The imaging diagnosis and prognostication of different degrees of traumatic brain injury (TBI) is very important for early care and clinical treatment. Especially, the exact recognition of mild TBI is the bottleneck for current label-free imaging technologies in neurosurgery. Here, we report an automatic evaluation method for TBI recognition with terahertz (THz) continuous-wave (CW) transmission imaging based on machine learning (ML). We propose a new feature extraction method for biological THz images combined with the transmittance distribution features in spatial domain and statistical distribution features in normalized gray histogram. Based on the extracted feature database, ML algorithms are performed for the classification of different degrees of TBI by feature selection and parameter optimization. The highest classification accuracy is up to 87.5%. The area under the curve (AUC) scores of the receiver operating characteristics (ROC) curve are all higher than 0.9, which shows this evaluation method has a good generalization ability. Furthermore, the excellent performance of the proposed system in the recognition of mild TBI is analyzed by different methodological parameters and diagnostic criteria. The system can be extensible to various diseases and will be a powerful tool in automatic biomedical diagnostics.

No abstract

No abstract

There has been a continuing effort to advance the understanding and modeling of frost formation on refrigerated surfaces during the last two decades for better design of air-to-refrigerant heat transfer equipment and effective and energy-saving control of defrosting processes. A review and comparative analysis of the available literature concerning frost properties, correlations, and mathematical models are presented in this study to provide an overview of the analytical tools for researchers, product developers, and designers. The frost research can be divided into two general groups-experimental correlations and mathematical models. In general, the properties correlated are the frost thermal conductivity, the frost average density, and air-frost heat transfer coefficient (Nusselt number). A limited operational range of these relations is observed. The mathematical models include both differential and integral approaches, which are, in general, solved numerically. These models are classified based on the geometrical configuration of cold surface. A comprehensive comparison of the models is given to assist the reader in making their decisions for design analysis. The existing gaps in the frost research are identified and recommendations are made.