Features of Intelligent Processing of Cytological Whole Slide Images
Abstract
The purpose of this work is to study the features of intelligent processing of full-slide cytological images using the example of working with cytological images of a thyroid puncture (thyroid gland) measuring 3-5 GB each. To do this, based on the analysis of scientific publications and the described approaches to the intelligent analysis of cytological images, specific actions for processing large images were identified. An approach using computer vision has been developed for multi-class categorization of images of thyroid cytological slides using the international Bethesda system and the selection of informative features that influence the categorization process, as well as training and testing of models. The target metrics for comparing the effectiveness of models were chosen for segmentation: Intersection over Union, Dice coefficient; for classification: accuracy, precision, recall, f1-score. The result of the work was the practical implementation of an approach to processing and intelligent analysis of cytological images of the thyroid gland using computer vision.
Full Text:
PDF (Russian)References
Haugen BR, Alexander EK, Bible KC, et al. 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid. 2016;26(1):1-133. doi: https://doi.org/10.1089/thy.2015.0020
Vanushko, V.E. Thyroid Nodules — Not Always Pathology. InfoMedFarm Dialogue, 2022 [Internet source]. — Access mode: https://imfd.ru/2022/03/15/yzlishitzelez/, free — (18.05.2024).
Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L. European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS. Eur Thyroid J. 2017. doi: https://doi.org/10.1159/000478927
Durante C, Hegedüs L, Czarniecka A, et al. 2023 European Thyroid Association Clinical Practice Guidelines for thyroid nodule management. Eur Thyroid J. 2023;12(5). doi: https://doi.org/10.1530/ETJ-23-0067
The Bethesda System for Reporting Thyroid Cytopathology.; 2023. doi: 10.1007/978-3-031-28046-7.
Maleki S, Zandvakili A, Gera S, Khutti SD, Gersten A, Khader SN. Differentiating noninvasive follicular thyroid neoplasm with papillary-like nuclear features from classic papillary thyroid carcinoma: analysis of cytomorphologic descriptions using a novel machine-learning approach. J Pathol Inform. 2019;10:29. [PMCID: PMC6767786] [PubMed: 31579155
Sanyal P, Mukherjee T, Barui S, Das A, Gangopadhyay P. Artificial intelligence in cytopathology: a neural network to identify papillary carcinoma on thyroid fine-needle aspiration cytology smears. J Pathol Inform. 2018;9:43. [PMCID: PMC6289006] [PubMed: 30607310]
Guan Q, Wang Y, Ping B, Li D, Du J, Qin Y, et al. Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study. J Cancer. 2019;10((20)):4876–82. [PMCID: PMC6775529] [PubMed: 31598159]
Elliott Range DD, Dov D, Kovalsky SZ, Henao R, Carin L, Cohen J. Application of a machine learning algorithm to predict malignancy in thyroid cytopathology. Cancer Cytopathol. 2020 Apr;128((4)):287–95. [PubMed: 32012493]
Brie Kezlarian, Oscar Lin Artificial Intelligence in Thyroid Fine Needle Aspiration Biopsies. Acta Cytol. 2021 Aug; 65(4): 324–329. Published online 2020 Dec 16. doi: 10.1159/000512097: 10.1159/000512097
I. Lozhkin,1, K. Tsyguleva, K. Zaytsev et al. Development of Neural Network Models for Obtaining Information About Nodular Neoplasms of the Thyroid Gland Based on Ultrasound Images. Journal of Theoretical and Applied Information Technology. 2023. Vol.101. No 15. P. 6076-6091.
P. Bankhead, et al. QuPath: Open source software for digital evelopment image analysis. Scientific Reports. 2017.
QuPath [Электронный ресурс]. — Режим доступа: https://qupath.github.io/, свободный — (18.05.2024).
Digital Pathology [Электронный ресурс]. — Режим доступа: https://dpathology.ru/, свободный — (18.05.2024).
Aperio Digital Pathology Software [Электронный ресурс]. — Режим доступа: https://www.leicabiosystems.com/digital-pathology/manage/, свободный — (18.05.2024).
Lozhkin, I.A., Mironov, A.M., Pavlov, D.V., Dunaev, M.E., Zaitsev, K.S. Digital Transformation of Complex Image Analysis Using Computer Vision in the Diagnosis of Thyroid Diseases // Digital Transformation of Social and Economic Systems: Proceedings of the International Scientific and Practical Conference. 2023. P. 243-250.
Lozhkin, I.A., Mironov, A.M., Dunaev, M.E., Zaitsev, K.S. Features of Processing Thyroid Cytology Images Using Computer Vision // Electronic Devices and Control Systems: Proceedings of the XIX International Scientific and Practical Conference. 2023. Part 2. P. 305-306.
I. Lozhkin, A. Mironov, A. Garmash. Features of Intelligent Analysis of Ultrasound and Cytological Studies of the Thyroid Gland // Physics, Engineering and Technologies for Biomedicine. The 8th International Symposium and Schools for Young Scientists November 11-15, 2023: Program. Book of Abstracts. 2023. P. 60-61.
B. Smith, et al. Developing Image Analysis Pipelines for Whole-Slide Images: Pre-and Post-Processing // Journal of Clinical and Translational Science. 2021. Vol. 5, No. 1. P. 1-11.
CVAT. Open Data Annotation Platform [Internet source]. — Access mode: https://www.cvat.ai/, free — (18.05.2024).
A. Kirillov, E. Mintun, N. Ravi, et al. Segment Anything // Computer Vision and Pattern Recognition. 2023.
Metrics to Evaluate Your Semantic Segmentation Model // Medium [Internet source]. — Access mode: https://towardsdatascience.com/metrics-to-evaluate-your-semantic-segmentation-model-6bcb99639aa2, free — (18.05.2024).
Classification and Regression Metrics // Yandex Education [Internet source]. — Access mode: https://education.yandex.ru/handbook/ml/article/metriki-klassifikacii-i-regressii, free — (18.05.2024).
L.-C. Chen, Y. Zhu, G. Papandreou, et al. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation // Computer Vision and Pattern Recognition. 2018.
M. Tan, Q.V. Le. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks // International Conference on Machine Learning. 2019.
K. He, X. Zhang, S. Ren, J. Sun. Deep Residual Learning for Image Recognition // Computer Vision and Pattern Recognition. 2015.
M. Lu, D. Williamson, T. Chen, et al. Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images // Electrical Engineering and Systems Science. Image and Video Processing. 2020.
CLAM [Internet source]. — Access mode: https://github.com/mahmoodlab/CLAM, free — (18.05.2024).
WSI-finetuning [Internet source]. — Access mode: https://github.com/invoker-LL/WSI-finetuning, free — (18.05.2024).
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность MoNeTec 2024
ISSN: 2307-8162