The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preserving fusion method, called shape-aware topology-preserving means (SATM), for merging complex simply connected shapes. The method is based on key point matching and piecewise contour averaging. Unlike existing pixelwise and contourwise fusion methods, SATM preserves topology and does not smooth morphological features. We also present a detailed comparison of SATM with state-of-the-art fusion techniques for the purpose of benchmarking and median shape construction. Our experiments show that SATM outperforms these techniques in terms of shape-related measures that reflect shape complexity, manifesting itself as a reliable method for both establishing a consensus of segmentation annotations and for computing mean shapes.

• Keywords
• Average shape, Mean shape, Median shape, Segmentation mask fusion, Shape analysis,
• Publication type
• Journal Article MeSH

OBJECTIVES: This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions. METHODS: We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes. RESULTS: The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann-Whitney U test, P < .0001). CONCLUSION: We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated.

• Keywords
• Cell detection, U-net++, cell segmentation, chronic lymphocytic leukaemia cells, image analysis,
• Publication type
• Journal Article MeSH