Implementation of deep neural networks to count dopamine neurons in substantia nigra.

Unbiased estimates of neuron numbers within substantia nigra are crucial for experimental Parkinson's disease models and gene-function studies. Unbiased stereological counting techniques with optical fractionation are successfully implemented, but are extremely laborious and time-consuming. The development of neural networks and deep learning has opened a new way to teach computers to count neurons. Implementation of a programming paradigm enables a computer to learn from the data and development of an automated cell counting method. The advantages of computerized counting are reproducibility, elimination of human error and fast high-capacity analysis. We implemented whole-slide digital imaging and deep convolutional neural networks (CNN) to count substantia nigra dopamine neurons. We compared the results of the developed method against independent manual counting by human observers and validated the CNN algorithm against previously published data in rats and mice, where tyrosine hydroxylase (TH)-immunoreactive neurons were counted using unbiased stereology. The developed CNN algorithm and fully cloud-embedded Aiforia™ platform provide robust and fast analysis of dopamine neurons in rat and mouse substantia nigra.

Temporal, seasonal, and regional differences in births and deaths in Aland (Finland).

A good knowledge of the seasonal variation during normal years is of fundamental importance for analyses of the effects of wars, famines, epidemics, or similar privations on births and deaths. In this study we consider data from the Aland Islands (Finland) for 1650-1950. During the period 1650-1793 there are subperiods with missing data for all parishes, and consequently the total data for the Aland Islands for this period have to be estimated using available data. For the period 1794-1950 the registered data seem to be complete and reliable, but the war year 1809 shows a marked deficit of births. During the last decades of the 19th century the number of births increases markedly and after that shows a strong decrease. After the 1930s births increase again. To allow seasonality comparisons between the Aland Islands as a whole and its subregions, we base our studies on seasonal indexes. There is a markedly decreasing temporal trend in the seasonal variation of births for the Aland Islands as a whole, but the general pattern remains mainly the same, having two peaks, one in March-April and one in September-October. For the period 1901-1950 the seasonal variation almost disappeared. The strength of the seasonal variation in births shows regional differences, but the general pattern is mainly the same. The outermost parish, Kökar, an isolate of its own, shows the strongest seasonal variation in births. The annual number of deaths shows some marked peaks, especially in the war year 1809. For both sexes there are marked peaks in 1809, indicating that the deaths were mainly caused by epidemic diseases rather than by killing in battles. For mortality a decreasing trend in the seasonal variation is observed during 1650-1750, but after 1751-1800 the strength of seasonality shows an increasing trend and a sinusoidal pattern.