{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T11:08:46Z","timestamp":1783940926871,"version":"3.55.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":62,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    While automation has transformed many areas inside clinical laboratories, microbiology still relies heavily on manual tasks, particularly the culture of samples on agar plates and their subsequent manual review for microorganism identification and antibiotic susceptibility profiling. Bacterial colony detection and classification require trained professionals, making the process time-consuming and prone to human error. Developing deep learning models to automate these tasks could improve microbiology workflows and accelerate clinical decision-making. In this study we trained and evaluated five object detection architectures (Faster R-CNN and RetinaNet with ResNet-50 and ResNet-101 backbones, and YOLOv8) on the Annotated Germs for Automated Recognition (AGAR) dataset for bacterial colony classification. Transfer learning, cross-subset generalization, and Weighted Box Fusion (WBF) ensemble methods were applied to enhance and characterize performance. Additionally, we created and publicly released a curated dataset of 165 agar plate images containing colonies of\n                    <jats:italic>S.\u00a0aureus<\/jats:italic>\n                    ,\n                    <jats:italic>P.\u00a0aeruginosa<\/jats:italic>\n                    , and\n                    <jats:italic>E.\u00a0coli<\/jats:italic>\n                    cultured across four distinct culture media. YOLOv8m achieved a mean Average Precision (mAP) of 69.0% on the AGAR dataset, outperforming the best Detectron2 model (Faster R-CNN ResNet-101, 63.1%) by 5.9 percentage points. A four-model WBF ensemble combining both architectures reached 70.5% mAP (95% CI: 68.4\u201371.7). Cross-subset evaluation showed that a single model trained on the full dataset generalizes well to individual imaging conditions, making subset-specific fine-tuning largely unnecessary. On the curated dataset, a mixed ensemble reached 58.7% mAP (95% CI: 57.1\u201363.7). These results demonstrate that architecture choice and training data diversity are the primary drivers of performance for colony detection on agar plates.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-48621-0","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:54:02Z","timestamp":1778576042000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep neural networks in medical microbiology for bacterial colonies classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Jos\u00e9 Duarte","family":"Pereira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Veloso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00e3o","family":"Gama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"48621_CR1","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1093\/clinchem\/hvab242","volume":"68","author":"K Antonios","year":"2021","unstructured":"Antonios, K., Croxatto, A. & Culbreath, K. Current state of laboratory automation in clinical microbiology laboratory. Clin. Chem. 68, 99\u2013114. https:\/\/doi.org\/10.1093\/clinchem\/hvab242 (2021).","journal-title":"Clin. Chem."},{"key":"48621_CR2","doi-asserted-by":"publisher","unstructured":"Williams, R.\u00a0E. & Trotman, R.\u00a0E. Automation in diagnostic bacteriology. J. Clin. Pathol. s2-3, 8\u201313. https:\/\/doi.org\/10.1136\/jcp.s2-3.1.8 (1969).","DOI":"10.1136\/jcp.s2-3.1.8"},{"key":"48621_CR3","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1016\/j.cll.2013.03.002","volume":"33","author":"SM Novak","year":"2013","unstructured":"Novak, S. M. & Marlowe, E. M. Automation in the clinical microbiology laboratory. Clin. Lab. Med. 33, 567\u2013588. https:\/\/doi.org\/10.1016\/j.cll.2013.03.002 (2013).","journal-title":"Clin. Lab. Med."},{"key":"48621_CR4","doi-asserted-by":"publisher","unstructured":"Bourbeau, P.\u00a0P. & Ledeboer, N.\u00a0A. Automation in clinical microbiology. J. Clin. Microbiol. 51, 1658\u20131665. https:\/\/doi.org\/10.1128\/JCM.00301-13 (2013).","DOI":"10.1128\/JCM.00301-13"},{"key":"48621_CR5","doi-asserted-by":"publisher","unstructured":"Bard, J.\u00a0D., Prinzi, A.\u00a0M., Larkin, P.\u00a0M., Peaper, D.\u00a0R. & Rhoads, D.\u00a0D. Proceedings of the clinical microbiology open 2024: artificial intelligence applications in clinical microbiology. J. Clin. Microbiol. 