Search

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.

Introduction: Infra-red (IR) and visible light (VL) based systems developed for transmission of information about physical quantities (e.g. humidity, temperature) out from closed areas, cannot be effectively employed in case of specific conditions in a targeted environment (because of fog or vapor for example). Objectives: In this work, we introduce a concept of wireless short-range transmitter and receiver to sense physical quantities, for instance temperature, with slow variation. The proposed concept is able to transmit analog-based information from isolated environments (e.g. aquariums or environments for plant growing) with high immunity against vapor and fog that limits standard optical (laser, IR band) methods of communication. Methods: In this work, a new concept of short range radiofrequency (RF) communication device consisting of transmitting and receiving parts build from active devices fabricated in 0.35 μm I3T25 3.3 V CMOS process and ferrite antennas is selected. RF part uses medium-wave propagation within 10 mm distance at frequency 700 kHz. Such an approach offers minimal path loss of the radiated energy of a signal and low-gain amplification required for restoration of similar levels as available at the transmitting side. Results: The processing of base-band signals of simple (sine wave) and complex (electrocardiogram) character was verified experimentally through the system. Application example of temperature monitoring in a closed environment, based on a temperature sensor (thermistor), verifies operationability in temperature range from 10 °C up to 50 °C. Conclusion: Compared to state-of-the-art solution, the presented concept has several advantages, for instance: less complexity; using of simpler type of modulation and demodulation; lower power consumption and significantly reduced issues caused by an environment with special transmission conditions (e.g. fog and vapor). The obtained results are in good agreement with expectations. Among others, the presented system brings beneficial performances for similar applications targeting on monitoring of low-frequency or slowly varying signals.

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.

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.

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 necessitates expert labor. To facilitate myelin annotation, we developed a workflow and a software for myelin ground truth extraction from multi-spectral fluorescent images. Additionally, we shared a set of myelin ground truths annotated using this workflow.