Search

The early detection of traumatic brain injuries can directly impact the prognosis and survival of patients. Preceding attempts to automate the detection and the assessment of the severity of traumatic brain injury continue to be based on clinical diagnostic methods, with limited tools for disease outcomes in large populations. Despite advances in machine and deep learning tools, current approaches still use simple trends of statistical analysis which lack generality. The effectiveness of deep learning to extract information from large subsets of data can be further emphasised through the use of more elaborate architectures. We therefore explore the use of a multiple input, convolutional neural network and long short-term memory (LSTM) integrated architecture in the context of traumatic injury detection through predicting the presence of brain injury in a murine preclinical model dataset. We investigated the effectiveness and validity of traumatic brain injury detection in the proposed model against various other machine learning algorithms such as the support vector machine, the random forest classifier and the feedforward neural network. Our dataset was acquired using a home cage automated (HCA) system to assess the individual behaviour of mice with traumatic brain injury or non-central nervous system (non-CNS) injured controls, whilst housed in their cages. Their distance travelled, body temperature, separation from other mice and movement were recorded every 15 minutes, for 72 hours weekly, for 5 weeks following intervention. The HCA behavioural data was used to train a deep learning model, which then predicts if the animals were subjected to a brain injury or just a sham intervention without brain damage. We also explored and evaluated different ways to handle the class imbalance present in the uninjured class of our training data. We then evaluated our models with leave-one-out cross validation. Our proposed deep learning model achieved the best performance and showed promise in its capability to detect the presence of brain trauma in mice.

Dexamphetamine (AMPH) is a psychostimulant drug that is used both recreationally and as medication for attention deficit hyperactivity disorder. Preclinical studies have demonstrated that repeated exposure to AMPH can induce damage to nerve terminals of dopamine (DA) neurons. We here assessed the underlying neurobiological changes in the DA system following repeated AMPH exposure and pre-treated rats with AMPH or saline (4 times 5 mg/kg s.c., 2 hours apart), followed by a 1-week washout period. We then used pharmacological MRI (phMRI) with a methylphenidate (MPH) challenge, as a sensitive and non-invasive in-vivo measure of DAergic function. We subsequently validated the DA-ergic changes post-mortem, using a.o. high-performance liquid chromatography (HPLC) and autoradiography. In the AMPH pre-treated group, we observed a significantly larger BOLD response to the MPH challenge, particularly in DA-ergic brain areas and their downstream projections. Subsequent autoradiography studies showed that AMPH pre-treatment significantly reduced DA transporter (DAT) density in the caudate-putamen (CPu) and nucleus accumbens, whereas HPLC analysis revealed increases in the DA metabolite homovanillic acid in the CPu. Our results suggest that AMPH pre-treatment alters DAergic responsivity, a change that can be detected with phMRI in rats. These phMRI changes likely reflect increased DA release together with reduced DAT binding. The ability to assess subtle synaptic changes using phMRI is promising for both preclinical studies of drug discovery, and for clinical studies where phMRI can be a useful tool to non-invasively investigate DA abnormalities, e.g. in neuropsychiatric disorders.