A multi-spectral myelin annotation tool for machine learning based myelin quantification

Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify myelin by co-localization of oligodendrocyte and axonal membranes that fit certain shape and size criteria. Because myelin wriggles along x-y-z axes, machine learning is ideal for its segmentation. However, machine-learning methods, especially convolutional neural networks (CNNs), require a high number of annotated images, which necessitate expert labor. To facilitate myelin annotation, we developed a workflow and software for myelin ground truth extraction from multi-spectral fluorescent images. Additionally, to the best of our knowledge, for the first time, a set of annotated myelin ground truths for machine learning applications were shared with the community.

Two phases of macrophages: Inducing maturation and death of oligodendrocytes in vitro co-culture

BACKGROUND

The plasticity of macrophages in the immune response is a dynamic situation dependent on external stimuli. The activation of macrophages both has beneficial and detrimental effects on mature oligodendrocytes (OLs) and myelin. The activation towards inflammatory macrophages has a critical role in the immune-mediated oligodendrocytes death in multiple sclerosis (MS) lesions.

NEW METHOD

We established an in vitro co-culture method to study the function of macrophages in the survival and maturation of OLs.

RESULTS

We revealed that M1 macrophages decreased the number of mature OLs and phagocytosed the myelin. Interestingly, non-activated as well as M2 macrophages contributed to an increase in the number of mature OLs in our in vitro co-culture platform.

COMPARISON WITH EXISTING METHODS

We added an antibody against an OL surface antigen in our in vitro co-cultures. The antibody presents the OLs to the macrophages enabling the investigation of direct interactions between macrophages and OLs.

CONCLUSION

Our co-culture system is a feasible method for the investigation of the direct cell-to-cell interactions between OLs and macrophages. We utilized it to show that M2 and non-activated macrophages may be employed to enhance remyelination.

Myelin detection in fluorescence microscopy images using machine learning

BACKGROUND

The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens.

NEW METHOD

In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total.

RESULTS

Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84±0.09% and 98.46±0.11% were achieved by Boosted Trees and customized-CNN, respectively.

COMPARISON WITH EXISTING METHODS

Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images.

CONCLUSIONS

Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening.

Motoneuron expression profiling identifies an association between an axonal splice variant of HDGF-related protein 3 and peripheral myelination

Disorders that disrupt myelin formation during development or in adulthood, such as multiple sclerosis and peripheral neuropathies, lead to severe pathologies, illustrating myelin's crucial role in normal neural functioning. However, although our understanding of glial biology is increasing, the signals that emanate from axons and regulate myelination remain largely unknown. To identify the core components of the myelination process, here we adopted a microarray analysis approach combined with laser-capture microdissection of spinal motoneurons during the myelinogenic phase of development. We identified neuronal genes whose expression was enriched during myelination and further investigated hepatoma-derived growth factor-related protein 3 (HRP3 or HDGFRP3). HRP3 was strongly expressed in the white matter fiber tracts of the peripheral (PNS) and central (CNS) nervous systems during myelination and remyelination in a cuprizone-induced demyelination model. The dynamic localization of HPR3 between axons and nuclei during myelination was consistent with its axonal localization during neuritogenesis. To study this phenomenon, we identified two splice variants encoded by the HRP3 gene: the canonical isoform HRP3-I and a newly recognized isoform, HRP3-II. HRP3-I remained solely in the nucleus, whereas HRP3-II displayed distinct axonal localization both before and during myelination. Interestingly, HRP3-II remained in the nuclei of unmyelinated neurons and glial cells, suggesting the existence of a molecular machinery that transfers it to and retains it in the axons of neurons fated for myelination. Overexpression of HRP3-II, but not of HRP3-I, increased Schwann cell numbers and myelination in PNS neuron-glia co-cultures. However, HRP3-II overexpression in CNS co-cultures did not alter myelination.