Brain age prediction method based on deep convolutional generative adversarial network / 医疗卫生装备

Objective To propose a brain age prediction method based on deep convolutional generative adversarial networks(DCGAN)for objective assessment of brain health status.Methods The DCGAN model was extended from 2D to 3D and improved by integrating the concept of residual block to enhance the ability for feature extraction.The classifiers were pre-trained with unsupervised adversarial learning and fine-tuned with migration learning to eliminate the overfitting of 3D convolutional neural network(CNN)due to small sample size.To verify the effectiveness of the improved model,comparison analyses based on UK Biobank(UKB)database were carried out between the improved model and least absolute shrinkage and selection operator(LASSO)model,machine learning model,3D CNN model and graph convolutional network model by using mean absolute error(MAE)as the evaluation metric.Results The model proposed gained advantages over LASSO model,machine learning model,3D CNN model and graph convolutional network model in predicting brain age with a MAE error of 2.896 years.Conclusion The method proposed behaves well for large-scale datasets,which can predict brain age accurately and assess brain health status objectively.

Using otolith weight to predict the age of different stocks of Sperata aor (Siluriformes: Bagridae) from the River Ganga

Estimation of accurate fish age is considered as an essential step for the understanding of life history characteristics, population dynamics, and the management of the fisheries resources. The otolith weight keeps on increasing because of continuous deposition of material on the otolith surface; therefore, otolith measurements are successfully used to infer fish age. The present study was conducted to estimate the relationship between otolith weight and observed age (estimated by counting annuli on the sectioned otoliths) for the stocks of Sperata aor. A total of 315 samples were collected from January 2016 to April 2017 from three different stocks of S. aor i.e. Narora-Kanpur, Varanasi and Bhagalpur from the River Ganga. Linear regression analysis was applied between otolith weight and observed age to predict the age of the fish of each stock from otolith weight. Significant relationships between otolith weight and fish age were observed for the three stocks of the selected fish species from the River Ganga (R2 > 0.9, P 0.05). Overall, 88.5, 88.8, and 87.2 % of the predicted ages were correctly classified to their observed ages for Narora-Kanpur, Varanasi, and Bhagalpur stock, respectively. Thus, it can be concluded that the relationship between otolith weight and fish age can provide a surrogate method of age estimation, and can be used to examine the age structure of the three stocks of S. aor from the River Ganga.

La estimación precisa de la edad de peces es considerada un paso esencial para la evaluación de su historia natural, dinámica de población y manejo de pesquerías. El otolito sigue creciendo debido a la continua deposición de material en la superficie; por lo tanto, las medidas del otolito son un buen indicador para inferir la edad del pez. En este estudio se evaluó la relación entre el peso de los otolitos y la edad observada (estimada contando los anillos de los otolitos seleccionados) de individuos de Sperata aor. En total se recolectaron 315 muestras entre enero 2016 y abril 2017 en tres zonas de S. aor en el Río Ganga (Narora-Kanpur, Varanasi y Bhagalpur). Se aplicó un análisis de regresión lineal entre el peso de los otolitos y la edad observada para predecir la edad de los peces de cada zona a partir del peso de los otolitos. Se observaron relaciones significativas entre el peso de los otolitos y la edad de los peces de las zonas del Río Ganga (R2 > 0.9, P 0.05). En general, 88.5, 88.8 y 87.2% de las edades predichas se clasificaron correctamente con respecto a las edades observadas para Narora-Kanpur, Varanasi y Bhagalpur, respectivamente. Se puede concluir que la relación entre el peso de los otolitos y la edad de los peces puede proveer un método para la estimación de la edad y puede ser usado para examinar la estructura de edades en tres stocks de S. aor en el Río Ganga.