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) 482-4329
+8 800 250-18-12
  • (toll-free number for subscriptions)
    Mon-Fri from 10 a.m. to 6 p.m.

  • © 1998-2026
+7 (495) 482-43-29
EN
All journals
Journal
Year
Year
Search result: 0

Mikhailov I.A.

Lomonosov Moscow State University

Khvostikov A.V.

Lomonosov Moscow State University

Krylov A.S.

Lomonosov Moscow State University

Methodical approaches to annotation and labeling of histological images in order to automatically detect the layers of the stomach wall and the depth of invasion of gastric cancer

Authors:

Mikhailov I.A., Khvostikov A.V., Krylov A.S.

More about the authors

Journal: Russian Journal of Archive of Pathology. 2022;84(6): 67‑73

DOI: 10.17116/patol20228406167

Read: 2786 times

Download PDF (RU)
Contact the author
Table of contents

METHODICAL APPROACHES TO ANNOTATION AND LABELING OF HISTOLOGICAL IMAGES IN ORDER TO AUTOMATICALLY DETECT THE LAYERS OF THE STOMACH WALL AND THE DEPTH OF INVASION OF GASTRIC CANCER
METHODICAL APPROACHES TO ANNOTATION AND LABELING OF HISTOLOGICAL IMAGES IN ORDER TO AUTOMATICALLY DETECT THE LAYERS OF THE STOMACH WALL AND THE DEPTH OF INVASION OF GASTRIC CANCER

To cite this article:

Mikhailov IA, Khvostikov AV, Krylov AS. Methodical approaches to annotation and labeling of histological images in order to automatically detect the layers of the stomach wall and the depth of invasion of gastric cancer. Russian Journal of Archive of Pathology. 2022;84(6):67‑73. (In Russ.)
https://doi.org/10.17116/patol20228406167

Подписка 2026 Архив патологии (Russian Journal of Archive of Pathology)
МСФ на ЯМ
Использование инфографики авторами научных работ
Close metadata
Recommended articles:
Microsatellite instability as a possible diagnostic marker of the gastric mucosa dysplasia. Russian Journal of Archive of Pathology. 2025;(3):5-16
Prognostic significance and comparison of methods for calculating tumor budding in gastric cancer. Russian Journal of Archive of Pathology. 2025;(3):17-25
Another sight at Gastric Cancer Mole­cular Classification: novel subtypes based on expression of CDX-2, E-cadherin, Epstein-Barr virus RNAs, MMR proteins. Russian Journal of Archive of Pathology. 2025;(3):49-61
Total gastrectomy with preserving duodenal passage by double tract reco­nstruction in patients with gastric cancer. Piro­gov Russian Journal of Surgery. 2025;(6):35-43
Technical aspe­cts of lapa­roscopic formation of gastroduodenoanastomosis (Billroth-I) during distal rese­ction in patients with gastric cancer. Endo­scopic Surgery. 2025;(3):44-51
Intra-abdominal pressurized aero­sol chemotherapy after proximal gastrectomy with double-tract reco­nstruction in a patient with loca­lly adva­nced gastric cancer. P.A. Herzen Journal of Onco­logy. 2025;(3):78-82
Standards of surgical approach in combined treatment of patients with loca­lly adva­nced gastric cancer. P.A. Herzen Journal of Onco­logy. 2025;(3):100-106
Multivisceral surgeries with pancreatoduodenectomy for gastric cancer: imme­diate and long-term resu­lts. Piro­gov Russian Journal of Surgery. 2025;(8):30-38
Evaluation of the skeletal muscle index in predicting toxic complications of anti­tumor drug therapy in patients with gastric cancer. P.A. Herzen Journal of Onco­logy. 2025;(4):29-36
Design of the multicenter cohort prospective study GASTROSTAT to analyse postoperative morbidity and mortality after elective radi­cal surgery for gastric cancer. Endo­scopic Surgery. 2025;(4):5-12
Abstract:

OBJECTIVE

Development of original methodological approaches to annotation and labeling of histological images in relation to the problem of automatic segmentation of the layers of the stomach wall.

MATERIAL AND METHODS

Three image collections were used in the study: NCT-CRC-HE-100K, CRC-VAL-HE-7K, and part of the PATH-DT-MSU collection. The used part of the original PATH-DT-MSU collection contains 20 histological images obtained using a high performance digital scanning microscope.

Each image is a fragment of the stomach wall, cut from the surgical material of gastric cancer and stained with hematoxylin and eosin. Images were obtained using a scanning microscope Leica Aperio AT2 (Leica Microsystems Inc., Germany), annotations were made using Aperio ImageScope 12.3.3 (Leica Microsystems Inc., Germany).

RESULTS

A labeling system is proposed that includes 5 classes (tissue types): areas of gastric adenocarcinoma (TUM), unchanged areas of the lamina propria (LP), unchanged areas of the muscular lamina of the mucosa (MM), a class of underlying tissues (AT), including areas of the submucosa, own muscular layer of the stomach and subserous sections, image background (BG). The advantage of this marking technique is to ensure high efficiency of recognition of the muscularis lamina (MM) — a natural «line» separating the lamina propria of the mucous membrane and all other underlying layers of the stomach wall. The disadvantages of the technique include a small number of classes, which leads to insufficient detailing of automatic segmentation.

