Significance: Label-free quantitative phase imaging is a promising technique for the automatic detection of abnormal red blood cells (RBCs) in real time. Although deep-learning techniques can accurately detect abnormal RBCs from quantitative phase images efficiently, their applications in diagnostic testing are limited by the lack of transparency. More interpretable results such as morphological and biochemical characteristics of individual RBCs are highly desirable. Aim: An end-to-end deep-learning model was developed to efficiently discriminate thalassemic RBCs (tRBCs) from healthy RBCs (hRBCs) in quantitative phase images and segment RBCs for single-cell characterization. Approach: Two-dimensional quantitative phase images of hRBCs and tRBCs were acquired using digital holographic microscopy. A mask region-based convolutional neural network (Mask R-CNN) model was trained to discriminate tRBCs and segment individual RBCs. Characterization of tRBCs was achieved utilizing SHapley Additive exPlanation analysis and canonical correlation analysis on automatically segmented RBC phase images. Results: The implemented model achieved 97.8% accuracy in detecting tRBCs. Phase-shift statistics showed the highest influence on the correct classification of tRBCs. Associations between the phase-shift features and three-dimensional morphological features were revealed. Conclusions: The implemented Mask R-CNN model accurately identified tRBCs and segmented RBCs to provide single-RBC characterization, which has the potential to aid clinical decision-making.

中文翻译：

---

使用基于掩模区域的卷积神经网络自动检测和表征地中海贫血红细胞的定量相位图像


意义：无标记定量相位成像是一种很有前途的实时自动检测异常红细胞（RBC）的技术。尽管深度学习技术可以从定量相位图像中准确有效地检测异常红细胞，但其在诊断测试中的应用由于缺乏透明度而受到限制。非常需要更可解释的结果，例如单个红细胞的形态和生化特征。目的：开发了一种端到端深度学习模型，以在定量相位图像中有效地区分地中海贫血红细胞 (tRBC) 与健康红细胞 (hRBC)，并分割红细胞以进行单细胞表征。方法：使用数字全息显微镜获取 hRBC 和 tRBC 的二维定量相位图像。训练基于掩模区域的卷积神经网络 (Mask R-CNN) 模型来区分 tRBC 并分割单个 RBC。利用 SHapley 附加解释分析和对自动分割的红细胞相位图像的典型相关分析来实现 tRBC 的表征。结果：实施的模型在检测 tRBC 方面实现了 97.8% 的准确度。相移统计显示对 tRBC 正确分类的影响最大。揭示了相移特征和三维形态特征之间的关联。结论：所实施的 Mask R-CNN 模型可以准确识别 tRBC 和分段 RBC，以提供单 RBC 表征，这有可能帮助临床决策。