63, e01804-24. https:\/\/doi.org\/10.1128\/jcm.01804-24 (2025).","DOI":"10.1128\/jcm.01804-24"},{"key":"48621_CR6","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1515\/cclm-2017-0287","volume":"56","author":"F Cabitza","year":"2018","unstructured":"Cabitza, F. & Banfi, G. Machine learning in laboratory medicine: waiting for the flood?. Clin. Chem. Lab. Med. (CCLM) 56, 516\u2013524. https:\/\/doi.org\/10.1515\/cclm-2017-0287 (2018).","journal-title":"Clin. Chem. Lab. Med. (CCLM)"},{"key":"48621_CR7","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","volume":"25","author":"MP McBee","year":"2018","unstructured":"McBee, M. P. et al. Deep learning in radiology. Acad. Radiol. 25, 1472\u20131480. https:\/\/doi.org\/10.1016\/j.acra.2018.02.018 (2018).","journal-title":"Acad. Radiol."},{"key":"48621_CR8","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1016\/j.ajpath.2019.05.007","volume":"189","author":"S Wang","year":"2019","unstructured":"Wang, S., Yang, D. M., Rong, R., Zhan, X. & Xiao, G. Pathology image analysis using segmentation deep learning algorithms. Am. J. Pathol. 189, 1686. https:\/\/doi.org\/10.1016\/j.ajpath.2019.05.007 (2019).","journal-title":"Am. J. Pathol."},{"key":"48621_CR9","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s13534-020-00168-3","volume":"10","author":"A Khouani","year":"2020","unstructured":"Khouani, A., El Habib Daho, M., Mahmoudi, S. A., Chikh, M. A. & Benzineb, B. Automated recognition of white blood cells using deep learning. Biomed. Eng. Lett. 10, 359\u2013367. https:\/\/doi.org\/10.1007\/s13534-020-00168-3 (2020).","journal-title":"Biomed. Eng. Lett."},{"key":"48621_CR10","unstructured":"Pritt, B. S. Computer vision and artificial intelligence are emerging diagnostic tools for the clinical microbiologist. J. Clin. Microbiol. (2020)."},{"key":"48621_CR11","doi-asserted-by":"publisher","unstructured":"Majchrowska, S. et al. Assessing microbial colony counting: a deep learning approach with the AGAR image dataset. Neurocomputing630, 2563. https:\/\/doi.org\/10.1016\/j.neucom.2025.129654 (2025).","DOI":"10.1016\/j.neucom.2025.129654"},{"key":"48621_CR12","doi-asserted-by":"crossref","unstructured":"Majchrowska, S. et al. Deep neural networks approach to microbial colony detection\u2014a comparative analysis. In Digital Interaction and Machine Intelligence (eds. Biele, C.) 98\u2013106 (Springer International Publishing, 2022).","DOI":"10.1007\/978-3-031-11432-8_9"},{"key":"48621_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-14879-3","volume":"12","author":"KM Graczyk","year":"2022","unstructured":"Graczyk, K. M., Paw\u0142owski, J., Majchrowska, S. & Golan, T. Self-normalized density map (SNDM) for counting microbiological objects. Sci. Rep. 12, 1\u201313. https:\/\/doi.org\/10.1038\/s41598-022-14879-3 (2022).","journal-title":"Sci. Rep."},{"key":"48621_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109706","volume":"130","author":"S-J Liu","year":"2022","unstructured":"Liu, S.-J., Huang, P.-C., Liu, X.-S., Lin, J.-J. & Zou, Z. A two-stage deep counting for bacterial colonies from multi-sources. Appl. Soft Comput. 130, 109706. https:\/\/doi.org\/10.1016\/j.asoc.2022.109706 (2022).","journal-title":"Appl. Soft Comput."},{"key":"48621_CR15","doi-asserted-by":"publisher","unstructured":"Whipp, J. & Dong, A. YOLO-based deep learning to automated bacterial colony counting. In 2022 IEEE Eighth International Conference on Multimedia Big Data (BigMM) 120\u2013124 (IEEE, 2022). https:\/\/doi.org\/10.1109\/BigMM55396.2022.00028.","DOI":"10.1109\/BigMM55396.2022.00028"},{"key":"48621_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-09264-z","volume":"12","author":"J Paw\u0142owski","year":"2022","unstructured":"Paw\u0142owski, J., Majchrowska, S. & Golan, T. Generation of microbial colonies dataset with deep learning style transfer. Sci. Rep. 12, 1\u201312. https:\/\/doi.org\/10.1038\/s41598-022-09264-z (2022).","journal-title":"Sci. Rep."},{"key":"48621_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.105268","volume":"184","author":"P Andreini","year":"2020","unstructured":"Andreini, P., Bonechi, S., Bianchini, M., Mecocci, A. & Scarselli, F. Image generation by GAN and style transfer for agar plate image segmentation. Comput. Methods Programs Biomed. 184, 105268. https:\/\/doi.org\/10.1016\/j.cmpb.2019.105268 (2020).","journal-title":"Comput. Methods Programs Biomed."},{"key":"48621_CR18","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.3390\/app15031260","volume":"15","author":"K Mennemann","year":"2025","unstructured":"Mennemann, K., Ebert, N., Reichardt, L. & Wasenm\u00fcller, O. Enhancing colony detection of microorganisms in agar dishes using sam-based synthetic data augmentation in low-data scenarios. Appl. Sci. 15, 1260. https:\/\/doi.org\/10.3390\/app15031260 (2025).","journal-title":"Appl. Sci."},{"key":"48621_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110141","volume":"191","author":"N Ebert","year":"2025","unstructured":"Ebert, N., Stricker, D. & Wasenm\u00fcller, O. Enhancing robustness and generalization in microbiological few-shot detection through synthetic data generation and contrastive learning. Comput. Biol. Med. 191, 110141. