-based classification of atherosclerotic carotid plaques. IEEE Trans Med Imaging 22:902–912CrossRefPubMed Christodoulou C, Pattichis C, Pantziaris M, Nicolaides A (2003) Texture-based classification of atherosclerotic carotid plaques. IEEE Trans Med Imaging 22:902–912CrossRefPubMed
9.
go back to reference Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics
10.
go back to reference Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, London Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, London
11.
go back to reference Duin R, Juszczak P, Paclik P, Pekalska E, de Ridder D, Tax D, Verzakov S (2013) A MATLAB toolbox for pattern recognition. Delft Univ. Techn., http://prtools.org/, pRTools 4.2.4 Duin R, Juszczak P, Paclik P, Pekalska E, de Ridder D, Tax D, Verzakov S (2013) A MATLAB toolbox for pattern recognition. Delft Univ. Techn., http://​prtools.​org/​, pRTools 4.2.4
12.
go back to reference Finette S, Bleier A, Swindell W (1983) Breast tissue classification using diagnostic ultrasound and pattern recognition techniques: I. Methods of pattern recognition. Ultrason Imaging 5:55–70CrossRefPubMed Finette S, Bleier A, Swindell W (1983) Breast tissue classification using diagnostic ultrasound and pattern recognition techniques: I. Methods of pattern recognition. Ultrason Imaging 5:55–70CrossRefPubMed
13.
go back to reference Good MS, Rose JL, Goldberg BB (1982) Application of pattern recognition techniques to breast cancer detection: Ultrasonic analysis of 100 pathologically confirmed tissue areas. Ultrason Imaging 4:378–396CrossRefPubMed Good MS, Rose JL, Goldberg BB (1982) Application of pattern recognition techniques to breast cancer detection: Ultrasonic analysis of 100 pathologically confirmed tissue areas. Ultrason Imaging 4:378–396CrossRefPubMed
14.
go back to reference Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621CrossRef Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621CrossRef
15.
go back to reference Huang Y, Han X, Tian X, Zhao Z, Zhao J, Hao D (2010) Texture analysis of ultrasonic liver images based on spatial domain methods. In: Proceedings of international congress on image signal processing, vol 2, pp 562–565 Huang Y, Han X, Tian X, Zhao Z, Zhao J, Hao D (2010) Texture analysis of ultrasonic liver images based on spatial domain methods. In: Proceedings of international congress on image signal processing, vol 2, pp 562–565
16.
go back to reference Huang YL, Wang KL, Chen DR (2006) Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines. Neural Comput Appl 15:164–169CrossRef Huang YL, Wang KL, Chen DR (2006) Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines. Neural Comput Appl 15:164–169CrossRef
17.
go back to reference Kier C, Seidel G, Brüggemann N, Hagenah J, Klein C, Aach T, Mertins A (2009) Transcranial sonography as early indicator for genetic Parkinson’s disease. In: European conference of the international federation for medical and biological engineering, vol 22. Springer, Berlin, pp 456–459 Kier C, Seidel G, Brüggemann N, Hagenah J, Klein C, Aach T, Mertins A (2009) Transcranial sonography as early indicator for genetic Parkinson’s disease. In: European conference of the international federation for medical and biological engineering, vol 22. Springer, Berlin, pp 456–459
18.
go back to reference König T, Rak M, Steffen J, Neumann G, von Rohden L, Tönnies KD (2013) Texture-based detection of myositis in ultrasonographies. Proceedings of Bildverarbeitung für die Medizin (BVM), Informatik aktuell, pp 81–86 König T, Rak M, Steffen J, Neumann G, von Rohden L, Tönnies KD (2013) Texture-based detection of myositis in ultrasonographies. Proceedings of Bildverarbeitung für die Medizin (BVM), Informatik aktuell, pp 81–86
19.
go back to reference Layer G, Zuna I, Lorenz A, Zerban H, Haberkorn U, Bannasch P, van Kaick G, Räth U (1990) Computerized ultrasound B-scan texture analysis of experimental fatty liver disease: influence of total lipid content and fat deposit distribution. Ultrason Imaging 12:171–188CrossRefPubMed Layer G, Zuna I, Lorenz A, Zerban H, Haberkorn U, Bannasch P, van Kaick G, Räth U (1990) Computerized ultrasound B-scan texture analysis of experimental fatty liver disease: influence of total lipid content and fat deposit distribution. Ultrason Imaging 12:171–188CrossRefPubMed
20.
