Aiforia speeds up research on Parkinson’s disease
When studying Parkinson’s disease, it is essential to recognize and count the neuronal cells from microscopic brain sections. Stereology is the current gold standard to count the neurons, but time-consuming and prone to human errors, since it requires a lot of manual hands-on work.
Watch how Aiforia AI is used in University of Helsinki study to count Dopamine neurons in substantia nigra.
Eur J Neurosci. 2018;1–8.
Implementation of deep neural networks to count dopamine neurons in substantia nigra
ABSTRACT 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 highcapacity 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.
J Neuro Res. 2018;1–16.
Downregulation of tyrosine hydroxylase phenotype after AAV injection above substantia nigra: Caution in experimental models of Parkinson’s disease
ABSTRACT Adeno‐associated virus (AAV) vector‐mediated delivery of human α‐synuclein (α‐syn) gene in rat substantia nigra (SN) results in increased expression of α‐syn protein in the SN and striatum which can progressively degenerate dopaminergic neurons. Therefore, this model is thought to recapitulate the neurodegeneration in Parkinson’s disease. Here, using AAV to deliver α‐syn above the SN in male and female rats re‐ sulted in clear expression of human α‐syn in the SN and striatum. The protein was associated with moderate behavioral deficits and some loss of tyrosine hydroxylase (TH) in the nigrostriatal areas. However, the immunohistochemistry results were highly variable and showed little to no correlation with behavior and the amount of α‐syn present. Expression of green fluorescent protein (GFP) was used as a control to monitor gene delivery and expression efficacy. AAV‐GFP resulted in a similar or greater TH loss compared to AAV‐α‐syn and therefore an additional vector that does not express a protein was tested. Vectors with double‐floxed inverse open reading frame (DIO ORF) encoding fluorescent proteins that generate RNA that is not trans‐ lated also resulted in TH downregulation in the SN but showed no significant behav‐ ioral deficits. These results demonstrate that although expression of wild‐type human α‐syn can cause neurodegeneration, the variability and lack of correlation with outcome measures are drawbacks with the model. Furthermore, design and control selection should be considered carefully because of conflicting conclusions due to AAV downregulation of TH, and we recommend caution with having highly regulated TH as the only marker for the dopamine system.
Meet us at:
April 25-27 2019 ,Clearwater Beach, FL, United States
Nordic Neuroscience 2019
June 12-14 2019 Helsinki, Finland
Digital Pathology & AI
June 13-14 2019 New York City, NY, United States
Interested in Aiforia AI?
Schedule a meeting or a demo with us to learn more how Aiforia AI could help you in your research.