The site of the Media Sphera Publishers contains materials intended solely for healthcare professionals.
By closing this message, you confirm that you are a certified medical professional or a student of a medical educational institution.

Login
EN
+7 (495) 482-4118
+7 (495) 482-0604
+8 800 250-18-12
  • (toll-free number for subscriptions)
    Mon-Fri from 10 a.m. to 6 p.m.

  • © 1998-2025
+7 (495) 482-43-29
EN
All journals
Journal
Year
Year
Search result: 0

Astaf’ev A.V.

National Research University Higher School of Economics

Maslenkina K.S.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
Academician A.P. Avtsyn Research Institute of Human Morphology a division of the Academician B.V. Petrovsky Russian Scientific Center of Surgery

Mikhaleva L.M.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
Academician A.P. Avtsyn Research Institute of Human Morphology a division of the Academician B.V. Petrovsky Russian Scientific Center of Surgery

Trofimova E.A.

National Research University Higher School of Economics

Zuenko D.O.

National Research University Higher School of Economics

Kaibysheva V.O.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
N.I. Pirogov Russian National Research Medical University

Lokhmatov M.M.

National Medical Research Center for Children’s Health;
Sechenov First Moscow State Medical University (Sechenov University)

Budkina T.N.

National Medical Research Center for Children’s Health

Kulikov K.A.

N.I. Pirogov Russian National Research Medical University;
National Medical Research Center for Children’s Health

Ilansskaya M.V.

National Medical Research Center for Children’s Health

Makarova S.G.

National Medical Research Center for Children’s Health

Vyazankina S.S.

National Medical Research Center for Children’s Health

Mokritskii A.I.

N.I. Pirogov Russian National Research Medical University

Fedorov E.D.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
N.I. Pirogov Russian National Research Medical University

High-accuracy eosinophil detection in eosinophilic esophagitis histological images using machine learning model YOLO11

Authors:

Astaf’ev A.V., Maslenkina K.S., Mikhaleva L.M., Trofimova E.A., Zuenko D.O., Kaibysheva V.O., Lokhmatov M.M., Budkina T.N., Kulikov K.A., Ilansskaya M.V., Makarova S.G., Vyazankina S.S., Mokritskii A.I., Fedorov E.D.

More about the authors

Journal: Russian Journal of Evidence-Based Gastroenterology. 2025;14(2): 19‑29

DOI: 10.17116/dokgastro20251402119

Read: 842 times

Download PDF (RU)
Contact the author
Table of contents

HIGH-ACCURACY EOSINOPHIL DETECTION IN EOSINOPHILIC ESOPHAGITIS HISTOLOGICAL IMAGES USING MACHINE LEARNING MODEL YOLO11
HIGH-ACCURACY EOSINOPHIL DETECTION IN EOSINOPHILIC ESOPHAGITIS HISTOLOGICAL IMAGES USING MACHINE LEARNING MODEL YOLO11

To cite this article:

Astaf’ev AV, Maslenkina KS, Mikhaleva LM, et al. . High-accuracy eosinophil detection in eosinophilic esophagitis histological images using machine learning model YOLO11. Russian Journal of Evidence-Based Gastroenterology. 2025;14(2):19‑29. (In Russ.)
https://doi.org/10.17116/dokgastro20251402119

