Deep learning to detect bacterial colonies for the production of vaccines

Beznik, Thomas; Smyth, Paul; Lannoy, Gaël de; Lee, John A.

doi:10.1016/j.neucom.2021.04.130

Cited by 23 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method can effectively change the image structure by the data augmentation method, which can make the augmented images be regarded as a new training image for the deep neural network, and thus can reduce the original data requirement to less than 10. Compared with other traditional neural networks that require at least hundreds of training datasets [ 20 , 35 , 36 ], our method reduces the data collection cost by more than 90% while maintaining a high accuracy rate.…”

Section: Results and Discussionmentioning

confidence: 99%

A New Few-Shot Learning Method of Bacterial Colony Counting Based on the Edge Computing Device

Zhang

Zhou²,

Cao³

et al. 2022

Biology

View full text Add to dashboard Cite

Bacterial colony counting is a time consuming but important task for many fields, such as food quality testing and pathogen detection, which own the high demand for accurate on-site testing. However, bacterial colonies are often overlapped, adherent with each other, and difficult to precisely process by traditional algorithms. The development of deep learning has brought new possibilities for bacterial colony counting, but deep learning networks usually require a large amount of training data and highly configured test equipment. The culture and annotation time of bacteria are costly, and professional deep learning workstations are too expensive and large to meet portable requirements. To solve these problems, we propose a lightweight improved YOLOv3 network based on the few-shot learning strategy, which is able to accomplish high detection accuracy with only five raw images and be deployed on a low-cost edge device. Compared with the traditional methods, our method improved the average accuracy from 64.3% to 97.4% and decreased the False Negative Rate from 32.1% to 1.5%. Our method could greatly improve the detection accuracy, realize the portability for on-site testing, and significantly save the cost of data collection and annotation over 80%, which brings more potential for bacterial colony counting.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

A New Few-Shot Learning Method of Bacterial Colony Counting Based on the Edge Computing Device

Zhang

Zhou²,

Cao³

et al. 2022

Biology

View full text Add to dashboard Cite

show abstract

“…Currently, machine learning is largely dominated by deep learning [27] and, hence, also molecular biology and medicine applications of machine learning models are in the focus of deep learning methods [73,72]. Those applications range from bioinformatics and computational biology [2,59], post-genomic biology and personalized medicine [50], detection of bacterial colonies for the production of vaccines [11] up to medical imaging [7], to name just a few. The possibility of end-to-end learning of deep networks and the availability of pre-trained models for many application areas and in particular for image processing contribute to the big success of those neural networks also in biology and medicine.…”

Section: Machine Learning In Context Of Medical and Biological Applic...mentioning

confidence: 99%

Tutorial - Machine Learning and Information Theoretic Methods for Molecular Biology and Medicine

Villmann¹,

Almeida²,

Lee³

et al. 2022

ESANN 2022 Proceedings

View full text Add to dashboard Cite

A short introduction to the application of informationtheoretic and machine learning methods to biomolecular and medical data is provided as the motivating material that supports special session dedicated to this topic at ESANN 2022. In particular, we highlight current developments of foundation such as interpretability and model certainty. Further, we emphasize how theoretic models provide a natural framework to deal with heterogeneous and complex data structures as frequently occurring in biomedical research.

show abstract

“…It uses encoder–decoder pathways alleviated with skip-connections [ 2 ] while visually resembling a U-shaped pathway. Many successful applications of the U-Net architecture could be found in cell and nuclei segmentations for digital pathology [ 3 ], tumor and organ segmentations [ 4 , 5 ] as well as colony-forming units (CFUs) and other cell segmentation tasks [ 6 , 7 , 8 ]. This vast diversity of applications has promoted credibility and trustworthiness in the U-Net architecture among researchers.…”

Section: Introductionmentioning

confidence: 99%

Multi-Path U-Net Architecture for Cell and Colony-Forming Unit Image Segmentation

Jumutc

Bliznuks

Lihachev

2022

Sensors

View full text Add to dashboard Cite

U-Net is the most cited and widely-used deep learning model for biomedical image segmentation. In this paper, we propose a new enhanced version of a ubiquitous U-Net architecture, which improves upon the original one in terms of generalization capabilities, while addressing several immanent shortcomings, such as constrained resolution and non-resilient receptive fields of the main pathway. Our novel multi-path architecture introduces a notion of an individual receptive field pathway, which is merged with other pathways at the bottom-most layer by concatenation and subsequent application of Layer Normalization and Spatial Dropout, which can improve generalization performance for small datasets. In general, our experiments show that the proposed multi-path architecture outperforms other state-of-the-art approaches that embark on similar ideas of pyramid structures, skip-connections, and encoder–decoder pathways. A significant improvement of the Dice similarity coefficient is attained at our proprietary colony-forming unit dataset, where a score of 0.809 was achieved for the foreground class.

show abstract

Deep learning to detect bacterial colonies for the production of vaccines

Cited by 23 publications

References 11 publications

A New Few-Shot Learning Method of Bacterial Colony Counting Based on the Edge Computing Device

A New Few-Shot Learning Method of Bacterial Colony Counting Based on the Edge Computing Device

Tutorial - Machine Learning and Information Theoretic Methods for Molecular Biology and Medicine

Multi-Path U-Net Architecture for Cell and Colony-Forming Unit Image Segmentation

Contact Info

Product

Resources

About