BACKGROUND: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

Brno University of Technology Faculty of Electrical Engineering and Communications Dept of Telecommunication Technicka 12 Brno 61600 Czech Republic

R and D Automation Microbiology and Diagnostics Bruker Daltonics GmbH and Co KG Fahrenheitstraße 4 Bremen 28359 Germany

Zobrazit více v PubMed

Lippi G., Rin G.D. Advantages and limitations of total laboratory automation: a personal overview. Clin. Chem. Lab. Med. 2019;57(6):802–811. doi: 10.1515/cclm-2018-1323. [cited 2023-09-07] PubMed DOI

Alonso C., Domínguez C., Heras J., Mata E., Pascual V., Torres C., Zarazaga M. Antibiogramj: a tool for analysing images from disk diffusion tests. Comput. Methods Programs Biomed. 2017;143:159–169. doi: 10.1016/j.cmpb.2017.03.010. PubMed DOI

Dauwalder O., Michel A., Eymard C., Santos K., Chanel L., Luzzati A., Roy-Azcora P., Sauzon J.F., Guillaumont M., Girardo P., Fuhrmann C., Lina G., Laurent F., Vandenesch F., Sobas C. Use of artificial intelligence for tailored routine urine analyses. Clin. Microbiol. Infect. 2021;27(8):1168.e1–1168.e6. doi: 10.1016/j.cmi.2020.09.056. PubMed DOI

Frost H.R., Tsoi S.K., Baker C.A., Laho D., Sanderson-Smith M.L., Steer A.C., Smeesters P.R. Validation of an automated colony counting system for group a streptococcus. BMC Res. Notes. Feb. 2016;9(1) doi: 10.1186/s13104-016-1875-z. PubMed DOI PMC

Heestermans R., Herroelen P., Emmerechts K., Vandoorslaer K., Geyter D.D., Demuyser T., Wybo I., Piérard D., Muyldermans A. Validation of the colibrí instrument for automated preparation of MALDI-TOF MS targets for yeast identification. J. Clin. Microbiol. Jul. 2022;60(7) doi: 10.1128/jcm.00237-22. PubMed DOI PMC

Chen Z., Yang J., Chen L., Feng Z., Jia L. Efficient railway track region segmentation algorithm based on lightweight neural network and cross-fusion decoder. Autom. Constr. 2023;155 doi: 10.1016/j.autcon.2023.105069. DOI

Feng Z., Yang J., Chen Z., Kang Z. Lrseg: an efficient railway region extraction method based on lightweight encoder and self-correcting decoder. Expert Syst. Appl. 2024;238 doi: 10.1016/j.eswa.2023.122386. DOI

Cheng D., Gao X., Mao Y., Xiao B., You P., Gai J., Zhu M., Kang J., Zhao F., Mao N. Brain tumor feature extraction and edge enhancement algorithm based on u-net network. Heliyon. 2023;9(11) doi: 10.1016/j.heliyon.2023.e22536. PubMed DOI PMC

Soh W.K., Yuen H.Y., Rajapakse J.C. Hut: hybrid unet transformer for brain lesion and tumour segmentation. Heliyon. 2023;9(12) doi: 10.1016/j.heliyon.2023.e22412. PubMed DOI PMC

Ferrari A., Lombardi S., Signoroni A. Bacterial colony counting with convolutional neural networks in digital microbiology imaging. Pattern Recognit. 2017;61:629–640. doi: 10.1016/j.patcog.2016.07.016. https://www.sciencedirect.com/science/article/pii/S0031320316301650 DOI

Geissmann Q. Opencfu, a new free and open-source software to count cell colonies and other circular objects. PLoS ONE. 2013;8 doi: 10.1371/journal.pone.0054072. PubMed DOI PMC

Bradski G. The OpenCV library. Dr. Dobb's J. Softw. Tools. 2000

Khan A.u.M., Torelli A., Wolf I., Gretz N. Autocellseg: robust automatic colony forming unit (cfu)/cell analysis using adaptive image segmentation and easy-to-use post-editing techniques. Sci. Rep. 2018;8(1):7302. doi: 10.1038/s41598-018-24916-9. PubMed DOI PMC

Stirling D.R., Swain-Bowden M.J., Lucas A.M., Carpenter A.E., Cimini B.A., Goodman A. Cellprofiler 4: improvements in speed, utility and usability. BMC Bioinform. 2021;22(1):433. doi: 10.1186/s12859-021-04344-9. PubMed DOI PMC