Подписка 2026 Доказательная гастроэнтерология (Russian Journal of Evidence-Based Gastroenterology)
МСФ на ЯМ
Использование инфографики авторами научных работ
Close metadata
Recommended articles:
Growth factors PDGF-AA, PDGF-BB and BDNF as pote­ntial differentiating biomarkers of unipolar and bipo­lar depression. S.S. Korsakov Journal of Neurology and Psychiatry. 2024;(9):104-108
Esophageal pathology and bronchial asthma: pathogenetic inte­ractions and possibilities for therapy opti­mization. Russian Journal of Preventive Medi­cine. 2024;(11):129-134
Comparison of models for prediction of spontaneous preterm birth. Medi­cal Technologies. Asse­ssment and Choice. 2024;(4):10-19
Analysis of exha­led air composition using a portable electronic nose as a promising method for non-invasive rapid diagnosis of pulmonary tube­rculosis. Labo­ratory Service. 2024;(4):12-20
On the path to personalized cardiology: prospects of precise asse­ssment of cardiovascular risks and predictive-prognostic diagnostics. Russian Journal of Cardiology and Cardiovascular Surgery. 2025;(2):206-215
Primary angle closure suspects: application of machine learning method for substantiation of close moni­toring. Russian Annals of Ophthalmology. 2025;(2):67-74
Prognostic model and calculator for asse­ssing the risk of prolonged pleural effu­sion after lobe­ctomy. Piro­gov Russian Journal of Surgery. 2025;(6):26-34
Arti­ficial inte­lligence capa­bilities in multiple scle­rosis. S.S. Korsakov Journal of Neurology and Psychiatry. 2025;(5):14-21
Arti­ficial inte­lligence in surgery. Redu­cing the risks rela­ted to poly­pharmacy in perioperative period. Piro­gov Russian Journal of Surgery. 2025;(7):59-66
Abstract:

OBJECTIVE

To evaluate the effectiveness of the YOLO11 machine learning model for automated segmentation and detection of eosinophils in histological images in order to improve the diagnostic accuracy of eosinophilic esophagitis (EoE).

MATERIALS AND METHODS

A multicenter retrospective analysis was conducted using histological images obtained through whole slide imaging (WSI) from 60 patients diagnosed with EoE. Out of 653 tissue section images, 54 were manually annotated and reviewed. The annotated dataset was then used to train the YOLO11 model.

RESULTS

By the 150th training epoch, the model demonstrated consistent improvement in precision and recall for bounding boxes detection. The final recall value reached 0.98, indicating a very high sensitivity of the model to the target areas (i.e., eosinophils) within the histological slides. The Intersection over Union (IoU) score peaked at 0.94, reflecting the model’s robust performance in accurately localizing and segmenting eosinophils. Furthermore, the model exhibited strong precision and recall not only for bounding boxes but also for segmentation masks, reinforcing its capability to delineate eosinophil boundaries. However, performance evaluation on new, unannotated images revealed several limitations requiring further optimization, particularly a decrease in effectiveness when analyzing clusters of eosinophils.

CONCLUSION

The YOLO11-based approach developed in this study represents a significant advancement in the automation of histological assessment for EoE, offering a highly accurate tool for eosinophilic infiltration analysis. Future research directions include expanding the annotated WSI dataset, refining the model through additional training, and exploring the application of vision transformer-based architectures. The results of eosinophil segmentation and peak eosinophil count (PEC) will require retrospective validation against values determined by pathologists through light microscopy.

Keywords:

machine learning
computer vision
transformer model architecture
analysis of medical images
eosinophilic esophagitis

Authors:

Astaf’ev A.V.

National Research University Higher School of Economics

Maslenkina K.S.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
Academician A.P. Avtsyn Research Institute of Human Morphology a division of the Academician B.V. Petrovsky Russian Scientific Center of Surgery

Mikhaleva L.M.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
Academician A.P. Avtsyn Research Institute of Human Morphology a division of the Academician B.V. Petrovsky Russian Scientific Center of Surgery

Trofimova E.A.

National Research University Higher School of Economics

Zuenko D.O.

National Research University Higher School of Economics

Kaibysheva V.O.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
N.I. Pirogov Russian National Research Medical University

Lokhmatov M.M.

National Medical Research Center for Children’s Health;
Sechenov First Moscow State Medical University (Sechenov University)

Budkina T.N.

National Medical Research Center for Children’s Health

Kulikov K.A.

N.I. Pirogov Russian National Research Medical University;
National Medical Research Center for Children’s Health

Ilansskaya M.V.

National Medical Research Center for Children’s Health

Makarova S.G.

National Medical Research Center for Children’s Health

Vyazankina S.S.

National Medical Research Center for Children’s Health

Mokritskii A.I.

N.I. Pirogov Russian National Research Medical University

Fedorov E.D.

