Abstract Quantification of colony forming units (CFU) on microbial cultures prepared according to the standard spread plate technique is a daily laboratory routine that requires significant resources. On the other hand, SP-SDS (Single Plate Serial Dilution Spotting) is a widely used technique that allows a great reduction in the use of material resources and time. However, previous approaches for automatic quantification are based on images of standard spread plate Petri dishes with low variation of CFU features and captured under controlled lighting conditions. In this paper, we propose a novel approach that automatically separates each dilution in images of Petri dishes prepared in the SP-SDS technique and counts total CFU per dilution, which most approaches are unable to perform. The proposed approach employs region-based shape descriptors for quantification of isolated CFU and cross-correlation granulometry for the quantification of CFU in agglomerates. For the experiments, we composed two image datasets and used images from two publicly available datasets. The images from our datasets were acquired under real laboratory ambient conditions and show variation in lighting, background noise, low contrast between bacterial colonies and background, and high variation in CFU features. Overall, the results obtained by our approach in terms of accuracy, precision, and sensitivity were superior to those of two other approaches recently proposed in the literature used for comparison in this study, especially for high-definition images. In addition, our results present greater or similar accuracy to various approaches found in the literature, most of which are not able to count CFU in images obtained from Petri dishes prepared in the SP-SDS technique and low control of ambient conditions. Our composed datasets are publicly available for download as a contribution to further research.

中文翻译：

---

单板连续稀释中CFU计数的自动分割方法

摘要 根据标准扩散板技术制备的微生物培养物上的菌落形成单位 (CFU) 的定量是实验室日常工作，需要大量资源。另一方面，SP-SDS（单板连续稀释点样）是一种广泛使用的技术，可以大大减少材料资源和时间的使用。然而，以前的自动量化方法是基于标准扩散板培养皿的图像，其 CFU 特征变化很小，并在受控照明条件下捕获。在本文中，我们提出了一种新方法，可以自动分离用 SP-SDS 技术制备的培养皿图像中的每个稀释度，并计算每个稀释度的总 CFU，这是大多数方法无法执行的。所提出的方法采用基于区域的形状描述符来量化孤立的 CFU，并使用互相关粒度来量化聚集体中的 CFU。对于实验，我们组成了两个图像数据集并使用了来自两个公开可用数据集的图像。我们数据集中的图像是在真实的实验室环境条件下获得的，显示了光照、背景噪声、细菌菌落和背景之间的低对比度以及 CFU 特征的高度变化。总体而言，我们的方法在准确性、精度和灵敏度方面获得的结果优于最近在本研究中用于比较的文献中提出的其他两种方法，特别是对于高清图像。此外，我们的结果与文献中发现的各种方法相比具有更高或相似的准确性，其中大多数无法计算从 SP-SDS 技术制备的培养皿中获得的图像中的 CFU，并且对环境条件的控制较低。我们的组合数据集可公开下载，作为对进一步研究的贡献。