Ultrasound texture-based CAD system for detecting neuromuscular diseases

• Published in: International journal for computer assisted radiology and surgery 2015-09, Vol.10 (9), p.1493-1503
• Main Authors: König, Tim, Steffen, Johannes, Rak, Marko, Neumann, Grit, von Rohden, Ludwig, Tönnies, Klaus D.
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Automation; Computer Imaging; Computer Science; Diagnosis, Computer-Assisted - methods; Health Informatics; Humans; Imaging; Medicine; Medicine & Public Health; Middle Aged; Muscle, Skeletal - diagnostic imaging; Myositis - diagnostic imaging; Neuromuscular Diseases - diagnosis; Neuromuscular Diseases - diagnostic imaging; Original Article; Pattern Recognition and Graphics; Principal Component Analysis; Radiology; Reproducibility of Results; Sensitivity and Specificity; Support Vector Machine; Surgery; Ultrasonography; Vision
• ISSN: 1861-6410; 1861-6429
• DOI: 10.1007/s11548-014-1133-6

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.