{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:52:42Z","timestamp":1773273162453,"version":"3.50.1"},"reference-count":22,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["AP32721703"],"award-info":[{"award-number":["AP32721703"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>This paper addresses the problem of multi-class classification of bacterial microscopic images using a rigorous experimental protocol designed to prevent information leakage and improve performance. The dataset consists of 2034 images representing 33 taxa, organized by class. Data integrity checks confirmed the absence of corrupted or unreadable files. To formalize image characteristics and ensure quality control, indirect geometric and textural features were calculated, including minimum frame size, brightness statistics (mean and standard deviation), Shannon entropy, Laplace variance, and Sobel gradient energy. Quality checks revealed a small proportion of images with extreme brightness (2.5074%), while no samples with critically low sharpness according to the selected criteria were detected. Statistical analysis of interclass differences using the Kruskal\u2013Wallis test with multiple comparison correction demonstrated the high discriminatory power of texture features, specifically gradient energy (\u03b52 = 0.819987) and Laplace variance (\u03b52 = 0.709904). Feature correlations were consistent with their physical interpretation, revealing a strong positive relationship between sharpness and gradient energy. Principal component analysis confirmed a strong structural pattern, with the first two components explaining 75.5766% of the total variance. For a unified comparison, classical machine learning, transfer learning, and modern deep architectures were evaluated within a single protocol.<\/jats:p>","DOI":"10.3390\/computers15030180","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T09:55:38Z","timestamp":1773136538000},"page":"180","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid MIL Architecture for Multi-Class Classification of Bacterial Microscopic Images"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8958-1846","authenticated-orcid":false,"given":"Aisulu","family":"Ismailova","sequence":"first","affiliation":[{"name":"Institute of Business and Digital Technology, GEP Information Systems, S. Seifullin Kazakh Agrotechnical Research University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gulbanu","family":"Yessenbayeva","sequence":"additional","affiliation":[{"name":"Institute of Business and Digital Technology, GEP Information Systems, S. Seifullin Kazakh Agrotechnical Research University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0506-4890","authenticated-orcid":false,"given":"Kuanysh","family":"Kadirkulov","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Technology, Esil University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raushan","family":"Moldasheva","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Faculty of Physics, Mathematics and Information Technology, Kh. Dosmukhamedov Atyrau University, Atyrau 010009, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elmira","family":"Eldarova","sequence":"additional","affiliation":[{"name":"Department of Informatics, Faculty of Physics, Mathematics and Information Technology, Kh. Dosmukhamedov Atyrau University, Atyrau 010009, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gulnaz","family":"Zhilkishbayeva","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Artificial Intelligence, Department of SMART Technologies, Sh. Yesenov Caspian University of Technology and Engineering, Aktau 010008, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shynar","family":"Kodanova","sequence":"additional","affiliation":[{"name":"Department of Production Automation and Information Technology, Faculty of Information Technology, Atyrau University of Oil and Gas, S. Utebayev, Atyrau 010009, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9815-9594","authenticated-orcid":false,"given":"Shynar","family":"Yelezhanova","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Faculty of Physics, Mathematics and Information Technology, Kh. Dosmukhamedov Atyrau University, Atyrau 010009, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentina","family":"Makhatova","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Faculty of Physics, Mathematics and Information Technology, Kh. Dosmukhamedov Atyrau University, Atyrau 010009, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6367-5900","authenticated-orcid":false,"given":"Alexander","family":"Nedzved","sequence":"additional","affiliation":[{"name":"Faculty of Applied Mathematics and Computer Science, Department of Management Information Systems, Belarusian State University, 220030 Minsk, Belarus"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.1038\/s41467-025-58606-8","article-title":"Data splitting to avoid information leakage with DataSAIL","volume":"16","author":"Joeres","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1038\/s41592-024-02362-y","article-title":"Guiding questions to avoid data leakage in biological machine learning applications","volume":"21","author":"Bernett","year":"2024","journal-title":"Nat. Methods"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis in ML-based science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"key":"ref_4","first-page":"772","article-title":"Improving generalization in classification of novel bacterial strains: A multi-headed ResNet approach for microscopic image classification","volume":"48","author":"Yachnaya","year":"2024","journal-title":"Comput. Opt."