In karyotyping, the classification of chromosomes is a tedious, complicated, and time-consuming process. It requires extremely careful analysis of chromosomes by well-trained cytogeneticists. To assist cytogeneticists in karyotyping, we introduce Proxy-ResNeXt-CBAM which is a metric learning based network using proxies with a convolutional block attention module (CBAM) designed for chromosome classification. RexNeXt-50 is used as a backbone network. To apply metric learning, the fully connected linear layer of the backbone network (ResNeXt-50) is removed and is replaced with CBAM. The similarity between embeddings, which are the outputs of the metric learning network, and proxies are measured for network training. Proxy-ResNeXt-CBAM is validated on a public chromosome image dataset, and it achieves an accuracy of 95.86%, a precision of 95.87%, a recall of 95.9%, and an F-1 score of 95.79%. Proxy-ResNeXt-CBAM which is the metric learning network using proxies outperforms the baseline networks. In addition, the results of our embedding analysis demonstrate the effectiveness of using proxies in metric learning for optimizing deep convolutional neural networks. As the embedding analysis results show, Proxy-ResNeXt-CBAM obtains a 94.78% Recall@1 in image retrieval, and the embeddings of each chromosome are well clustered according to their similarity.

中文翻译：

---

在染色体核型试验中使用代理进行染色体分类和检索的深度度量学习网络

在核型分析中，染色体的分类是一个繁琐，复杂且耗时的过程。需要训练有素的细胞遗传学家对染色体进行极为仔细的分析。为了帮助细胞遗传学家进行核型分析，我们引入了Proxy-ResNeXt-CBAM，这是一种基于度量学习的网络，使用代理进行卷积块关注模块（CBAM）的设计，用于染色体分类。RexNeXt-50用作骨干网。要应用度量学习，将删除骨干网络（ResNeXt-50）的完全连接的线性层，并用CBAM代替。作为度量学习网络的输出的嵌入与代理之间的相似性被测量以进行网络训练。Proxy-ResNeXt-CBAM在公共染色体图像数据集上进行了验证，其准确度达到95.86％，准确度达到95.87％，召回率为95.9％，F-1得分为95.79％。Proxy-ResNeXt-CBAM是使用代理的度量学习网络，其性能优于基准网络。此外，我们的嵌入分析结果证明了在度量学习中使用代理来优化深度卷积神经网络的有效性。如嵌入分析结果所示，Proxy-ResNeXt-CBAM在图像检索中获得了94.78％的Recall @ 1，并且每个染色体的嵌入根据它们的相似性很好地聚类了。