Cellcounter: a deep learning framework for high-fidelity spatial localization of neurons
This addresses the challenge of neuron localization for neuroscientists by reducing annotation effort, though it appears incremental as it builds on existing deep learning approaches.
The authors tackled the problem of robust and accurate neuron localization in neuroscience by developing Cellcounter, a deep learning framework that reduces the need for complete manual annotation. It achieved improved accuracy over state-of-the-art methods and significantly reduced false-positive detection in several protocols.
Many neuroscientific applications require robust and accurate localization of neurons. It is still an unsolved problem because of the enormous variation in intensity, texture, spatial overlap, morphology and background artifacts. In addition, curation of a large dataset containing complete manual annotation of neurons from high-resolution images to train a classifier requires significant time and effort. We present Cellcounter, a deep learning-based model trained on images containing incompletely-annotated neurons with highly-varied morphology and control images containing artifacts and background structures. Leveraging the striking self-learning ability, Cellcounter gradually labels neurons, obviating the need for time-intensive complete annotation. Cellcounter shows its efficacy over the state of the arts in the accurate localization of neurons while significantly reducing false-positive detection in several protocols.