Objective: To propose a method for mitigate the impact of anomaly points (such as dust, bubbles, scratches on the chip surface, and minor indentations) in images on the results of digital droplet PCR (ddPCR) detection to achieve high-throughput, stable, and accurate detection.
Methods: We propose a Filter Faster R-CNN ddPCR detection model, which employs Faster R-CNN to generate droplet prediction boxes followed by removing the anomalies within the positive droplet prediction boxes using an outlier filtering module (Filter). Using a plasmid carrying a norovirus fragment as the template, we established a ddPCR dataset for model training (2462 instances, 78.56%) and testing (672 instances, 21.44%). Ablation experiments were performed to test the effectiveness of 3 filtering branches of the Filter for anomaly removal on the validation dataset. Comparative experiments with other ddPCR droplet detection models and absolute quantification experiments of ddPCR were conducted to assess the performance of the Filter Faster R-CNN model.
Results: In low-dust and dusty environments, the Filter Faster R-CNN model achieved detection accuracies of 98.23% and 88.35% for positive droplets, respectively, with composite F1 scores reaching 99.15% and 99.14%, obviously superior to the other models. The introduction of the filtering module significantly enhanced the positive accuracy of the model in dusty environments. In the absolute quantification experiments, a regression line was plotted using the results from commercial flow cytometry equipment as the standard concentration. The results show a regression line slope of 1.0005, an intercept of -0.025, and a determination coefficient of 0.9997, indicating high consistency between the two results.
Conclusion: The ddPCR detection technique using the Filter Faster R-CNN model provides a robust detection method for ddPCR under various environmental conditions.
目的: 研究液滴数字聚合酶链式反应（ddPCR）液滴检测技术，去除图像中灰尘、气泡、芯片表面的划痕以及微小凹陷等因素产生的异常点对结果的影响，实现高通量、稳定和准确的ddPCR液滴的自动检测。
方法: 提出Filter Faster R-CNN ddPCR液滴检测模型。使用Faster R-CNN生成液滴预测框，之后使用异常点过滤模块（Filter）去除阳性液滴预测框中的异常点。以诺如病毒片段的质粒为模板进行ddPCR实验，建立一个ddPCR数据集，用于模型的训练（2462例，约占78.56%）和测试（672例，约占21.44%）。对异常点过滤模块的3个过滤支路在验证集上进行消融实验，通过与其他ddPCR液滴检测模型进行比较的对比实验以及进行ddPCR的绝对定量实验。
结果: 在少尘和多尘的环境中，Filter Faster R-CNN阳性液滴准确率为98.23%和88.35%，综合指标F1分数分别达到了99.15%和99.14%，高于其他相比较的模型。独立样本T检验的结果证明，相比未添加过滤模块的网络，添加过滤模块后能够显著提示模型在多尘环境中的阳性准确率。在ddPCR绝对定量实验中，将商业化流式检测设备的结果作为标准浓度，绘制了回归线。结果显示，回归线斜率为1.0005，截距为-0.025，决定系数达到了0.9997，二者结果高度一致。
结论: 本文提出了一种基于Filter Faster R-CNN的ddPCR液滴检测技术，为在多种环境条件下的ddPCR实验提供了鲁棒的液滴检测方法。
Keywords: Filter Faster R-CNN; anomaly points removal; digital droplet ddPCR.