Showing papers by "Qi Zhang published in 2015"

Quantification of elastic heterogeneity using contourlet-based texture analysis in shear-wave elastography for breast tumor classification.

Abstract: Ultrasound shear-wave elastography (SWE) has become a valuable tool for diagnosis of breast tumors. The purpose of this study was to quantify the elastic heterogeneity of breast tumors in SWE by using contourlet-based texture features and evaluating their diagnostic performance for classification of benign and malignant breast tumors, with pathologic results as the gold standard. A total of 161 breast tumors in 125 women who underwent B-mode and SWE ultrasonography before biopsy were included. Five quantitative texture features in SWE images were extracted from the directional subbands after the contourlet transform, including the mean (Tmean), maximum (Tmax), median (Tmed), third quartile (Tqt), and standard deviation (Tsd) of the subbands. Diagnostic performance of the texture features and the classic features was compared using the area under the receiver operating characteristic curve (AUC) and the leave-one-out cross validation with Fisher classifier. The feature Tmean achieved the highest AUC (0.968) among all features and it yielded a sensitivity of 89.1%, a specificity of 94.3% and an accuracy of 92.5% for differentiation between benign and malignant tumors via the leave-one-out cross validation. Compared with the best classic feature, i.e., the maximum elasticity, Tmean improved the AUC, sensitivity, specificity and accuracy by 3.5%, 12.7%, 2.8% and 6.2%, respectively. The Tmed, Tqt and Tsd were also superior to the classic features in terms of the AUC and accuracy. The results demonstrated that the contourlet-based texture features captured the tumor's elastic heterogeneity and improved diagnostic performance contrasted with the classic features.

Tumor Classification by Deep Polynomial Network and Multiple Kernel Learning on Small Ultrasound Image Dataset

Abstract: Ultrasound imaging is a most common modality for tumor detection and diagnosis. Deep learning DL algorithms generally suffer from the small sample problem. The traditional texture feature extraction methods are still commonly used for small ultrasound image dataset. Deep polynomial network DPN is a newly proposed DL algorithm with excellent feature representation, which has the potential for small dataset. However, the simple concatenation of the learned hierarchical features from different layers in DPN limits its performance. Since the features from different layers in DPN can be regarded as heterogeneous features, they then can be effectively integrated by multiple kernel learning MKL methods. In this work, we propose a DPN and MKL based feature learning and classification framework DPN-MKL for tumor classification on small ultrasound image dataset. The experimental results show that DPN-MKL algorithm outperforms the commonly used DL algorithms for ultrasound image based tumor classification on small dataset.