City Clinical Hospital No. 31 named after Academician G.M. Savelyeva Moscow Healthcare Department;
N.I. Pirogov Russian National Research Medical University

Received:

05.05.2025

Accepted:

26.05.2025

Close metadata

References:

  1. Amil-Dias J, Oliva S, Papadopoulou A, Thomson M, Gutiérrez-Junquera C, Kalach N, Orel R, Auth MK, Nijenhuis-Hendriks D, Strisciuglio C, Bauraind O, Chong S, Ortega GD, Férnandez SF, Furman M, Garcia-Puig R, Gottrand F, Homan M, Huysentruyt K, Kostovski A, Otte S, Rea F, Roma E, Romano C, Tzivinikos C, Urbonas V, Velde SV, Zangen T, Zevit N. Diagnosis and management of eosinophilic esophagitis in children: An update from the European Society for Paediatric Gastroenterology, Hepatology and Nutrition (ESPGHAN). Journal of Pediatric Gastroenterology and Nutrition. 2024;79(2):394-437.  https://doi.org/10.1002/jpn3.12188
  2. Dhar A, Haboubi HN, Attwood SE, Auth MKH, Dunn JM, Sweis R, Morris D, Epstein J, Novelli MR, Hunter H, Cordell A, Hall S, Hayat JO, Kapur K, Moore AR, Read C, Sami SS, Turner PJ, Trudgill NJ. British Society of Gastroenterology (BSG) and British Society of Paediatric Gastroenterology, Hepatology and Nutrition (BSPGHAN) joint consensus guidelines on the diagnosis and management of eosinophilic oesophagitis in children and adults. Gut. 2022;71(8):1459-1487. https://doi.org/10.1136/gutjnl-2022-327326
  3. Kaibysheva VO, Drapkina OM, Berns SA, Kashin SV, Fedorov ED, Mikhaleva LM, Maslenkina KS, Nikonov EL, Shepel’ RN. Diagnostika i lechenie eozinofil‘nogo ezofagita. Metodicheskie rekomendatsii. M.: ROPNIZ, 2024. (In Russ.). https://doi.org/10.15829/ROPNIZ-k7-2024
  4. Kaibysheva VO, Mikhaleva LM, Fedorov ED. Eozinofil’nyy ezofagit. Pererabotannoe i dopolnennoe izdanie. M.: Meditsinskoye izdatel’stvo «Media Sfera»; 2024. (In Russ.).
  5. Perechen’ redkikh (orfannykh) zabolevanii ot 12 marta 2025 goda. Perechen’, Minzdrav Rossii, 12 marta 2025, № b/n. Accessed May 10, 2025. (In Russ.). https://minzdrav.gov.ru/documents/9824-perechen-redkih-orfannyh-zabolevaniy
  6. Lebedev GS, Shaderkin IA, Tertychny AS, Shaderkina AI. Digital pathomorphology: creation of an automated microscopy system. Rossijskij Zhurnal telemediciny` i e`lektronnogo zdravooxraneniya. 2021;7(4):27-47. (In Russ.). https://doi.org/10.29188/2712-9217-2021-7-4-27-47
  7. Adorno W 3rd, Catalano A, Ehsan L, Vitzhum von Eckstaedt H, Barnes B, McGowan E, Syed S, Brown DE. Advancing eosinophilic esophagitis diagnosis and phenotype assessment with deep learning computer vision. In: Biomedical Engineering Systems and Technologies, International Joint Conference, BIOSTEC. Revised Selected Papers. BIOSTEC (Conference). Vol 2021. NIH Public Access; 2021:44.  https://doi.org/10.5220/0010241900002865
  8. Archila LR, Smith L, Sihvo HK, Westerling-Bui T, Koponen V, O’Sullivan DM, Fernandez MCC, Alexander EE, Wang Y, Sivasubramaniam P, Patil A, Hopson PE, Absah I, Ravi K, Mounajjed T, Pai R, Hagen C, Hartley C, Graham RP, Moreira RK. Development and technical validation of an artificial intelligence model for quantitative analysis of histopathologic features of eosinophilic esophagitis. Journal of Pathology Informatics. 2022;13:100144. https://doi.org/10.1016/j.jpi.2022.100144
  9. Collins MH, Martin LJ, Alexander ES, Boyd JT, Sheridan R, He H, Pentiuk S, Putnam PE, Abonia JP, Mukkada VA, Franciosi JP, Rothenberg ME. Newly developed and validated eosinophilic esophagitis histology scoring system and evidence that it outperforms peak eosinophil count for disease diagnosis and monitoring. Diseases of the Esophagus. 2016;30 3:1-8.  https://doi.org/10.1111/dote.12470
