Liu Jin, Li Yanxin, Wilkins Ruth, Flegal Farrah, Knoll Joan H M, Rogan Peter K
Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, ON, N6A 5C1, Canada.
Cytognomix Inc., London, ON, N5X 3X5, Canada.
F1000Res. 2017 Aug 9;6:1396. doi: 10.12688/f1000research.12226.1. eCollection 2017.
Accurate digital image analysis of abnormal microscopic structures relies on high quality images and on minimizing the rates of false positive (FP) and negative objects in images. Cytogenetic biodosimetry detects dicentric chromosomes (DCs) that arise from exposure to ionizing radiation, and determines radiation dose received based on DC frequency. Improvements in automated DC recognition increase the accuracy of dose estimates by reclassifying FP DCs as monocentric chromosomes or chromosome fragments. We also present image segmentation methods to rank high quality digital metaphase images and eliminate suboptimal metaphase cells. A set of chromosome morphology segmentation methods selectively filtered out FP DCs arising primarily from sister chromatid separation, chromosome fragmentation, and cellular debris. This reduced FPs by an average of 55% and was highly specific to these abnormal structures (≥97.7%) in three samples. Additional filters selectively removed images with incomplete, highly overlapped, or missing metaphase cells, or with poor overall chromosome morphologies that increased FP rates. Image selection is optimized and FP DCs are minimized by combining multiple feature based segmentation filters and a novel image sorting procedure based on the known distribution of chromosome lengths. Applying the same image segmentation filtering procedures to both calibration and test samples reduced the average dose estimation error from 0.4 Gy to <0.2 Gy, obviating the need to first manually review these images. This reliable and scalable solution enables batch processing for multiple samples of unknown dose, and meets current requirements for triage radiation biodosimetry of high quality metaphase cell preparations.
对异常微观结构进行准确的数字图像分析，依赖于高质量的图像以及尽量降低图像中假阳性（FP）和阴性物体的出现率。细胞遗传学生物剂量测定法可检测因暴露于电离辐射而产生的双着丝粒染色体（DCs），并根据DC频率确定所接受的辐射剂量。自动DC识别技术的改进，通过将FP DCs重新分类为单着丝粒染色体或染色体片段，提高了剂量估计的准确性。我们还提出了图像分割方法，用于对高质量的数字中期图像进行排序，并消除次优的中期细胞。一组染色体形态分割方法选择性地滤除了主要由姐妹染色单体分离、染色体片段化和细胞碎片产生的FP DCs。这在三个样本中平均减少了55%的FP，并且对这些异常结构具有高度特异性（≥97.7%）。额外的过滤器选择性地去除了中期细胞不完整、高度重叠或缺失，或整体染色体形态不佳从而增加FP率的图像。通过结合多个基于特征的分割过滤器和一种基于已知染色体长度分布的新型图像分类程序，优化了图像选择并将FP DCs降至最低。将相同的图像分割过滤程序应用于校准样本和测试样本，将平均剂量估计误差从0.4 Gy降低到<0.2 Gy，从而无需首先手动查看这些图像。这种可靠且可扩展的解决方案能够对多个未知剂量的样本进行批量处理，并满足当前对高质量中期细胞制剂进行分流辐射生物剂量测定的要求。
