Liu Hui, Wang Guangjie, Song Sifan, Huang Daiyun, Zhang Lin
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China.
Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China.
Front Genet. 2022 May 18;13:895099. doi: 10.3389/fgene.2022.895099. eCollection 2022.
Precise segmentation of chromosome in the real image achieved by a microscope is significant for karyotype analysis. The segmentation of image is usually achieved by a pixel-level classification task, which considers different instances as different classes. Many instance segmentation methods predict the Intersection over Union (IoU) through the head branch to correct the classification confidence. Their effectiveness is based on the correlation between branch tasks. However, none of these methods consider the correlation between input and output in branch tasks. Herein, we propose a chromosome instance segmentation network based on regression correction. First, we adopt two head branches to predict two confidences that are more related to localization accuracy and segmentation accuracy to correct the classification confidence, which reduce the omission of predicted boxes in NMS. Furthermore, a NMS algorithm is further designed to screen the target segmentation mask with the IoU of the overlapping instance, which reduces the omission of predicted masks in NMS. Moreover, given the fact that the original IoU loss function is not sensitive to the wrong segmentation, -IoU loss function is defined to strengthen the penalty of the wrong segmentation, which rationalizes the loss of mis-segmentation and effectively prevents wrong segmentation. Finally, an ablation experiment is designed to evaluate the effectiveness of the chromosome instance segmentation network based on regression correction, which shows that our proposed method can effectively enhance the performance in automatic chromosome segmentation tasks and provide a guarantee for end-to-end karyotype analysis.
通过显微镜在真实图像中对染色体进行精确分割对于核型分析具有重要意义。图像分割通常通过像素级分类任务来实现，该任务将不同实例视为不同类别。许多实例分割方法通过头部分支预测交并比（IoU）来校正分类置信度。它们的有效性基于分支任务之间的相关性。然而，这些方法都没有考虑分支任务中输入与输出之间的相关性。在此，我们提出一种基于回归校正的染色体实例分割网络。首先，我们采用两个头部分支来预测与定位精度和分割精度更相关的两个置信度，以校正分类置信度，这减少了非极大值抑制（NMS）中预测框的遗漏。此外，进一步设计了一种NMS算法，以重叠实例的IoU来筛选目标分割掩码，这减少了NMS中预测掩码的遗漏。而且，鉴于原始IoU损失函数对错误分割不敏感，定义了-IoU损失函数以加强对错误分割的惩罚，这使错误分割的损失合理化并有效防止错误分割。最后，设计了消融实验来评估基于回归校正的染色体实例分割网络的有效性，结果表明我们提出的方法能够有效提高自动染色体分割任务的性能，并为端到端核型分析提供保障。
