Automatic recognition of breast invasive ductal carcinoma based on terahertz spectroscopy with wavelet packet transform and machine learning.

We demonstrate an automatic recognition strategy for terahertz (THz) pulsed signals of breast invasive ductal carcinoma (IDC) based on a wavelet entropy feature extraction and a machine learning classifier. The wavelet packet transform was implemented into the complexity analysis of the transmission THz signal from a breast tissue sample. A novel index of energy to Shannon entropy ratio (ESER) was proposed to distinguish different tissues. Furthermore, the principal component analysis (PCA) method and machine learning classifier were further adopted and optimized for automatic classification of the THz signal from breast IDC sample. The areas under the receiver operating characteristic curves are all larger than 0.89 for the three adopted classifiers. The best breast IDC recognition performance is with the precision, sensitivity and specificity of 92.85%, 89.66% and 96.67%, respectively. The results demonstrate the effectiveness of the ESER index together with the machine learning classifier for automatically identifying different breast tissues.

Self-Assembled Formation of Well-Aligned Cu-Te Nano-Rods on Heavily Cu-Doped ZnTe Thin Films.

Cu doping of ZnTe, which is an important semiconductor for various optoelectronic applications, has been successfully achieved previously by several techniques. However, besides its electrical transport characteristics, other physical and chemical properties of heavily Cu-doped ZnTe have not been reported. We found an interesting self-assembled formation of crystalline well-aligned Cu-Te nano-rods near the surface of heavily Cu-doped ZnTe thin films grown via the molecular beam epitaxy technique. A phenomenological growth model is presented based on the observed crystallographic morphology and measured chemical composition of the nano-rods using various imaging and chemical analysis techniques. When substitutional doping reaches its limit, the extra Cu atoms favor an up-migration toward the surface, leading to a one-dimensional surface modulation and formation of Cu-Te nano-rods, which explain unusual observations on the reflection high energy electron diffraction patterns and apparent resistivity of these thin films. This study provides an insight into some unexpected chemical reactions involved in the heavily Cu-doped ZnTe thin films, which may be applied to other material systems that contain a dopant having strong reactivity with the host matrix.