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Samarin, A., Savelev, A., Toropov, A., Dozortseva, A., Kotenko, E., Nazarenko, A., Motyko, A., Narova, G., Mikhailova, E., and Malykh, V. (2025). Automation of Multi-Class Microscopy Image Classification Based on the Microorganisms Taxonomic Features Extraction. J. Imaging, 11.","DOI":"10.3390\/jimaging11060201"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, M., Luo, J., Lin, K., Chen, Y., Huang, X., Liu, J., Wang, A., and Xiao, D. (2025). Colony-YOLO: An Efficient Object Detection Approach for Automated Bacterial Colony Counting and Size Measurement. Microorganisms, 13.","DOI":"10.3390\/microorganisms13071617"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhu, H., Luo, J., and He, S. (2024). Detecting Multiple Mixed Bacteria Using Dual-Mode Hyperspectral Imaging and Deep Neural Networks. Appl. Sci., 14.","DOI":"10.3390\/app14041525"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e2180","DOI":"10.7717\/peerj-cs.2180","article-title":"Bacterial image analysis using multi-task deep learning approaches for clinical microscopy","volume":"10","author":"Chin","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"78409","DOI":"10.1109\/ACCESS.2024.3403538","article-title":"Multiple instance learning in medical images: A systematic review","volume":"12","author":"Barbosa","year":"2024","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"15609","DOI":"10.1109\/ACCESS.2024.3358671","article-title":"A Deep Learning Model for Bacterial Classification Using Big Transfer (BiT)","volume":"12","author":"Visitsattaponge","year":"2024","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: A survey","volume":"88","author":"Shamshad","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of Vision Transformers and Convolutional Neural Networks in Medical Imaging: A Literature Review","volume":"48","author":"Takahashi","year":"2024","journal-title":"J. Med. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"8690","DOI":"10.1002\/cam4.5581","article-title":"Application of EfficientNet-B0 and GRU-based deep learning in medical image recognition","volume":"12","author":"Chen","year":"2023","journal-title":"Cancer Med."},{"key":"ref_14","first-page":"20552076241284920","article-title":"Brain tumor grade classification using the ConvNeXt architecture","volume":"10","author":"Mehmood","year":"2024","journal-title":"SAGE Open Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102562","DOI":"10.1016\/j.ecoinf.2024.102562","article-title":"Bacterial community characterization by deep learning aided image analysis in soil chips","volume":"82","author":"Zou","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"111369","DOI":"10.1016\/j.engappai.2025.111369","article-title":"Automated imaging and machine learning for soil bacteria classification: Challenges and insights","volume":"139","author":"Konopka","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"16633","DOI":"10.1038\/s41598-023-43542-8","article-title":"Risk of data leakage in estimating the diagnostic performance of a deep-learning-based computer-aided system for psychiatric disorders","volume":"13","author":"Lee","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"38893","DOI":"10.1038\/s41598-025-22649-0","article-title":"A multi-scale attention-based Swin transformer model for medical image analysis","volume":"15","author":"Golkhatmi","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"111323","DOI":"10.1016\/j.asoc.2024.111323","article-title":"An efficient medical image classification network based on multi-branch CNN and token grouping Transformer","volume":"153","author":"Liu","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8747","DOI":"10.21037\/qims-23-542","article-title":"Transformers in medical image segmentation: A narrative review","volume":"13","author":"Khan","year":"2023","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_21","first-page":"12","article-title":"Development of a Feature Vector for Accurate Breast Cancer Detection in Mammographic Images","volume":"7","author":"Ismailova","year":"2026","journal-title":"Int. J. Cogn. Comput. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-0716-4642-7_1","article-title":"An assay for variable fragment length allele-specific genotyping","volume":"2943","author":"Kalendar","year":"2025","journal-title":"Genotyping Methods Protoc."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/3\/180\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T09:14:12Z","timestamp":1773220452000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/3\/180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":22,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["computers15030180"],"URL":"https:\/\/doi.org\/10.3390\/computers15030180","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]}}}