Background: In medicine, chromosome karyotyping analysis plays a crucial role in prenatal diagnosis for diagnosing whether a fetus has severe defects or genetic diseases. However, chromosome instance segmentation is the most critical obstacle to automatic chromosome karyotyping analysis due to the complicated morphological characteristics of chromosome clusters, restricting chromosome karyotyping analysis to highly depend on skilled clinical analysts. Method: In this paper, we build a clinical dataset and propose multiple segmentation baselines to tackle the chromosome instance segmentation problem of various overlapping and touching chromosome clusters. First, we construct a clinical dataset for deep learning-based chromosome instance segmentation models by collecting and annotating 1,655 privacy-removal chromosome clusters. After that, we design a chromosome instance labeled dataset augmentation (CILA) algorithm for the clinical dataset to improve the generalization performance of deep learning-based models. Last, we propose a chromosome instance segmentation framework and implement multiple baselines for the proposed framework based on various instance segmentation models. Results and Conclusions:Experiments evaluated on the clinical dataset show that the best baseline of the proposed framework based on the Mask-RCNN model yields an outstanding result with 77%77\% mAPmAP, 97.5%97.5\% AP50AP^{50}, and 95.5% AP7595.5\%\ AP^{75} segmentation precision, and 95.38%95.38\% accuracy, which exceeds results reported in current chromosome instance segmentation methods. The quantitative evaluation results demonstrate the effectiveness and advancement of the proposed method for the chromosome instance segmentation problem. The experimental code and privacy-removal clinical dataset can be found at Github.

中文翻译：

---

染色体实例分割的临床数据集和各种基线


背景：在医学上，染色体核型分析在产前诊断中对于诊断胎儿是否存在严重缺陷或遗传性疾病起着至关重要的作用。然而，由于染色体簇复杂的形态特征，染色体实例分割是自动染色体核型分析的最关键障碍，限制了染色体核型分析高度依赖熟练的临床分析人员。方法：在本文中，我们构建了一个临床数据集，并提出了多个分割基线来解决各种重叠和接触染色体簇的染色体实例分割问题。首先，我们通过收集和注释 1,655 个隐私删除染色体簇，为基于深度学习的染色体实例分割模型构建临床数据集。之后，我们为临床数据集设计了染色体实例标记数据集增强（CILA）算法，以提高基于深度学习的模型的泛化性能。最后，我们提出了一个染色体实例分割框架，并基于各种实例分割模型为所提出的框架实现了多个基线。结果和结论：在临床数据集上评估的实验表明，基于 Mask-RCNN 模型的建议框架的最佳基线产生了出色的结果，分别为 77%77\% mAPmAP、97.5%97.5\% AP50AP^{50} 和95.5% AP7595.5\%\ AP^{75} 分割精度和 95.38%95.38\% 准确率，超过了当前染色体实例分割方法报告的结果。定量评估结果证明了该方法针对染色体实例分割问题的有效性和先进性。 实验代码和隐私删除临床数据集可以在 Github 上找到。