  10. Czyzewski T, Daniel N, Rochman M, Caldwell JM, Osswald GA, Collins MH, Rothenberg ME, Savir Y. Machine learning approach for biopsy-based identification of eosinophilic esophagitis reveals importance of global features. IEEE Open Journal of Engineering in Medicine and Biology. 2021;2:218-223.  https://doi.org/10.1109/ojemb.2021.3089552
  11. Daniel N, Larey A, Aknin E, Osswald GA, Caldwell JM, Rochman M, Collins MH, Yang GY, Arva NC, Capocelli KE, Rothenberg ME, Savir Y. A deep multi-label segmentation network for eosinophilic esophagitis whole slide biopsy diagnostics. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE; 2022: 3211-3217. https://doi.org/10.1109/embc48229.2022.9871086
  12. Hirano I, Chan ES, Rank MA, Sharaf RN, Stollman NH, Stukus DR, Wang K, Greenhawt M, Falck-Ytter YT. AGA institute and the joint task force on allergy-immunology practice parameters clinical guidelines for the management of eosinophilic esophagitis. Gastroenterology. 2020;158(6):1776-1786. https://doi.org/10.1053/j.gastro.2020.02.038
  13. Larey A, Aknin E, Daniel N, Osswald GA, Caldwell JM, Rochman M, Wasserman T, Collins MH, Arva NC, Yang GY, Rothenberg ME, Savir Y. Harnessing artificial intelligence to infer novel spatial biomarkers for the diagnosis of eosinophilic esophagitis. Frontiers in Medicine. 2022;9:950728. https://doi.org/10.3389/fmed.2022.950728
  14. Votto M, Rossi CM, Caimmi SME, De Filippo M, Di Sabatino A, Lenti MV, Raffaele A, Marseglia GL, Licari A. The State of the Art of Artificial Intelligence Applications in Eosinophilic Esophagitis: A Systematic Review. Big Data and Cognitive Computing. 2024;8(7):76.  https://doi.org/10.3390/bdcc8070076
  15. Huang H, You Z, Cai H, Xu J, Lin D. Fast detection method for prostate cancer cells based on an integrated ResNet50 and YoloV5 framework. Computer Methods and Programs in Biomedicine. 2022;226:107184. https://doi.org/10.1016/j.cmpb.2022.107184
  16. Ultralytics YOLO11 Docs. The Ultralytics Docs Home Page. Accessed March 27, 2025. https://docs.ultralytics.com/
  17. Bankhead P, Loughrey MB, Fernández JA, Dombrowski Y, McArt DG, Dunne PD, McQuaid S, Gray RT, Murray LJ, Coleman HG, James JA, Salto-Tellez M, Hamilton PW. QuPath: Open source software for digital pathology image analysis. Scientific Reports. 2017;7(1):16878. https://doi.org/10.1038/s41598-017-17204-5
  18. Studer S, Bui TB, Drescher C, Hanuschkin A., Winkler L., Peters S., Müller K.-R. Towards CRISP-ML (Q): a machine learning process model with quality assurance methodology. Machine Learning and Knowledge Extraction. 2021;3(2):392-413.  https://doi.org/10.3390/make3020020
  19. Japkowicz N, Boukouvalas Z. Machine Learning Evaluation: Towards Reliable and Responsible AI. Cambridge University Press; 2024.
Contact the author
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.

Email Confirmation

An email was sent to test@gmail.com with a confirmation link. Follow the link from the letter to complete the registration on the site.

Email Confirmation

Contact us
If you have any questions, complaints or suggestions, please use this feedback form.
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.
Submit Application

You can become an author of one of our magazines, send a request and we will consider it in during the day.

Name
Phone
E-mail
Message
Login
Registration
E-mail
Password
Forgot Password?

Log in to the site using your account in one of the services

Password recovery
E-mail
Login
Register

We use cооkies to improve the performance of the site. By staying on our site, you agree to the terms of use of cооkies. To view our Privacy and Cookie Policy, please. click here.