[A digital droplet PCR detection technique based on filter faster R-CNN]

Abstract

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.

Keywords: Filter Faster R-CNN; anomaly points removal; digital droplet ddPCR.

图 1

ddPCR图像预处理 ddPCR image preprocessing (Scale bar=300 μm). A: Original ddPCR image. B: Local portion of the ddPCR image. C: Pre-annotation using Hough Circle Transform, with yellow arrows indicating missed and mislabeled areas. D: Manual label correction and addition of anomaly point labels. E: Image with Gaussian blur.

图 2

Filter Faster R-CNN模型框架，其中橙色虚线为Faster R-CNN部分，蓝色虚线为异常点过滤模块 Filter Faster R-CNN model framework, in which the orange dotted line is the Faster R-CNN and the blue dotted line is the Filter module.

图 3

常见异常斑点 Representative anomalous spots (Scale bar=300 μm). A: Fuzziness or scratches. B: Bubbles within droplets. C: Dust particles between droplets. D: Dust outside the grooves.

图 4

Loss函数收敛性能分析 Convergence performance analysis of Loss function.

图 5

少尘环境中ddPCR图像测试结果 Test results of ddPCR images in a low-dust environment, where red boxes represent positive droplets, blue boxes represent negative droplets, and yellow boxes represent anomaly points (A and B are both representative cases).

图 6

多尘环境中ddPCR图像测试结果 Test results of ddPCR images in a dusty environment, where red boxes represent positive droplets, blue boxes represent negative droplets, and yellow boxes represent anomaly points. A and B are both representative cases.

图 7

SSD与Faster R-CNN添加Filter模块前后预测结果比较 Comparison of prediction results before and after adding the Filter module for SSD and Faster R-CNN.