Automated detection of cervical cancer cells/clumps has the potential to significantly reduce error rate and increase productivity in cervical cancer screening. However, most traditional methods rely on the success of accurate cell segmentation and discriminative hand-crafted features extraction. Recently there are emerging deep learning-based methods which train Convolutional Neural Networks (CNN) to classify cell patches or to detect cells from the whole image. But the former is computationally expensive, while the latter often requires a large-scale dataset with expensive annotations. In this paper we propose an efficient cervical cancer cells/clumps detection method, called Comparison detector, to deal with the limited data problem. Specifically, we utilize the state-of-the-art proposal-based object detection method, Faster R-CNN with Feature Pyramid Network (FPN) as the baseline and replace the classification of each proposal by comparing it with the prototype representation of each category. In addition, we propose to learn the prototype representation of the background category from data instead of manually choosing them by some heuristic rules. Experimental results show that the proposed Comparison detector yields significant improvement on the small dataset, achieving a mean Average Precision (mAP) of 26.3% and an Average Recall (AR) of 35.7%, both improved by about 20% comparing to the baseline. Moreover, when training on the medium-sized dataset, our Comparison detector gains a mAP of 48.8% and an AR of 64.0%, improving the AR by 5.1% and the mAP by 3.6% respectively. Our method is promising for the development of automation-assisted cervical cancer screening systems. Code and datasets are available at  https://github.com/kuku-sichuan/ComparisonDetector.

宫颈癌细胞/团块的自动检测具有显着降低错误率并提高宫颈癌筛查效率的潜力。但是，大多数传统方法都依赖于精确的细胞分割和有区别的手工特征提取的成功。最近，出现了基于深度学习的新兴方法，它们可以训练卷积神经网络（CNN）来对细胞补丁进行分类或从整个图像中检测细胞。但是前者在计算上很昂贵，而后者通常需要带有昂贵注释的大规模数据集。在本文中，我们提出了一种有效的宫颈癌细胞/团块检测方法，称为比较检测器，以处理有限的数据问题。具体来说，我们利用基于建议的最新对象检测方法，以特征金字塔网络（FPN）为基准的更快的R-CNN，并通过将其与每个类别的原型表示进行比较来替换每个提案的分类。另外，我们建议从数据中学习背景类别的原型表示，而不是通过一些启发式规则手动选择它们。实验结果表明，所提出的比较检测器在小型数据集上有显着改进，平均平均准确度（mAP）为26.3％，平均召回率（AR）为35.7％，两者均提高了约 我们建议从数据中学习背景类别的原型表示，而不是通过一些启发式规则手动选择它们。实验结果表明，所提出的比较检测器在小型数据集上有显着改进，平均平均准确度（mAP）为26.3％，平均召回率（AR）为35.7％，两者均提高了约 我们建议从数据中学习背景类别的原型表示，而不是通过一些启发式规则手动选择它们。实验结果表明，所提出的比较检测器在小型数据集上有显着改进，平均平均准确度（mAP）为26.3％，平均召回率（AR）为35.7％，两者均提高了约与基线相比，降低了20％。此外，在中型数据集上进行训练时，我们的“比较”检测器获得了48.8％的mAP和64.0％的AR，分别将AR提升了5.1％和mAP提升了3.6％。我们的方法对于开发自动化辅助宫颈癌筛查系统很有希望。代码和数据集可在 https://github.com/kuku-sichuan/ComparisonDetector获得。