Nie D., Shank E.A., Jojic V. Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics, BCB '15. Association for Computing Machinery; New York, NY, USA: 2015. A deep framework for bacterial image segmentation and classification; pp. 306–314.https://doi.org/10.1145/2808719.2808751 DOI

Zhu G., Yan B., Xing M., Tian C. Automated counting of bacterial colonies on agar plates based on images captured at near-infrared light. J. Microbiol. Methods. 2018;153:66–73. doi: 10.1016/j.mimet.2018.09.004. https://www.sciencedirect.com/science/article/pii/S0167701218306146 PubMed DOI

Naets T., Huijsmans M., Smyth P., Sorber L., de Lannoy G. A mask R-CNN approach to counting bacterial colony forming units in pharmaceutical development. 2021. https://doi.org/10.48550/ARXIV.2103.05337https://arxiv.org/abs/2103.05337 DOI

Majchrowska S., Pawłowski J., Guła G., Bonus T., Hanas A., Loch A., Pawlak A., Roszkowiak J., Golan T., Drulis-Kawa Z. Agar a microbial colony dataset for deep learning detection. 2021. arXiv:2108.01234

Cicatka M., Burget R., Karasek J. 2022 45th International Conference on Telecommunications and Signal Processing (TSP) 2022. Machine-learning approach to microbial colony localisation; pp. 206–211.https://doi.org/10.1109/TSP55681.2022.9851236 DOI

Xu M., Yoon S., Fuentes A., Park D.S. A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognit. 2023;137 doi: 10.1016/j.patcog.2023.109347. https://www.sciencedirect.com/science/article/pii/S0031320323000481 DOI

Ghiasi G., Cui Y., Srinivas A., Qian R., Lin T., Cubuk E.D., Le Q.V., Zoph B. Simple copy-paste is a strong data augmentation method for instance segmentation. 2020. arXiv:2012.07177 [abs]arXiv:2012.07177https://arxiv.org/abs/2012.07177 CoRR.

Andreini P., Bonechi S., Bianchini M., Mecocci A., Scarselli F. Image generation by gan and style transfer for agar plate image segmentation. Comput. Methods Programs Biomed. 2020;184 doi: 10.1016/j.cmpb.2019.105268. https://www.sciencedirect.com/science/article/pii/S0169260719311216 PubMed DOI

Andreini P., Bonechi S., Bianchini M., Mecocci A., Scarselli F. In: Artificial Neural Networks and Machine Learning – ICANN 2018. Kůrková V., Manolopoulos Y., Hammer B., Iliadis L., Maglogiannis I., editors. Springer International Publishing; Cham: 2018. A deep learning approach to bacterial colony segmentation; pp. 522–533.

Pawłowski J., Majchrowska S., Golan T. Generation of microbial colonies dataset with deep learning style transfer. Sci. Rep. 2022;12(1):5212. doi: 10.1038/s41598-022-09264-z. PubMed DOI PMC

Ronneberger O., Fischer P., Brox T. U-net: convolutional networks for biomedical image segmentation. 2015. https://doi.org/10.48550/ARXIV.1505.04597https://arxiv.org/abs/1505.04597 DOI

Oktay O., Schlemper J., Folgoc L.L., Lee M., Heinrich M., Misawa K., Mori K., McDonagh S., Hammerla N.Y., Kainz B., Glocker B., Rueckert D. Attention u-net: learning where to look for the pancreas. 2018. arXiv:1804.03999

Huang H., Lin L., Tong R., Hu H., Zhang Q., Iwamoto Y., Han X., Chen Y.-W., Wu J. Unet 3+: a full-scale connected unet for medical image segmentation. 2020. arXiv:2004.08790

Hogekamp L., Hogekamp S.H., Stahl M.R. Experimental setup and image processing method for automatic enumeration of bacterial colonies on agar plates. PLoS ONE. 2020;15(6):1–17. doi: 10.1371/journal.pone.0232869. PubMed DOI PMC

Sudre C.H., Li W., Vercauteren T., Ourselin S., Cardoso M.J. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. 2017. arXiv:1707.03237 [abs]arXiv:1707.03237http://arxiv.org/abs/1707.03237 CoRR. PubMed PMC

Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. 2015. arXiv:1409.1556

Deng J., Dong W., Socher R., Li L.-J., Li K., Fei-Fei L. 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009. Imagenet: a large-scale hierarchical image database; pp. 248–255.https://doi.org/10.1109/CVPR.2009.5206848 DOI