Accurate detection and instance segmentation of unstained living adherent cells in differential interference contrast images

Abstract

Detecting and segmenting unstained living adherent cells in differential interference contrast (DIC) images is crucial in biomedical research, such as cell microinjection, cell tracking, cell activity characterization, and revealing cell phenotypic transition dynamics. We present a robust approach, starting with dataset transformation. We curated 520 pairs of DIC images, containing 12,198 HepG2 cells, with ground truth annotations. The original dataset was randomly split into training, validation, and test sets. Rotations were applied to images in the training set, creating an interim “$\alpha$ set.” Similar transformations formed “$\beta$” and “$\gamma$ sets” for validation and test data. The $\alpha$ set trained a Mask R-CNN, while the $\beta$ set produced predictions, subsequently filtered and categorized. A residual network (ResNet) classifier determined mask retention. The $\gamma$ set underwent iterative processing, yielding final segmentation. Our method achieved a weighted average of 0.567 in ${\text{average precision (AP)}}_{\text{0.75}}^{\text{bbox}}$ and 0.673 in ${\text{AP}}_{\text{0.75}}^{\text{segm}}$, both outperforming major algorithms for cell detection and segmentation. Visualization also revealed that our method excels in practicality, accurately capturing nearly every cell, a marked improvement over alternatives.