Vašinková Markéta, Doleží Vít, Vašinek Michal, Gajdoš Petr, Kriegová Eva
Department of Computer Science, FEECS, VSB - Technical University of Ostrava, Ostrava, Czech Republic.
Department of Immunology, Faculty of Medicine and Dentistry, Palacky University & University Hospital, Olomouc, Czech Republic.
Bioinform Biol Insights. 2024 Sep 5;18:11779322241272387. doi: 10.1177/11779322241272387. eCollection 2024.
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.
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.
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 test, < .0001).
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.
本文聚焦于低对比度明场显微镜图像中的细胞检测；在我们的案例中，指的是慢性淋巴细胞白血病细胞。从明场延时显微镜图像中自动检测细胞为细胞形态学和迁移研究带来了新机遇；为取得理想结果，宜采用最先进的图像分割方法，该方法不仅能检测细胞，还能尽可能精确地检测其边界，从而确定其形状和尺寸。
我们比较了八种具有不同骨干编码器的最先进神经网络架构用于图像数据分割，即U-net、U-net++、金字塔注意力网络、多注意力网络、LinkNet、特征金字塔网络、DeepLabV3和DeepLabV3+。训练过程包括使用PyTorch和PyTorch Lightning库对这些网络分别进行1000个轮次的训练。对于实例分割，使用了分水岭算法和三类图像语义分割。我们还使用了StarDist，这是一个基于深度学习的用于检测星凸形状物体的工具。
语义分割的最佳组合是具有ResNeSt - 269背景的U-net++架构，其数据集交并比分数为0.8902。对于所检测的细胞特征（面积、圆形度、紧实度、周长、半径和形状指数），使用不同慢性淋巴细胞白血病细胞分割方法的平均值差异在统计学上似乎具有显著性（曼 - 惠特尼检验，<0.0001）。
我们发现总体而言，这些算法与真实情况的一致性相当，但通过比较可以看出，不同方法偏好细胞的不同形态特征。因此，选择最适合基于实例的细胞分割方法取决于具体应用，即所研究的特定细胞特征。
