Kim DY, et al. Brain Neurorehabil. 2023 Jul;16(2):e18. https://doi.org/10.12786/bn.2023.16.e18

Kinematic analysis of the hyoid bone in a videofluorosopic swallowing study (VFSS) is important for assessing dysphagia. However, calibrating the hyoid bone movement is time-consuming, and its reliability shows wide variation. Computer-assisted analysis has been studied to improve the efficiency and accuracy of hyoid bone identification and tracking, but its performance is limited. In this study, we aimed to design a robust network that can track hyoid bone movement automatically without human intervention. Using 69,389 frames from 197 VFSS files as the data set, a deep learning model for detection and trajectory prediction was constructed and trained by the BiFPN-U-Net(T) network. The present model showed improved performance when compared with the previous models: an area under the curve (AUC) of 0.998 for pixelwise accuracy, an accuracy of object detection of 99.5%, and a Dice similarity of 90.9%. The bounding box detection performance for the hyoid bone and reference objects was superior to that of other models, with a mean average precision of 95.9%. The estimation of the distance of hyoid bone movement also showed higher accuracy. The deep learning model proposed in this study could be used to detect and track the hyoid bone more efficiently and accurately in VFSS analysis.

Exercise training is a traditional method to maximize remaining function in patients with spinal cord injury (SCI), but the exact mechanism by which exercise promotes recovery after SCI has not been identified; whether exercise truly has a beneficial effect on SCI also remains unclear. Previously, we showed that epigenetic changes in the brain motor cortex occur after SCI and that a treatment leading to epigenetic modulation effectively promotes functional recovery after SCI. We aimed to determine how exercise induces functional improvement in rats subjected to SCI and whether epigenetic changes are engaged in the effects of exercise. A spinal cord contusion model was established in rats, which were then subjected to treadmill exercise for 12 weeks. We found that the size of the lesion cavity and the number of macrophages were decreased more in the exercise group than in the control group after 12 weeks of injury. Immunofluorescence and DNA dot blot analysis revealed that levels of 5-methylcytosine (5mC) and 5-hydroxymethylcytosine (5hmC) in the brain motor cortex were increased after exercise. Accordingly, the expression of ten-eleven translocation (Tet) family members (Tet1, Tet2, and Tet3) in the brain motor cortex also elevated. However, no macrophage polarization was induced by exercise. Locomotor function, including Basso, Beattie, and Bresnahan (BBB) and ladder scores, also improved in the exercise group compared to the control group. We concluded that treadmill exercise facilitates functional recovery in rats with SCI, and mechanistically epigenetic changes in the brain motor cortex may contribute to exercise-induced improvements.