CLASSIFICATION OF HISTOLOGICAL IMAGES BASED ON CONVOLUTIONAL NEURAL NETWORKS
DOI:
https://doi.org/10.15588/1607-3274-2025-4-11Keywords:
convolutional neural networks, classification, optimization, histologyAbstract
Context. Automated classification of histological images is of great importance for speeding up and improving the accuracy of
diagnostics in medicine. Taking into account the complexity and high variability of histological structures, the use of deep learning and convolutional neural networks, in particular, is a promising direction in solving this problem.
The object of study is the process of classifying histological images using convolutional neural networks to determine and optimize the architecture with the highest accuracy rate.
Objective. The aim of this work is to develop an effective approach to histological image classification using convolutional neural networks that provides high accuracy through step-by-step optimization of the architecture and application of data expansion methods using affine transformations and synthesis based on diffusion models.
Method. The study includes four main stages. The first stage involves a comparative analysis of 12 well-known convolutional neural network architectures on a basic histological dataset. The second and third stages involve comparative analysis on extended data, including affine transformations and synthetic images generated by the diffusion model, respectively. The final, fourth stage involves a neuroevolutionary search for the optimal architectural cell. Once it is found, it is integrated into the model architecture, where for each layer a choice is made between certain blocks and the found cell. This approach allows to automatically form the optimal sequence of blocks in the model, which ensures the highest classification accuracy.
Results. The proposed approach improved the accuracy of histological image classification compared to the initial architectures. The addition of synthetic images to the training set provided an increase in model performance. The search for the optimal cell and its integration into the model with further optimization demonstrated an additional improvement in classification quality, increasing the accuracy to 94.9, 96.1, and 99.8% on each dataset, respectively.
Conclusions. The proposed approach allows achieving high accuracy of histological image classification through a step-by-step process that includes the use of classical convolutional neural network architectures, generation of synthetic data, and search for optimal architectural and hyperparametric configurations. A software module for classifying histological images has been developed that can be used in an automatic diagnostic system.
References
Underwood J. C. E. More than meets the eye: the changingface of histopathology, Histopathology, 2016, Vol. 70, № 1, pp. 4–9. DOI: 10.1111/his.13047.
Schafer et al. K. A. Use of Severity Grades to Characterize Histopathologic Changes, Toxicologic Pathology, 2018, Vol. 46, № 3, pp. 256–265. DOI: 10.1177/0192623318761348.
Ho C., Rodig S. J. Immunohistochemical markers in lymphoid malignancies: Protein correlates of molecular alterations, Seminars in Diagnostic Pathology, 2015, Vol. 32, № 5, pp. 381–391. DOI: 10.1053/j.semdp.2015.02.016.
Li Z. et al. Large-scale retrieval for medical image analytics: A comprehensive review, Medical Image Analysis, 2018, Vol. 43, pp. 66–84. DOI: 10.1016/j.media.2017.09.007.
Zeiser FE. et al. Breast cancer intelligent analysis of histopathological data: A systematic review, Applied Soft Computing, 2021, Vol. 113, P. 107886. DOI: 10.1016/j.asoc.2021.107886.
Houssein E. H. et al. Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review, Expert Systems with Applications, 2020, Vol. 167, P. 114161. DOI: 10.1016/j.eswa.2020.114161.
He W. et al. A review: The detection of cancer cells in histopathology based on machine vision, Computers in Biology and Medicine, 2022, Vol. 146, P. 105636. DOI: 10.1016/j.compbiomed.2022.105636.
Komura D., Ochi M., Ishikawa S. Machine learning methods for histopathological image analysis: Updates in 2024, Computational and Structural Biotechnology Journal. – 2024, Vol. 27, pp. 383–400. DOI: 10.1016/j.csbj.2024.12.033.
Abdelsamea M. M. et al. A survey on artificial intelligence in histopathology image analysis, WIREs Data Mining and Knowledge Discovery, 2022, Vol. 12, № 6, P. e1474. DOI: 10.1002/widm.1474.
Yan T. et al. Convolutional Neural Network with Parallel Convolution Scale Attention Module and ResCBAM for Breast Histology Image Classification, Heliyon, 2024, Vol. 10, № 10, P. e30889. DOI: 10.1016/j.heliyon.2024.e30889.
Rafiq A. et al. Detection and Classification of Histopathological Breast Images Using a Fusion of CNN Frameworks, Diagnostics, 2023, Vol. 13, № 10, P. 1700. DOI: 10.3390/diagnostics13101700.
Peng C. C., Lee B. R.Enhancing colorectal cancer histological image classification using transfer learning and ResNet50 CNN Model, 2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS) : proceedings, 2023, pp. 36–40. DOI:
1109/ECBIOS57802.2023.10218590.
Srikantamurthy M. M. et al. Classification of benign and malignant subtypes of breast cancer histopathology imaging using hybrid CNN-LSTM based transfer learning, BMC Medical Imaging, 2023, Vol. 23, № 1. DOI: 10.1186/s12880-023-00964-0.
Al-Jabbar M. et al. Analyzing Histological Images Using Hybrid Techniques for Early Detection of Multi-Class Breast Cancer Based on Fusion Features of CNN and Handcrafted, Diagnostics, 2023, Vol. 13, № 10, P. 1753. DOI: 10.3390/diagnostics13101753.
Ruiz FM. et al. CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology, Frontiers in Medicine, 2023, Vol. 10. DOI: 10.3389/fmed.2023.1173616.
Ünlükal N. et al. Histological tissue classification with a novel statistical filterbased convolutional neural network, Anatomia, Histologia, Embryologia, 2024, Vol. 53, № 4. DOI: 10.1111/ahe.13073.