CONCLUSION

In the course of the study, an original technique for labeling and annotating images was developed, including 5 classes (types of tissues). This technique is effective at the initial stages of teaching mathematical algorithms for the classification and segmentation of histological images. Further stages in the development of a real diagnostic algorithm to automatically determine the depth of invasion of gastric cancer require the correction and development of the presented method of marking and annotation.

Keywords:

whole-slide images
image annotation
neural networks
digital pathology
gastric cancer

Authors:

Mikhailov I.A.

Lomonosov Moscow State University

Khvostikov A.V.

Lomonosov Moscow State University

Krylov A.S.

Lomonosov Moscow State University

Received:

15.09.2022

Accepted:

22.09.2022

Close metadata

References:

  1. Komura D, Ishikawa S. Machine learning methods for histopathological image analysis. Comput Struct Biotechnol J. 2018;16:34-42.  https://doi.org/10.1016/j.csbj.2018.01.001
  2. Kainz P, Pfeiffer M, Urschler M. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization. PeerJ. 2017;5:e3874. https://doi.org/10.7717/peerj.3874
  3. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211-252.  https://doi.org/10.1007/s11263-015-0816-y
  4. Doyle S, Monaco J, Feldman M, Tomaszewski J, Madabhushi A. An active learning based classification strategy for the minority class problem: application to histopathology annotation. BMC Bioinformatics. 2011;12:424.  https://doi.org/10.1186/1471-2105-12-424
  5. Haixiang G, Li Y, Shang J, Mingyun G, Yuanyue H, Gong B. Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl. 2016;73:220-39.  https://doi.org/10.1016/j.eswa.2016.12.035
  6. Marée R, Rollus L, Stévens B, Hoyoux R, Louppe G, Vandaele R, Begon JM, Kainz P, Geurts P, Wehenkel L. Collaborative analysis of multi-gigapixel imaging data using Cytomine. Bioinformatics. 2016;32(9):1395-401.  https://doi.org/10.1093/bioinformatics/btw013
  7. Nalisnik M, Amgad M, Lee S, Halani SH, Velazquez Vega JE, Brat DJ, Gutman DA, Cooper LAD. Interactive phenotyping of large-scale histology imaging data with HistomicsML. Sci Rep. 2017;7(1):14588. https://doi.org/10.1038/s41598-017-15092-3
  8. Brunye TT, Carney PA, Allison KH, Shapiro LG, Weaver DL, Elmore JG. Eye movements as an index of pathologist visual expertise: a pilot study. PLoS One. 2014;9(8):e103447. https://doi.org/10.1371/journal.pone.0103447
  9. Raghunath V, Braxton MO, Gagnon SA, Brunyé TT, Allison KH, Reisch LM, Weaver DL, Elmore JG, Shapiro LG. Mouse cursor movement and eye tracking data as an indicator of pathologists’ attention when viewing digital whole slide images. J Pathol Inform. 2012;3(1):43.  https://doi.org/10.4103/2153-3539.104905
  10. Mercan E, Aksoy S, Shapiro LG, Weaver DL, Brunyé TT, Elmore JG. Localization of diagnostically relevant regions of interest in whole slide images: a comparative study. J Digit Imaging. 2016;29(4):496-506.  https://doi.org/10.1007/s10278-016-9873-1
  11. Padmanabhan RK, Somasundar VH, Griffith SD, Zhu J, Samoyedny D, Tan KS, Hu J, Liao X, Carin L, Yoon SS, et al. An active learning approach for rapid characterization of endothelial cells in human tumors. PLoS One. 2014;9(3):e90495. https://doi.org/10.1371/journal.pone.0090495
  12. Zhu Y, Zhang S, Liu W, Metaxas DN. Scalable histopathological image analysis via active learning. In: Golland P, Hata N, Barillot C, Hornegger J, Howe R, eds. Medical image computing and computer-assisted intervention — MICCAI 2014. Lecture Notes in Computer Science. Springer, Cham; 2014;8675:369-376.  https://doi.org/10.1007/978-3-319-10443-0_47
  13. Xu Y, Zhu JY, Chang EI, Lai M, Tu Z. Weakly supervised histopathology cancer image segmentation and classification. Med Image Anal. 2014;18(3):591-604.  https://doi.org/10.1016/j.media.2014.01.010
  14. Tong S, Koller D. Support vector machine active learning with applications to text classification. J Mach Learn Res. 2001;2:45-66.  https://doi.org/10.1162/153244302760185243
  15. Lewis DD. A sequential algorithm for training text classifiers: corrigendum and additional data. Acm Sigir Forum. 1995;29(2):13-19.  https://doi.org/10.1145/219587.219592
  16. Macenko M, Niethammer M, Marron JS, Borland D, Woosley JT, Guan X, Schmitt C, Thomas NE. A method for normalizing histology slides for quantitative analysis. 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. 2009;1107-1110. https://doi.org/10.1109/ISBI.2009.5193250
  17. Huang G, Liu Z, Van Der Maaten, Weinberger K.Q. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017;2261-2269. https://doi.org/10.1109/CVPR.2017.243
  18. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;770-778.  https://doi.org/10.1109/CVPR.2016.90
  19. Huang G, Liu Z, Weinberger K.Q. Densely connected convolutional networks. arXiv. 2016;2:12.  https://doi.org/10.48550/arXiv.1608.06993
  20. Khvostikov AV, Krylov AS, Mikhailov IA, Malkov PG. Visualization of whole slide histological images with automatic tissue type recognition. Pattern Recognit Image Anal. 2022;32:483-488.  https://doi.org/10.1134/S1054661822030208
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

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.