A deep image classification model based on prior feature knowledge embedding and application in medical diagnosis.

Aiming at the problem of image classification with insignificant morphological structural features, strong target correlation, and low signal-to-noise ratio, combined with prior feature knowledge embedding, a deep learning method based on ResNet and Radial Basis Probabilistic Neural Network (RBPNN) is proposed model. Taking ResNet50 as a visual modeling network, it uses feature pyramid and self-attention mechanism to extract appearance and semantic features of images at multiple scales, and associate and enhance local and global features. Taking into account the diversity of category features, channel cosine similarity attention and dynamic C-means clustering algorithms are used to select representative sample features in different category of sample subsets to implicitly express prior category feature knowledge, and use them as the kernel centers of radial basis probability neurons (RBPN) to realize the embedding of diverse prior feature knowledge. In the RBPNN pattern aggregation layer, the outputs of RBPN are selectively summed according to the category of the kernel center, that is, the subcategory features are combined into category features, and finally the image classification is implemented based on Softmax. The functional module of the proposed method is designed specifically for image characteristics, which can highlight the significance of local and structural features of the image, form a non-convex decision-making area, and reduce the requirements for the completeness of the sample set. Applying the proposed method to medical image classification, experiments were conducted based on the brain tumor MRI image classification public dataset and the actual cardiac ultrasound image dataset, and the accuracy rate reached 85.82% and 83.92% respectively. Compared with the three mainstream image classification models, the performance indicators of this method have been significantly improved.

Bibliometric mapping of microbiology research topics (2012-16): a comparison by socioeconomic development and infectious disease vulnerability values.

Amongst health-related scientific disciplines, microbiology appears to play a vital role in creating a sustainable future with respect to health, the environment and a biobased economy. Microbiology research covers a wide range of different disciplines and addresses many important global issues. This study aimed to identify topics being addressed within the last 5 years (2012-16) in the field of microbiology worldwide and to compare them in terms of three different indicators: gross domestic product, Human Development Index and Infectious Disease Vulnerability Index. The dataset of this study comprised 167 874 articles and reviews from 2012 to 2016, which were extracted from the Web of Science Medline. To identify and visualise the topics addressed during the studied period, VOSviewer was used. The construction and visualisation of the term map was done based on 5918 MESH subject headings. The methodology and procedures employed included Kruskal-Wallis test and two-sample proportion test. Overall, our study showed that the field of microbiology has focused on six different topics during 2012-16. The papers written with the collaboration of countries with low socioeconomic status and high vulnerability to infectious diseases mainly addressed topics related to the primary needs of people such as food safety, the prevention and control of infectious diseases, food and energy poverty. In contrast, papers written with the collaboration of countries with high socioeconomic development status and less vulnerability to infectious diseases mainly focused on big data, alternative methods to animal experiments.