An Instance Segmentation Dataset of Yeast Cells in Microstructures

TL;DR

This work addresses the challenge of obtaining pixel-level, instance-aware segmentation of yeast cells in microstructured environments by introducing a dedicated dataset of 493 densely annotated brightfield images that label both cells and trap structures. It provides two trap geometries (regular and L-shaped) and a standardized evaluation protocol to enable fair comparisons of novel segmentation methods, along with public code for metrics. The dataset captures variability across traps, debris, focus, and budding scenarios, and includes careful train/validation/test splits to support robust benchmarking. Overall, the dataset and evaluation framework aim to accelerate development of accurate cell segmentation and tracking in microfluidic contexts, with potential extensions to temporal and video segmentation in future work.

Abstract

Extracting single-cell information from microscopy data requires accurate instance-wise segmentations. Obtaining pixel-wise segmentations from microscopy imagery remains a challenging task, especially with the added complexity of microstructured environments. This paper presents a novel dataset for segmenting yeast cells in microstructures. We offer pixel-wise instance segmentation labels for both cells and trap microstructures. In total, we release 493 densely annotated microscopy images. To facilitate a unified comparison between novel segmentation algorithms, we propose a standardized evaluation strategy for our dataset. The aim of the dataset and evaluation strategy is to facilitate the development of new cell segmentation approaches. The dataset is publicly available at https://christophreich1996.github.io/yeast_in_microstructures_dataset/ .

Figures (6)

• Figure 1: Samples of our yest cells in microstructures dataset. The top row show unlabelled brightfield imagery to demonstrate the visual similarity between the cells and similarly sized microsctuctures. In the following rows, the instance segmentation labels are overlayed onto the the brightfield microscopy imagery (grayscale). A bounding box and object class label denotes each object for clarity. Shades of pink ( $\blacksquare\!\!\!\!\blacksquare$) indicate individual cell instances and shades of (dark) gray ( $\blacksquare\!\!\!\!\blacksquare$) indicate microstructures (traps).
• Figure 2: TLFM experiment setup for single-cell fluorescence measurement. A microfluidic chip sits atop the microscope table (top left). The trap chamber (pink $\blacksquare\!\!\!\!\blacksquare$ on the top right) contains approximately one thousand traps. We extract cropped specimen images from the fluorescence and brightfield channels (bottom left), that include a pair of trap microstructures and cells. The brightfield channel is used for segmentation (and in this dataset). The black scale bar is $1mm$, the white scale bar is $10µm$.
• Figure 3: Brightfield microscopy imagery of yeast cells and microstructures with the corresponding labels. Brightfield images on the left, instance segmentation label in the middle, and an overlay of the brightfield images and labels on the right. Shades of gray ( $\blacksquare\!\!\!\!\blacksquare$) indicate different instances of microstructures (trap). Cell instances are visualized in shades of pink ( $\blacksquare\!\!\!\!\blacksquare$). The background is white.
• Figure 4: Histogram showing the frequency of number of object instances in an image of our dataset. Left column visualizes the cell class (pink $\blacksquare\!\!\!\!\blacksquare$) and right column the trap class (grey $\blacksquare\!\!\!\!\blacksquare$).
• Figure 5: Histogram of object instance sizes in number of pixels. Left column visualizes the class cell (pink $\blacksquare\!\!\!\!\blacksquare$) and right column the class trap (grey $\blacksquare\!\!\!\!\blacksquare$).