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110141 (2025).","journal-title":"Comput. Biol. Med."},{"key":"48621_CR20","doi-asserted-by":"publisher","first-page":"10568","DOI":"10.3390\/app131910568","volume":"13","author":"F Yang","year":"2023","unstructured":"Yang, F. et al. Microbial colony detection based on deep learning. Appl. Sci. 13, 10568. https:\/\/doi.org\/10.3390\/app131910568 (2023).","journal-title":"Appl. Sci."},{"key":"48621_CR21","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1038\/s41597-023-02404-8","volume":"10","author":"L Makrai","year":"2023","unstructured":"Makrai, L. et al. Annotated dataset for deep-learning-based bacterial colony detection. Sci. Data 10, 497. https:\/\/doi.org\/10.1038\/s41597-023-02404-8 (2023).","journal-title":"Sci. Data"},{"key":"48621_CR22","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.3390\/microorganisms13071617","volume":"13","author":"M Wang","year":"2025","unstructured":"Wang, M. et al. Colony-YOLO: a lightweight micro-colony detection network based on improved YOLOv8n. Microorganisms 13, 1617. https:\/\/doi.org\/10.3390\/microorganisms13071617 (2025).","journal-title":"Microorganisms"},{"key":"48621_CR23","doi-asserted-by":"publisher","unstructured":"Pereira, J. D. Deep neural networks in medical microbiology for bacterial colonies classification: curated dataset (coco and yolo) https:\/\/doi.org\/10.5281\/zenodo.18505210 (2026).","DOI":"10.5281\/zenodo.18505210"},{"key":"48621_CR24","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y. & Girshick, R. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)."},{"key":"48621_CR25","doi-asserted-by":"publisher","unstructured":"Pereira, J. D. Micro-colony detection reproducibility package. https:\/\/doi.org\/10.5281\/zenodo.19065201 (2026).","DOI":"10.5281\/zenodo.19065201"},{"key":"48621_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117","volume":"107","author":"R Solovyev","year":"2021","unstructured":"Solovyev, R., Wang, W. & Gabruseva, T. Weighted boxes fusion: ensembling boxes from different object detection models. Image Vis. Comput. 107, 104117. https:\/\/doi.org\/10.1016\/j.imavis.2021.104117 (2021).","journal-title":"Image Vis. Comput."},{"key":"48621_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Microsoft coco: common objects in context. ECCV (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"48621_CR28","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R. et al. Coco api: pycocotools cocoeval.py. https:\/\/github.com\/cocodataset\/cocoapi\/blob\/master\/PythonAPI\/pycocotools\/cocoeval.py (2015)."},{"key":"48621_CR29","unstructured":"Ultralytics. Ultralytics yolo configuration documentation. https:\/\/docs.ultralytics.com\/usage\/cfg\/ (2026)."},{"key":"48621_CR30","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/TPAMI.2015.2465908","volume":"38","author":"J Hosang","year":"2015","unstructured":"Hosang, J., Benenson, R., Doll\u00e1r, P. & Schiele, B. What makes for effective detection proposals?. IEEE Trans. Pattern Anal. Mach. Intell. 38, 814\u2013830. https:\/\/doi.org\/10.1109\/TPAMI.2015.2465908 (2015).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"48621_CR31","doi-asserted-by":"crossref","unstructured":"Efron, B. & Tibshirani, R.\u00a0J. An Introduction to the Bootstrap (Chapman & Hall, 1993).","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"48621_CR32","doi-asserted-by":"publisher","unstructured":"Pereira, J. D. Deep neural networks in medical microbiology for bacterial colonies classification: paper results bundle https:\/\/doi.org\/10.5281\/zenodo.19048988 (2026).","DOI":"10.5281\/zenodo.19048988"},{"key":"48621_CR33","doi-asserted-by":"publisher","unstructured":"Ebert, N., Stricker, D. & Wasenm\u00fcller, O. Transformer-based detection of microorganisms on high-resolution petri dish images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW). https:\/\/doi.org\/10.48550\/arXiv.2308.09436. arXiv:2308.09436 (2023).","DOI":"10.48550\/arXiv.2308.09436"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48621-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48621-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48621-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T11:01:42Z","timestamp":1783940502000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48621-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["48621"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-48621-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"assertion":[{"value":"2 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21683"}}