A Reproducible Microscopy Acquisition Pipeline and Microscopy-Aware Attention for Classification, Detection, and Segmentation of Microorganisms
Machine Learning and Knowledge Extraction · 14.10.2026 · 8 (10) · 330
DOI: 10.3390/make8100330 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 14.10.2026. Verfasst von Aleksei Samarin und 11 weiteren Autor:innen. Die Arbeit nennt 126 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Economic Development of the Russian Federation, HSE University.
Abstract (Originalsprache)
Automated microscopic image analysis is essential for quantitative microbiology, yet manual acquisition and generic recognition models struggle with morphological variability and scene artifacts. We address both ends of this pipeline. First, we present a low-cost, open-source acquisition system, based on an Arduino UNO R3 microcontroller and NEMA 17 stepper motors, that automates focusing, magnification, and illumination on microscopes from the Levenhuk MED series, including the Levenhuk MED 20T, MED 25T, MED 30T, MED 35T, and MED 40T, and applies a standardized, programmable control procedure intended to improve the reproducibility of imaging conditions. Using this system, we construct a benchmark of 100,000 microscopy images across five classes (micrococci, diplococci, streptococci, bacilli, and background), with annotations for classification, detection, and segmentation. Second, we propose Microscopy-Aware Attention (MAA), which augments standard self-attention with six learnable, biologically motivated priors capturing cell boundaries, focus quality, internal-structure contrast, spatial compactness, shape, and local density. MAA is evaluated on six classification backbones, six detection backbones, and five segmentation backbones against no-attention, Squeeze-and-Excitation, spatial-attention, and CBAM baselines. It consistently yields the best results, raising weighted F1 for classification from 0.947 to 0.975 (DINOv3), mAP50 for detection from 0.901 to 0.928 (InternImage-H), and mIoU for segmentation from 0.834 to 0.862 (SegMAN), with component-wise ablations showing task-specific contributions of each prior.
Förderung
- Ministry of Economic Development of the Russian Federation
- HSE University
Zitieren
APA
Samarin, A., Nazarenko, A., Nazarenko, D., Afonina, J., Kotenko, E., Dozortseva, A., Mamaeva, A., Savelev, A., Narova, G., Mikhailova, E., Motyko, A., & Malykh, V. (2026). A Reproducible Microscopy Acquisition Pipeline and Microscopy-Aware Attention for Classification, Detection, and Segmentation of Microorganisms. Machine Learning and Knowledge Extraction, 8(10), 330. https://doi.org/10.3390/make8100330
Vancouver
Samarin A, Nazarenko A, Nazarenko D, Afonina J, Kotenko E, Dozortseva A, et al. A Reproducible Microscopy Acquisition Pipeline and Microscopy-Aware Attention for Classification, Detection, and Segmentation of Microorganisms. Machine Learning and Knowledge Extraction. 2026;8(10):330. doi:10.3390/make8100330
BibTeX
@article{Samarin2026,
author = {Samarin, Aleksei and Nazarenko, Artem and Nazarenko, Dmitry and Afonina, Julia and Kotenko, Egor and Dozortseva, Aleksandra and Mamaeva, Anastasia and Savelev, Alexander and Narova, Galiya and Mikhailova, Elena and Motyko, Alexander and Malykh, Valentin},
title = {A Reproducible Microscopy Acquisition Pipeline and Microscopy-Aware Attention for Classification, Detection, and Segmentation of Microorganisms},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {10},
pages = {330},
doi = {10.3390/make8100330}
}
EUVIMED