Cicatka Michal, Burget Radim, Karasek Jan, Lancos Jan
Brno University of Technology, Faculty of Electrical Engineering and Communications, Dept. of Telecommunication, Technicka 12, Brno, 61600, Czech Republic.
R&D Automation, Microbiology & Diagnostics, Bruker Daltonics GmbH & Co. KG, Fahrenheitstraße 4, Bremen, 28359, Germany.
Heliyon. 2024 Feb 7;10(3):e25714. doi: 10.1016/j.heliyon.2024.e25714. eCollection 2024 Feb 15.
Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems.
In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions.
The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767.
Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing.
琼脂平板分析对于食品、制药和生物技术等行业的微生物检测至关重要。人工检查速度慢、劳动强度大且容易出错，而现有的自动化系统难以应对现实世界中琼脂平板的复杂性。多样数据集的短缺阻碍了强大自动化系统的开发和评估。
本文提出了两个新的带注释数据集以及一种用于合成琼脂平板生成的新方法。这些数据集包括854张培养琼脂平板的图像和1588张空琼脂平板的图像，涵盖了各种琼脂平板类型和微生物。这些数据集是公开可用的BRUKERCOLONY数据集的扩展，共同构成了最大的公开可用带注释研究数据集之一。该方法基于一个高效的图像生成管道，该管道还模拟了诸如溶血或显色反应等与培养相关的现象。
增强显著提高了训练后的U-Net模型的骰子系数，从0.671提高到0.721。此外，使用真实数据和150%合成数据的组合训练U-Net模型证明了其有效性，产生了显著的骰子系数0.729，比基线0.518有了大幅提高。在U-Net和注意力U-Net架构中，UNet3+表现出最高的性能，实现了0.767的骰子系数。
我们的实验表明该方法适用于现实世界的场景，即使是对于高度可变的琼脂平板。我们的论文通过提出一个新的数据集和有效的方法，为琼脂平板分析的自动化做出了贡献，有可能增强全自动微生物检测。
