MICROBE-LENS A Deep Learning Framework for Automated Bacterial Image Analysis and Laboratory Report Generation

This paper presented Microbe-Lens, an end-to-end automated framework designed to streamline clinical microbiology workflows by combining custom YOLOv8-based bacterial colony detection with a FastAPI and ReportLabdriven automated reporting system.  Future work will focus on expanding the model to identify a broader spectrum of pathogenic microorganisms and enhancing deployment in resourceconstrained laboratory environments.

[1]            M. Talo, "An Automated Deep Learning Approach for Bacterial Image Classification," International Conference  on Advanced Technologies, Computer Engineering and Science (ICATCES), pp. 26-28, 2019. [2]            M. Amano et al., "Deep Learning Approach for Classifying Bacteria types using Morphology of Bacterial Colony," IEEE Engineering in Medicine & Biology Society (EMBC), pp. 2165-2168, 2022. [3]            M. F. Amri et al., "Bacterial Classification Using Deep Structured Convolutional Neural Network for Low Resource Data," Jurnal Elektronika dan Telekomunikasi (JET), vol. 23, no. 1, pp. 47-54, 2023. [4]            K. G. Mannava, M. R. Kalyan, and K. S. S. Praneeth, "Bacterial Image Classification Using Deep Learning Approach," Journal of Emerging Technologies and Innovative Research (JETIR), vol. 11, no. 4, pp. g379-g386, 2024. [5]            S. A. Nagro et al., "Automatic Identification of Single Bacterial Colonies Using Deep and Transfer Learning," IEEE Access,   vol.  10, pp. 120181-120190, 2022.  [6]            Ultralytics, "YOLOv8: State-of-the-art YOLO models," GitHub repository, 2023. [Online].  Available: https://github.com/ultralytics/ultralytics  [7]     Tiangolo, "FastAPI: High performance, easy to learn, fast to code, ready for production," 2018. [Online]. Available: https://github.com/tiangolo/fastapi [8] The ReportLab Open Source PDF Library User Guide, ReportLab Inc., 2023.