Machine learning is a powerful tool that is increasingly being used in many research areas, including neuroscience. The recent development of new algorithms and network architectures, especially in the field of deep learning, has made machine learning models more reliable and accurate and useful for the biomedical research sector. By minimizing the effort necessary to extract valuable features from datasets, they can be used to find trends in data automatically and make predictions about future data, thereby improving the reproducibility and efficiency of research. One application is the automatic evaluation of micrograph images, which is of great value in neuroscience research. While the development of novel models has enabled numerous new research applications, the barrier to use these new algorithms has also decreased by the integration of deep learning models into known applications such as microscopy image viewers. For researchers unfamiliar with machine learning algorithms, the steep learning curve can hinder the successful implementation of these methods into their workflows. This review explores the use of machine learning in neuroscience, including its potential applications and limitations, and provides some guidance on how to select a fitting framework to use in real-life research projects.

The spinal cord has a poor ability to regenerate after an injury, which may be due to cell loss, cyst formation, inflammation, and scarring. A promising approach to treating a spinal cord injury (SCI) is the use of biomaterials. We have developed a novel hydrogel scaffold fabricated from oligo(poly(ethylene glycol) fumarate) (OPF) as a 0.08 mm thick sheet containing polymer ridges and a cell-attractive surface on the other side. When the cells are cultured on OPF via chemical patterning, the cells attach, align, and deposit ECM along the direction of the pattern. Animals implanted with the rolled scaffold sheets had greater hindlimb recovery compared to that of the multichannel scaffold control, which is likely due to the greater number of axons growing across it. The immune cell number (microglia or hemopoietic cells: 50–120 cells/mm2 in all conditions), scarring (5–10% in all conditions), and ECM deposits (Laminin or Fibronectin: approximately 10–20% in all conditions) were equal in all conditions. Overall, the results suggest that the scaffold sheets promote axon outgrowth that can be guided across the scaffold, thereby promoting hindlimb recovery. This study provides a hydrogel scaffold construct that can be used in vitro for cell characterization or in vivo for future neuroprosthetics, devices, or cell and ECM delivery.

The spinal cord has poor ability to regenerate after injury, which may be due to cell loss, cyst formation, inflammation, and scarring. A promising approach to treat spinal cord injury (SCI) is the use of biomaterials. We have developed a novel hydrogel scaffold fabricated from oligo(poly(ethylene glycol) fumarate) (OPF) as a 0.08 mm thick sheet containing polymer ridges and a cell-attractive surface chemistry on the other side. When the cells are cultured on OPF with the chemical patterning, the cells attach, align, and deposit ECM along the direction of the pattern. Animals implanted with the rolled scaffold sheets had greater hindlimb recovery compared to the multichannel scaffold control, likely due to the greater number of axons growing across. Inflammation, scarring, and ECM deposits were equal across conditions. Overall, the results suggest that the scaffold sheets promote axon outgrowth that can be guided across the scaffold, thereby promoting hindlimb recovery.