Dogar G. M., Shahzad M., Fraz M. M. Attention augmented distance regression and classification network for nuclei instance segmentation and type classification in histology images, Biomedical Signal Processing and Control, 2023, Vol. 79, P. 104199. DOI: 10.1016/j.bspc.2022.104199.
Xiao S. et al. A scale and region-enhanced decoding network for nuclei classification in histology image, Biomedical Signal Processing and Control, 2023, Vol. 83, P. 104626. DOI: 10.1016/j.bspc.2023.104626.
Carreras J. Celiac Disease Deep Learning Image Classification Using Convolutional Neural Networks / J. Carreras // Journal of Imaging. – 2024. – Vol. 10, № 8. – P. 200. – DOI: 10.3390/jimaging10080200.
Chandana Mani R. K., Kamalakannan J. The Comparative Study of CNN models for Breast Histopathological Image Classification, 2023 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, 23–25 January 2023 : proceedings, 2023. DOI: 10.1109/iccci56745.2023.10128352.
Weber A. et al. AI-Based Detection of Oral Squamous Cell Carcinoma with Raman Histology, Cancers, 2024, Vol. 16, № 4, P. 689. DOI: 10.3390/cancers16040689.
Shimizu T. et al. A trial deep learning-based model for fourclass histologic classification of colonic tumor from narrow band imaging, Scientific Reports, 2023, Vol. 13, № 1. DOI: 10.1038/s41598-023-34750-3.
Karthikeyan A., Jothilakshmi S., Suthir S. Colorectal cancer detection based on convolutional neural networks (CNN) and ranking algorithm, Measurement: Sensors, 2024, Vol. 31, P. 100976. DOI: 10.1016/j.measen.2023.100976.
Amin M. S., Ahn H. FabNet: A Features AgglomerationBased Convolutional Neural Network for Multiscale Breast Cancer Histopathology Images Classification, Cancers, 2023, Vol. 15, № 4, P. 1013. DOI: 10.3390/cancers15041013.
Sawant D., Kundale J., Varma P. Hybrid Deep Learning based Multi-Classification of Breast Cancer Approach using Histology Images, 2024 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT), Gharuan, India, 2–3 May 2024 : proceedings, 2024. DOI: 10.1109/incacct61598.2024.10551068.
Sreelekshmi V., Pavithran K., Jyothisha J. Nair SwinCNN: An Integrated Swin Trasformer and CNN for Improved Breast Cancer Grade Classification, IEEE Access, 2024, Vol. 12, P. 1. DOI: 10.1109/access.2024.3397667.
Kanadath A., Jothi J. A. A., Urolagin S. CViTS-Net: A CNN-ViT Network with Skip Connections for Histopathology Image Classification, IEEE Access, 2024, Vol. 12, P. 1. DOI: 10.1109/access.2024.3448302.
Muniasamy A. et al. Lung cancer histopathology image classification using transfer learning with convolution neural network model, Technology and Health Care, 2023, Vol. 32, № 2, pp. 1–12. DOI: 10.3233/thc-231029.
Kousalya K., Saranya T. Improved the detection and classification of breast cancer using hyper parameter tuning, Materials Today: Proceedings, 2021, Vol. 81. DOI: 10.1016/j.matpr.2021.03.707.
Kanimozhi S., Priyadarsini S. Breast Cancer Histopathological Image Classification Using CNN and VGG-19, 2024 Third International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Krishnankoil, Virudhunagar distric. Tamil Nadu, India, 14–16 March 2024 : proceedings, 2024. DOI: 10.1109/incos59338.2024.10527543.
Chanchal A. K. et al. Classification and grade prediction of kidney cancer histological images using deep learning [Electronic resource], Multimedia Tools and Applications, 2024, Vol. 83, pp. 78247–78267. DOI: 10.1007/s11042-024- 18639-5.
Simonyan E. O., Badejo J. A., Weijin J. S. Histopathological breast cancer classification using CNN, Materials Today: Proceedings, 2023, Vol. 105, pp. 268–275. DOI: 10.1016/j.matpr.2023.10.154.
Berezsky O. et al. Synthesis of Convolutional Neural Network architectures for biomedical image classification, Biomedical Signal Processing and Control, 2024, Vol. 95, P. 106325. DOI: 10.1016/j.bspc.2024.106325.
Real E. et al. Regularized evolution for image classifier architecture search, Proceedings of the AAAI Conference on Artificial Intelligence : proceedings, 2019, pp. 4780–4789. DOI: 10.48550/arXiv.1802.01548.
Berezsky O. M., Liashchynskyi P. B. Method of generativeadversarial networks searching architectures for biomedical images synthesis, Radio Electronics, Computer Science, Control, 2024, № 1, P. 104. DOI: 10.15588/1607-3274- 2024-1-10.
Radosavovic I. et al. Designing Network Design Spaces, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : proceedings, 2020. DOI: 10.48550/arXiv.2003.13678.
Berezsky O. M., Liashchynskyi P. B. Development of the architecture of a computer aided diagnosis system in medicine, Applied Aspects of Information Technology, 2024, Vol. 7, № 4, P. 359–369. DOI: 10.15276/aait.07.2024.25.
Berezsky O. M., Pitsun O. Y. Evaluation methods of image segmentation quality, Radio Electronics, Computer Science,Control, 2018, № 1, pp. 119–128. DOI: 10.15588/1607- 3274-2018-1-14.
[Berezsky O. M., Liashchynskyi P. B. et al. Deep networkbased method and software for small sample biomedical image generation and classification, Radio Electronics, Computer Science, Control, 2024, № 4, P. 76. DOI: 10.15588/1607-3274-2023-4-8.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 P. B. Liashchynskyi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
