TrCL-AGS: A Universal Sequential Triple-Stage Contrastive Learning Framework for Bacterial Detection With Across-Growth-Stage Information
- 8 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (10) , 14886-14896
Abstract
The imprudent use of antibiotics has led to increased bacterial resistance, posing a serious threat to public health. Traditional visual-based antibiotic susceptibility testing (AST) methods are time-consuming and labor-intensive. Deep-learning-based bacterial detection algorithms have significantly improved the efficiency and accuracy of AST. However, existing deep-learning-based bacterial detection algorithms ignore unique challenges of AST images, such as confluent clusters, complex backgrounds, and morphologically similar noise. To address these issues, we propose a novel bacterial detection framework named the triple-stage contrastive learning framework with across-growth-stage information (TrCL-AGS). Specifically, we design a novel across-growth-stage pretraining (AGSP) task to mine across-growth-stage information from the continuous images, providing a richer and more robust feature space for subsequent stages. Instance-level contrastive learning (ILCL) is constructed to extract invariant semantic features of bacteria at a particular growth stage and exclude features similar to bacteria but do not match the specific growth stages. Besides, discriminative features between objects and backgrounds are enhanced by the category-level contrastive learning (CLCL) stage. Extensive experiments on a real-world clinical bacterial AST dataset demonstrate that our method can achieve state-of-the-art performance compared with existing object detection methods. And our framework is compatible with most detectors.Keywords
Funding Information
- National Natural Science Foundation of China (32170173)
- Pilot Project of Basic Research in Suzhou Science and Technology Plan (SSD2024015)
This publication has 35 references indexed in Scilit:
- YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information2024
- A portable deep-learning-assisted digital single-particle counting biosensing platform for amplification-free nucleic acid detection using a lens-free holography microscopeNano Today, 2024
- Fine-grained recognition: Multi-granularity labels and category similarity matrixKnowledge-Based Systems, 2023
- Antimicrobial Resistance2023
- Trichromatic ratiometric fluorescent sensor based on machine learning and smartphone for visual and portable monitoring of tetracycline antibioticsChemical Engineering Journal, 2022
- Multi-network contrastive learning of visual representationsKnowledge-Based Systems, 2022
- Smartphone-integrated multi-color ratiometric fluorescence portable optical device based on deep learning for visual monitoring of Cu2+ and thiramChemical Engineering Journal, 2022
- End-to-End Object Detection with Transformers2020
- Identification and Antibiotic‐Susceptibility Profiling of Infectious Bacterial Agents: A Review of Current and Future TrendsBiotechnology Journal, 2018
- Microsoft COCO: Common Objects in Context2014