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

Abstract

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.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

“…In addition, Rattray et al investigated the identification of Pseudomonas aeruginosa strains from colony image data from clinical and environmental samples for a robust, repeatable detection of phenotype on the level of individual strains, and they reported an average validation accuracy of 92.9% and an average test accuracy of 90.7% for the classification of individual strains [ 69 ]. A new few-shot learning method of bacterial colony counting was also described to be useful for Escherichia coli on Plate Count Agar (PCA) with YOLOv3 models, aiding colony-forming unit (CFU) counting and bacterial quantification in the clinical laboratory [ 70 ].…”

Deep learning networks for microbiology images recognition

“…Furthermore, CNN will automatically seize a grasp of filters without explicitly mentioning them [4]. These filters can be of help to draw correct and relevant features from the input data.…”

“…As we know, nowadays parallel training task plays an important role in pre-training of big model including Bidirectional Encoder Representations from Transformer (BERT) and Generative Pre-Training (GPT). The basic procedure of parallel training can be depicted as when faced with large amounts of data, plenty of GPU is needed to speed up the calculation targeted at current pre-training task, and our task is to design a series of scheduling policies in order to put the GPU resource to better use and cut down the vacancy and waste of the GPU hash rate [4][5][6]. It can be split up into two different types named Data-parallel based method and Model-parallel based method.…”

U2-Net and ResNet50-Based Automatic Pipeline for Bacterial Colony Counting

“…Cascade R-CNN achieved the highest mean average precision (MAP) of 52.3% and 59.4% on intersection over union (IoU) ranging from 0.5 to 0.95. Furthermore, a lightweight improved YOLOv3 [ 24 ] network based on the few-shot learning strategy was proposed [ 25 ]. The network was trained and validated using only five raw images, resulting in an improvement in average accuracy from 64.3% to 97.4% and a significant decrease in the false negative rate from 32.1% to 1.5%.…”