Light distribution in a strong turbid medium such as skin tissue depends on both the bulk optical properties and the profiles of the interfaces where mismatch in the refractive index occurs. We present recent results of a numerical investigation on the light distribution inside a human skin tissue phantom for a converging laser beam with a wavelength near 1 mum and its dependence on the roughness of the interfaces and index mismatch. The skin tissue is modeled by a two-layer structure, and within each layer the tissue is considered macroscopically homogeneous. The two interfaces that separate the epidermis from the ambient medium and the dermis are considered randomly rough. With a recently developed method of Monte Carlo simulation capable of treating inhomogeneous boundary conditions, light distributions in various cases of interface roughness and index mismatch are obtained, and their relevance to the measurements of optical parameters of the skin tissue and laser surgery under the skin surface are discussed.

No abstract

Drug-drug interactions (DDIs) may bring huge health risks and dangerous effects to a patient’s body when taking two or more drugs at the same time or within a certain period of time. Therefore, the automatic extraction of unknown DDIs has great potential for the development of pharmaceutical agents and the safety of drug use. In this article, we propose a novel recurrent hybrid convolutional neural network (RHCNN) for DDI extraction from biomedical literature. In the embedding layer, the texts mentioning two entities are represented as a sequence of semantic embeddings and position embeddings. In particular, the complete semantic embedding is obtained by the information fusion between a word embedding and its contextual information which is learnt by recurrent structure. After that, the hybrid convolutional neural network is employed to learn the sentence-level features which consist of the local context features from consecutive words and the dependency features between separated words for DDI extraction. Lastly but most significantly, in order to make up for the defects of the traditional cross-entropy loss function when dealing with class imbalanced data, we apply an improved focal loss function to mitigate against this problem when using the DDIExtraction 2013 dataset. In our experiments, we achieve DDI automatic extraction with a micro F-score of 75.48% on the DDIExtraction 2013 dataset, outperforming the state-of-the-art approach by 2.49%.

A new method of Monte Carlo simulation has been developed to simulate the spatial distribution of photon density of converging laser beams propagating in a turbid medium such as the phantom of biological tissue. This method can be used to obtain steady-state light distribution in the tissue phantom for a continuous-wave laser beam. We have calculated the steady-state distribution of the photon density and found important features that are uniquely related to the propagation of the converging beams in the tissue phantom.