IEEE/ACM Trans Comput Biol Bioinform. 2022 May-Jun;19(3):1285-1293. doi: 10.1109/TCBB.2020.3003445. Epub 2022 Jun 3.
In medicine, karyotyping chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosome karyotyping is usually done by skilled cytologists manually, which requires experience, domain expertise, and considerable manual efforts. Therefore, automating the karyotyping process is a significant and meaningful task.
This paper focuses on chromosome classification because it is critical for chromosome karyotyping. In recent years, deep learning-based methods are the most promising methods for solving the tasks of chromosome classification. Although the deep learning-based Inception architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge, it has not been used in chromosome classification tasks so far. Therefore, we develop an automatic chromosome classification approach named CIR-Net based on Inception-ResNet which is an optimized version of Inception. However, the classification performance of origin Inception-ResNet on the insufficient chromosome dataset still has a lot of capacity for improvement. Further, we propose a simple but effective augmentation method called CDA for improving the performance of CIR-Net.
The experimental results show that our proposed method achieves 95.98 percent classification accuracy on the clinical G-band chromosome dataset whose training dataset is insufficient. Moreover, the proposed augmentation method CDA improves more than 8.5 percent (from 87.46 to 95.98 percent) classification accuracy comparing to other methods. In this paper, the experimental results demonstrate that our proposed method is recent the most effective solution for solving clinical chromosome classification problems in chromosome auto-karyotyping on the condition of the insufficient training dataset. Code and Dataset are available at https://github.com/CloudDataLab/CIR-Net.
在医学领域，对染色体进行核型分析对于医学诊断、药物开发和生物医学研究非常重要。不幸的是，染色体核型分析通常由熟练的细胞学家手动完成，这需要经验、领域专业知识和大量的手动工作。因此，自动化核型分析过程是一项重要且有意义的任务。
本文专注于染色体分类，因为它是染色体核型分析的关键。近年来，基于深度学习的方法是解决染色体分类任务的最有前途的方法。尽管基于深度学习的 Inception 架构在 2015 年的 ILSVRC 挑战赛中取得了最先进的性能，但迄今为止它尚未在染色体分类任务中使用。因此，我们开发了一种名为 CIR-Net 的基于 Inception-ResNet 的自动染色体分类方法，Inception-ResNet 是 Inception 的优化版本。然而，原始 Inception-ResNet 在不足的染色体数据集上的分类性能仍有很大的改进空间。此外，我们提出了一种简单而有效的增强方法 CDA，用于提高 CIR-Net 的性能。
实验结果表明，我们提出的方法在临床 G 带染色体数据集上实现了 95.98%的分类准确率，而该数据集的训练数据集不足。此外，与其他方法相比，所提出的增强方法 CDA 提高了超过 8.5%（从 87.46%提高到 95.98%）的分类准确率。本文的实验结果表明，在训练数据集不足的情况下，我们提出的方法是解决染色体自动核型分析中临床染色体分类问题的最新、最有效的解决方案。代码和数据集可在 https://github.com/CloudDataLab/CIR-Net 上获得。