go back to reference Lee WL, Chen YC, Hsieh KS (2003) Ultrasonic liver tissues classification by fractal feature vector based on m-band wavelet transform. IEEE Trans Med Imaging 22:382–392CrossRefPubMed Lee WL, Chen YC, Hsieh KS (2003) Ultrasonic liver tissues classification by fractal feature vector based on m-band wavelet transform. IEEE Trans Med Imaging 22:382–392CrossRefPubMed
21.
go back to reference Liao YY, Tsui PH, Li CH, Chang KJ, Kuo WH, Chang CC, Yeh CK (2011) Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images. Med Phys 38:2198–2207CrossRefPubMed Liao YY, Tsui PH, Li CH, Chang KJ, Kuo WH, Chang CC, Yeh CK (2011) Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images. Med Phys 38:2198–2207CrossRefPubMed
22.
go back to reference Lu NH, Kuo CM, Ding HJ (2013) Automatic ROI segmentation in B-mode ultrasound image for liver fibrosis classification. In: Proceedings of international symposium on biometrics and security technologies (ISBAST), pp 10–13 Lu NH, Kuo CM, Ding HJ (2013) Automatic ROI segmentation in B-mode ultrasound image for liver fibrosis classification. In: Proceedings of international symposium on biometrics and security technologies (ISBAST), pp 10–13
23.
go back to reference Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11:674–693CrossRef Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11:674–693CrossRef
24.
go back to reference Minhas FU, Sabih D, Hussain M (2012) Automated classification of liver disorders using ultrasound images. J Med Sys 36:3163–3172CrossRef Minhas FU, Sabih D, Hussain M (2012) Automated classification of liver disorders using ultrasound images. J Med Sys 36:3163–3172CrossRef
25.
go back to reference Mohamed S, Salama M (2008) Prostate cancer spectral multifeature analysis using TRUS images. IEEE Trans Med Imaging 27:548–556CrossRefPubMed Mohamed S, Salama M (2008) Prostate cancer spectral multifeature analysis using TRUS images. IEEE Trans Med Imaging 27:548–556CrossRefPubMed
26.
go back to reference Ogawa K, Fukushima M, Kubota K, Hisa N (1998) Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural networks. IEEE Trans Nucl Sci 45:3069–3074CrossRef Ogawa K, Fukushima M, Kubota K, Hisa N (1998) Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural networks. IEEE Trans Nucl Sci 45:3069–3074CrossRef
27.
go back to reference Pillen S, van Alfen N (2010) Skeletal muscle ultrasound. Eur J Transl Myol 1:145–155CrossRef Pillen S, van Alfen N (2010) Skeletal muscle ultrasound. Eur J Transl Myol 1:145–155CrossRef
28.
go back to reference Pohle R, Fischer D, von Rohden L (2000) Computer-supported tissue characterization in ultrasound images of neuromuscular diseases. Ultrasound Med 21:245–252 Pohle R, Fischer D, von Rohden L (2000) Computer-supported tissue characterization in ultrasound images of neuromuscular diseases. Ultrasound Med 21:245–252
29.
go back to reference Reimers K, Reimers CD, Wagner S, Paetzke I, Pongratz DE (1993) Skeletal muscle sonography: a correlative study of echogenicity and morphology. J Med Ultrasound 12:73–77 Reimers K, Reimers CD, Wagner S, Paetzke I, Pongratz DE (1993) Skeletal muscle sonography: a correlative study of echogenicity and morphology. J Med Ultrasound 12:73–77
30.
go back to reference von Rohden L, Wien F, Ptzsch S (2007) Myosonographie neuromuskulärer Erkrankungen unter besonderer Berücksichtigung des Kindes- und Jugendalters. Klin Neurophysiol 38:141–154CrossRef von Rohden L, Wien F, Ptzsch S (2007) Myosonographie neuromuskulärer Erkrankungen unter besonderer Berücksichtigung des Kindes- und Jugendalters. Klin Neurophysiol 38:141–154CrossRef
31.
go back to reference Sakalauskas A, Lukoševičius A, Laučkaite K (2011) Texture analysis of transcranial sonographic images for Parkinson disease diagnostics. Ultragarsas 66:32–36 Sakalauskas A, Lukoševičius A, Laučkaite K (2011) Texture analysis of transcranial sonographic images for Parkinson disease diagnostics. Ultragarsas 66:32–36
32.
