Time-lapse light microscopy combined with in vitro neuronal cultures has provided a significant contribution to the field of Developmental Neuroscience. The establishment of the neuronal polarity, i.e., formation of axons and dendrites, key structures responsible for inter-neuronal signaling, was described in 1988 by Dotti, Sullivan and Banker in a milestone paper that continues to be cited 30 years later. In the following decades, numerous fluorescently labeled tags and dyes were developed for live cell imaging, providing tremendous advancements in terms of resolution, acquisition speed and the ability to track specific cell structures. However, long-term recordings with fluorescence-based approaches remain challenging because of light-induced phototoxicity and/or interference of tags with cell physiology (e.g., perturbed cytoskeletal dynamics) resulting in compromised cell viability leading to cell death. Therefore, a label-free approach remains the most desirable method in long-term imaging of living neurons. In this paper we will focus on label-free high-resolution methods that can be successfully used over a prolonged period. We propose novel tools such as scanning ion conductance microscopy (SICM) or digital holography microscopy (DHM) that could provide new insights into live cell dynamics during neuronal development and regeneration after injury.

Scanning Ion Conductance Microscopy (SICM) provides high‐resolution, nanoscale imaging of living cells, but it is generally limited by a slow scan rate, making it challenging to capture dynamic processes in real time. To tackle this challenge, an integrated data acquisition and computational framework is proposed that improves the temporal resolution of SICM by selectively skipping certain scan lines. A partial convolutional neural network (Partial‐CNN) model is developed and trained on SICM images and their corresponding masks to reconstruct the complete images from the undersampled data, ensuring the retention of structural integrity. This approach significantly reduces the image acquisition time (i.e., by 30–63%) without compromising quality, as validated through multiple quantitative metrics. Compared to conventional deep learning methods, the Partial‐CNN demonstrates higher accuracy in reconstructing fine details and maintaining consistent height maps across skipped regions. It is shown that this method provides an increased temporal resolution and retains image fidelity, making it suitable for real‐time dynamic SICM imaging and improving the smart scanning microscopy applications in time‐resolved biological imaging.