Quantitative Analysis of Miniature Synaptic Calcium Transients using Positive Unlabeled Deep Learning

Dataset for Quantitative Analysis of Miniature Synaptic Calcium Transients This dataset provides the testing benchmarks for the deep learning models described in "Quantitative Analysis of Miniature Synaptic Calcium Transients using Positive Unlabeled Deep Learning". It is specifically designed to facilitate the validation of automated detection systems for calcium imaging in synaptic research. Dataset Structure The repository is organized into two primary components to allow for direct comparison between raw data and ground-truth expert labels: raw-input/: Contains raw fluorescence microscopy videos in .tif format. These represent the unprocessed input data used for model inference. manual-expert/: Contains the "gold standard" ground-truth annotations. Each video has a corresponding .csv file detailing the X-coordinate, Y-coordinate, and Slice (Time) position for every synaptic event, as identified by an expert annotator. Usage and Training Data While this Zenodo record contains the full Testing Dataset for model validation, the Training Dataset, due to its significant size, is hosted via our laboratory's dedicated repository. Full Training Set & Code: https://github.com/FLClab/Calcium-Analysis Methodology: For a comprehensive breakdown of the Positive Unlabeled (PU) Deep Learning framework and experimental setup, please refer to the associated manuscript. Technical Specifications File Formats: OME-TIFF (Videos), CSV (Annotations) Domain: Neuroscience, Calcium Imaging, Deep Learning Annotation Method: Manual expert curation Abstract Ca2+ imaging methods are widely used for studying cellular activity in the brain, allowing detailed analysis of dynamic processes across various scales. Enhanced by high-contrast optical microscopy and fluorescent Ca2+ sensors, this technique can be used to reveal localized Ca2+ fluctuations within neurons, including in sub-cellular compartments, such as the dendritic shaft or spines. Despite advances in Ca2+ sensors, the analysis of miniature Synaptic Calcium Transients (mSCTs), characterized by variability in morphology and low signal-to-noise ratios, remains challenging. Traditional threshold-based methods struggle with the detection and segmentation of these small, dynamic events. Deep learning (DL) approaches offer promising solutions but are limited by the need for large annotated datasets. Positive Unlabeled (PU) learning addresses this limitation by leveraging unlabeled instances to increase dataset size and enhance performance. This approach is particularly useful in the case of mSCTs that are scarce and small, associated with a very small proportion of the foreground pixels. PU learning significantly increases the effective size of the training dataset, improving model performance. Here, we present a PU learning-based strategy for detecting and segmenting mSCTs. We evaluate the performance of two 3D deep learning models, StarDist-3D and 3D U-Net, which are well established for the segmentation of small volumetric structures in microscopy datasets. By integrating PU learning, we enhance the 3D U-Net's performance, demonstrating significant gains over traditional methods. This work pioneers the application of PU learning in Ca2+ imaging analysis, offering a robust framework for mSCT detection and segmentation. We also demonstrate how this quantitative analysis pipeline can be used for subsequent mSCTs feature analysis. We characterize morphological and kinetic changes of mSCTs associated with the application of chemical long-term potentiation (cLTP) stimulation in cultured rat hippocampal neurons. Our data-driven approach shows that a cLTP-inducing stimulus leads to the emergence of new active dendritic regions and differently affects mSCTs subtypes.