go back to reference Sakr AA, Fares ME, Ramadan M (2014) Automated focal liver lesion staging classification based on Haralick texture features and multi-SVM. Int J Comput Appl 91(8):17–25 Sakr AA, Fares ME, Ramadan M (2014) Automated focal liver lesion staging classification based on Haralick texture features and multi-SVM. Int J Comput Appl 91(8):17–25
33.
go back to reference Sheppard M, Shih L (2007) P6C-2 image texture clustering for prostate ultrasound diagnosis. In: Proceedings of IEEE ultrasonic symposium, pp 2473–2476 Sheppard M, Shih L (2007) P6C-2 image texture clustering for prostate ultrasound diagnosis. In: Proceedings of IEEE ultrasonic symposium, pp 2473–2476
34.
go back to reference Su Y, Wang Y, Jiao J, Guo Y (2011) Automatic detection and classification of breast tumors in ultrasonic images using texture and morphological features. Open Med Inf J 5:26–37CrossRef Su Y, Wang Y, Jiao J, Guo Y (2011) Automatic detection and classification of breast tumors in ultrasonic images using texture and morphological features. Open Med Inf J 5:26–37CrossRef
35.
go back to reference Tsiaparas NN, Golemati S, Andreadis I, Stoitsis JS, Valavanis I, Nikita KS (2011) Comparison of multiresolution features for texture classification of carotid atherosclerosis from B-mode ultrasound. IEEE Trans Inf Technol Biomed 15:130–137CrossRefPubMed Tsiaparas NN, Golemati S, Andreadis I, Stoitsis JS, Valavanis I, Nikita KS (2011) Comparison of multiresolution features for texture classification of carotid atherosclerosis from B-mode ultrasound. IEEE Trans Inf Technol Biomed 15:130–137CrossRefPubMed
36.
37.
go back to reference Wilhjelm J, Gronholdt ML, Wiebe B, Jespersen S, Hansen L, Sillesen H (1998) Quantitative analysis of ultrasound B-mode images of carotid atherosclerotic plaque: correlation with visual classification and histological examination. IEEE Trans Med Imaging 17:910–922CrossRefPubMed Wilhjelm J, Gronholdt ML, Wiebe B, Jespersen S, Hansen L, Sillesen H (1998) Quantitative analysis of ultrasound B-mode images of carotid atherosclerotic plaque: correlation with visual classification and histological examination. IEEE Trans Med Imaging 17:910–922CrossRefPubMed
38.
go back to reference Wu CM, Chen YC, Hsieh KS (1992) Texture features for classification of ultrasonic liver images. IEEE Trans Med Imaging 11:141–152CrossRefPubMed Wu CM, Chen YC, Hsieh KS (1992) Texture features for classification of ultrasonic liver images. IEEE Trans Med Imaging 11:141–152CrossRefPubMed
39.
go back to reference Wu WJ, Lin SW, Moon WK (2012) Combining support vector machine with genetic algorithm to classify ultrasound breast tumor images. Comput Med Imaging Graph 36(8):627–633CrossRefPubMed Wu WJ, Lin SW, Moon WK (2012) Combining support vector machine with genetic algorithm to classify ultrasound breast tumor images. Comput Med Imaging Graph 36(8):627–633CrossRefPubMed
40.
go back to reference Zhou S, Shi J, Zhu J, Cai Y, Wang R (2013) Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image. Biomed Signal Process Control 8(6):688–696CrossRef Zhou S, Shi J, Zhu J, Cai Y, Wang R (2013) Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image. Biomed Signal Process Control 8(6):688–696CrossRef
Metadata
Title
Ultrasound texture-based CAD system for detecting neuromuscular diseases
Authors
Tim König
Johannes Steffen
Marko Rak
Grit Neumann
Ludwig von Rohden
Klaus D. Tönnies
Publication date
01-09-2015
Publisher
Springer Berlin Heidelberg
Published in
International Journal of Computer Assisted Radiology and Surgery / Issue 9/2015
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI
https://doi.org/10.1007/s11548-014-1133-6

Other articles of this Issue 9/2015

International Journal of Computer Assisted Radiology and Surgery 9/2015 Go to the issue