A deep learning-based approach for unbiased kinematic analysis in CNS injury

Traumatic spinal cord injury (SCI) is a devastating condition that impacts over 300,000 individuals in the US alone. Depending on the severity of the injury, SCI can lead to varying degrees of sensorimotor deficits and paralysis. Despite advances in our understanding of the underlying pathological mechanisms of SCI and the identification of promising molecular targets for repair and functional restoration, few therapies have made it into clinical use. To improve the success rate of clinical translation, more robust, sensitive, and reproducible means of functional assessment are required. The gold standards for the evaluation of locomotion in rodents with SCI are the Basso Beattie Bresnahan (BBB) and Basso Mouse Scale (BMS) tests. To overcome the shortcomings of current methods, we developed two separate marker-less kinematic analysis paradigms in mice, MotorBox and MotoRater, based on deep-learning algorithms generated with the DeepLabCut open-source toolbox. The MotorBox system uses an originally designed, custom-made chamber, and the MotoRater system was implemented on a commercially available MotoRater device. We validated the MotorBox and MotoRater systems by comparing them with the traditional BMS test and extracted metrics of movement and gait that can provide an accurate and sensitive representation of mouse locomotor function post-injury, while eliminating investigator bias and variability. The integration of MotorBox and/or MotoRater assessments with BMS scoring will provide a much wider range of information on specific aspects of locomotion, ensuring the accuracy, rigor, and reproducibility of behavioral outcomes after SCI.

Highlights

MotorBox and MotoRater systems are two novel marker-less kinematic analysis paradigms in mice, based on deep-learning algorithms generated with DeepLabCut.MotorBox and MotoRater systems are highly sensitive, accurate and unbiased in analyzing locomotor behavior in mice.MotorBox and MotoRater systems allow for sensitive detection of SCI-induced changes in movement metrics, including range of motion, gait, coordination, and speed.MotorBox and MotoRater systems allow for detection of movement metrics not measurable with the BMS.

Microglia activation in postmortem brains with schizophrenia demonstrates distinct morphological changes between brain regions

Schizophrenia (SCZ) is a psychiatric disorder that can include symptoms of disorganized speech and thoughts with uncertain underlying mechanisms possibly linked to over-activated microglia. In this study, we used brain samples from sixteen donors with SCZ and thirteen control donors to assess the differential activation of microglia by quantifying density and 3D reconstruction of microglia stained with ionized calcium-binding adaptor molecule-1 (Iba1). Our samples consisted of sections from the frontal, temporal, and cingulate cortical gray matter, subcortical white matter regions (SCWM), and included the anterior corpus callosum. In the first series of studies, we performed a density analysis followed by a spatial analysis to ascertain the microglial density, distribution, and soma size in SCZ brains. Second, we performed a series of morphological quantification techniques to investigate the arborization patterns of the microglia in SCZ. The results demonstrated an increase in microglia density in the cortical gray matter regions in SCZ cases, while in the SCWM, there was a significant increase in microglia density in the frontal and temporal, but not in the other brain regions of interest (ROIs). Spatial analysis using the "nearest neighbor" demonstrated that there was no effect in "clustering", but there were shorter distances between microglia seen in the SCZ cases. The morphological measures showed that there was a region-dependent increase in the microglia soma size in the SCZ cases while the Sholl analysis revealed a significant decrease in the microglia arborization in the SCZ cases across all the ROI's studied. An in-depth 3D reconstruction of microglia in Brodmann area 9 cortical region found that there was a significant association between age and reduced microglial arborization in the SCZ cases. This region-dependent age association can help determine whether longitudinal changes in microglial activation across age are brain region-dependent, which may point to potential therapeutic targets.