Breast mass is one of the most distinctive signs for the diagnosis of breast cancer, and the accurate segmentation of masses is critical for improving the accuracy of breast cancer detection and reducing the mortality rate. It is time-consuming for a physician to review the film. Besides, traditional medical segmentation techniques often require prior knowledge or manual extraction of features, which often lead to a subjective diagnosis. Therefore, developing an automatic image segmentation method is important for clinical application. In this paper, a fully automatic method based on deep learning for breast mass segmentation is proposed, which combines densely connected U-Net with attention gates (AGs). It contains an encoder and a decoder. The encoder is a densely connected convolutional network and the decoder is the decoder of U-Net integrated with AGs. The proposed method is tested on the public and authoritative database-Digital Database for Screening Mammography (DDSM) database. F1-score, mean intersection over union, sensitivity, specificity, and overall accuracy are used to evaluate the effectiveness of the proposed method. The experimental results show that dense U-Net integrated AGs achieve better segmentation results than U-Net, attention U-Net, DenseNet, and state-of-the-art methods. INDEX TERMS Breast masses segmentation, deep learning, biomedical image processing, attention gates, densely connected convolutional network.

No abstract

Spectral transmittance and reflectance in the 300 to 2500 nm solar-optical wavelength range were calculated for nanoparticles of titanium dioxide and vanadium dioxide with radii between 5 and 100 nm embedded in transparent dielectric media. Both of the materials are of large importance in green nanotechnologies: thus TiO 2 is a photocatalyst that can be applied as a porous film or a nanoparticle composite on indoor or outdoor surfaces for environmental remediation, and VO 2 is a thermochromic material with applications to energy-efficient fenestration. The optical properties, including scattering, of the nanoparticle composites were computed from the Maxwell-Garnett effective-medium theory as well as from a four-flux radiative transfer model. Predictions from these theories approach one another in the limit of small particles and in the absence of optical interference. Effects of light scattering can be modeled only by the four-flux theory, though. We found that nanoparticle radii should be less than ~20 nm in order to avoid pronounced light scattering.

No abstract