(Aim) Abnormal breast can be diagnosed using the digital mammography. Traditional manual interpretation method cannot yield high accuracy. (Method) In this study, we proposed a novel computer-aided diagnosis system for detecting abnormal breasts in mammogram images. First, we segmented the region-of-interest. Next, the weighted-type fractional Fourier transform (WFRFT) was employed to obtain the unified time-frequency spectrum. Third, principal component analysis (PCA) was introduced and used to reduce the spectrum to only 18 principal components. Fourth, feed-forward neural network (FNN) was utilized to generate the classifier. Finally, a novel algorithm-specific parameter free approach, Jaya, was employed to train the classifier. (Results) Our proposed WFRFT + PCA + Jaya-FNN achieved sensitivity of 92.26%±3.44%, specificity of 92.28%±3.58%, and accuracy of 92.27%±3.49%. (Conclusions) The proposed CAD system is effective in detecting abnormal breasts and performs better than 5 state-of-the-art systems. Besides, Jaya is more effective in training FNN than BP, MBP, GA, SA, and PSO. ∗Address for correspondence: Jiangsu Key Laboratory of 3D, Printing Equipment and Manufacturing, Nanjing, Jiangsu 210042, China 192 S. Wang et al. / Abnormal Breast Detection in Mammogram Images by Feed-forward Neural Network Trained

Abnormal Breast Detection in Mammogram Images by Feed-forward Neural Network Trained by Jaya Algorithm

A novel, simple, and compact optical fiber directional bending vector sensor based on Mach-Zehnder interferometer (MZI) is proposed and experimentally demonstrated. The device consists of a piece of seven-core photonic crystal fiber (PCF) sandwiched between two single mode fibers (SMFs) with a lateral offset splicing joint that covering two cores of PCF. Bending sensitivity of the seven-core PCF based MZI is changed by an axial rotation angle, which shows its capacity for recognizing positive and negative directions. Within a curvature range of −7.05 m−1 to 7.05 m−1, the calculated bending sensitivities of two resonant central wavelengths with opposite fiber orientations are 1.232 nm/m−1 and 1.174 nm/m−1, respectively. This novel MZI is formed by invoking interference between the LP01-like supermode and other higher order supermodes in the core, which leads to insensitive to ambient refractive index (ARI). We have also investigated the transmission characteristics of the sensor with the temperature change.

Ambient refractive index-independent bending vector sensor based on seven-core photonic crystal fiber using lateral offset splicing.

Generation, optimization, and application of ultrashort femtosecond pulse in mode-locked fiber lasers

Computer-aided detection (CAD) systems can be served as a second view for radiologist. An overview of recent development in CAD methods are presented in this paper. Abnormalities detection, abnormalities classification and content-based image retrieval (CBIR) are briefly reviewed. For the abnormalities detection, micro-calcification detection, mass detection and multi-view based detection are introduced. For the abnormalities classification, micro-calcification classification and mass classification are given.

/pdf/a-survey-of-computer-aided-detection-of-breast-cancer-with-3blgkbvi7v.pdf

A Survey of Computer-aided Detection of Breast Cancer with Mammography

Generation and Categories of Solitons in Various Mode-locked Fiber Lasers

The eigenvalue equation associated with seven-core photonic crystal fiber was derived from coupled-mode equation. Mode properties were analyzed by its eigenvalues and eigenvector. Using the frequency domain finite difference method, the relationship between fiber structure and coupling coefficient was fully discussed through changing the wavelength, hole pitch and core distance. Mode shaping and higher-order supermode cut off was realized. The results were helpful to the fiber structure design and in-phase supermode selection.

Numerical analysis for structure optimization of seven-core photonic crystal fibers

It Is reported that the supercontinuum spectrum can be generated in holey microstructure fibers by femtosecond laser pulses with a 800nm center wavelength. Broadband continua extending from 440 to 890nm are generated in holey microstructure fibers. Based on the theory of scalar approximation, the effective refractive index of the cladding and effective area for the fundamental space-filling mode and chromatic dispersion of fibers are calculated. It is found that the holey microstructure fibers have specifically the ability of controlling dispersion and waveguide property. The mechanism of supercontinuum generation in holey microstructure fibers is explicated preliminarily. The theoretic analysis is in good accodance with the experimental result. It is, considered that supercontinuum broadband spectrum can be generated in holey microstructure fibers even if their cladding constitutes of random gas-line.

Supercontinuum generation in holey microstructure fibers by femtosecond laser pulses

Photonic crystal fibers are a new class of single-material optical fibers with wavelength-scale air holes running down the entire fiber length. Photonic crystal fibers were first developed in 1996 and have subsequently been the focus of increasing scientific and technological interest in the field of fiber optics. The manufacturing, principles, basic properties, and some applications of photonic crystal fibers are briefly described in this paper. A review of our recent work on the nonlinear effects in photonic crystal fibers is presented, and special emphasis is placed on such effects as supercontinuum generation, frequency conversion, and solitons observed when femtosecond light pulses propagate in these fibers.

Enhanced nonlinear effects in photonic crystal fibers

Copper nitride (Cu 3 N) thin films were deposited on glass substrates by reactive radio frequency magnetron sputtering under different radio frequency power ( P ) and nitrogen partial pressure r ( r =N 2 /［N 2 +Ar］). The thickness, crystalline structure and surface morphology of films were characterized by profilometer, X-ray diffraction (XRD) and atomic force microscopy (AFM), respectively. The optical transmission spectrum was obtained by an ultraviolet-visible (UV-VIS) spectrophotometer and the optical band gap ( E g ) was calculated. The results suggest that the films' deposition rate increases with P and r . The surface of the films reveals a compact structure, and the grain size of Cu 3 N is about 30nm. Meanwhile, with increasing r , the grain size and optical band gap of Cu 3 N increase, of which E g ranges from 1.47 to 1.82eV, and the films' growth prefers the (111) direction at low r and the (100) direction at high r .

Li Yan-Feng

Papers

Numerical analysis for structure optimization of seven-core photonic crystal fibers

Supercontinuum generation in holey microstructure fibers by femtosecond laser pulses

Enhanced nonlinear effects in photonic crystal fibers

Effect of nitrogen pressure on structure and optical band gap of copper nitride thin films

Microcalcification clusters processing in mammograms based on relevance vector machine with adaptive kernel learning