Peng Yu-lan

The role of ultrasonography in the diagnosis of gluteal muscle contracture

AimTo evaluate the use of ultrasonography (US) in the diagnosis of gluteal muscle contracture (GMC) by analysis of its imaging characteristics.Materials and MethodsThirty-nine patients suspected of having GMC due to abnormal gait underwent pre-operative US.ResultsThe diagnosis of GMC was confirmed by surgery in 27 patients. Six patients were diagnosed with congenital hip dysplasia, and the remaining six patients were diagnosed with sciatic nerve damage, post-poliomyelitis sequelae, and myasthenia gravis. For the patients with GMC, US showed muscle thinning and hyperechoic strips (specific for muscular contracture) in the muscles involved. In three patients with GMC, the strips were integrated into muscle bundles, demonstrating both strong and weak sonographic echoes. The sensitivity and specificity of the diagnosis of GMC using the presence of strips were 88.9% and 83.3%, respectively, and using muscle thinning, the sensitivity and specificity were 92.6% and 50%, respectively. The contracture strips, as measured by US, were significantly smaller than the actual measurements at the time of surgery, but there was a significant correlation between the two measurements (r = 0.814, P < 0.01). The highest detection rate of GMC by US was found in the gluteus maximus muscle (91.8%), and the lowest rate was found in the piriformis muscle (52.9%).ConclusionUltrasonography is a valuable tool for the diagnosis of GMC, especially for the detection of specific contracture strips in involved muscles. Its role in the pre-operative diagnosis of GMC also provides surgical planning that can guide subsequent treatment.

Boundary-Based Feature Extraction and Recognition of Breast Tumors Using Support Vector Machine

Breast cancer is the most common cancer among women. To assist the ultrasound (US) diagnosis of solid breast tumors, the lobulated contour feature quantified by boundary-based corner counts is studied to classify breast tumors as malignant or benign. The corner points in this research was detected based on wavelet transform (WT), and the classification selected through comparison is Support Vector Machine (SVM), with radial based function (RBF) as the kernel function. Experiments were done on a total of 240 cases of breast lesions, including 104 cases of malignant tumors proved at histology and 136 cases of benign tumors. The accuracy of this system is 95.42%, specificity is 98.53% while sensitivity is 91.35%. Consequently, by SVM, the obtained results show that the pro-posed method can be a new intelligent assistance diagnosis.