KOMPYUTER TOMOGRAFIYASI TASVIRLARI ASOSIDA OʻPKA PATOLOGIYALARINI AVTOMATIK TASHXISLASH UCHUN GIBRID CNN ARXITEKTURASI: MS-AttUNet MODELI
Keywords:
kompyuter tomografiyasi, sun'iy intellekt, chuqur oʻqitish, konvolyutsion neyron tarmoqlar, U-Net, ResNet, attention mexanizmi, multi-scale feature extraction, segmentatsiya, tibbiy tasvirlarni qayta ishlash.Abstract
Maqolada kompyuter tomografiyasi (KT) tasvirlari asosida oʻpka kasalliklarini avtomatik tashxislash uchun yangi gibrid konvolyutsion neyron tarmoq arxitekturasi — MS-AttUNet (Multi-Scale Attention U-Net) taklif etiladi. Model U-Net segmentatsiya, ResNet 50 klassifikatsiya bloklari, MultiScale Feature Extraction (MSFE) moduli va Convolutional Block Attention Module (CBAM) attention mexanizmini birlashtiradi. Tadqiqot LIDC-IDRI, MosMedData, COVID-19 CT va mahalliy ma'lumotlar bazalaridan toʻplangan 2 398 ta bemorning 380 000 ta KT kesim tasvirida olib borildi. Test toʻplamida model 96,4% aniqlik, 94,7% sezgirlik, 97,1% maxsuslik va 0,974 AUC-ROC koʻrsatkichlariga erishdi va mavjud zamonaviy yondashuvlardan 2,6–8,1% ga ustun keldi. Natijalar asosida CT-DiagAI nomli web-asoslangan dasturiy vosita ishlab chiqildi.
References
1. Hsieh J. Computed Tomography: Principles, Design, Artifacts, and Recent
Advances. — 3rd ed. — Bellingham: SPIE Press, 2015. — 666 p.
2. Goldman L.W. Principles of CT and CT technology // Journal of Nuclear
Medicine Technology. — 2007. — Vol. 35, No. 3. — P. 115–128.
3. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for
biomedical image segmentation // Medical Image Computing and ComputerAssisted Intervention (MICCAI). — 2015. — Vol. 9351. — P. 234–241.
4. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition //
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). —
2016. — P. 770–778.
5. Wang S., Kang B., Ma J., et al. A deep learning algorithm using CT images to
screen for COVID-19 // European Radiology. — 2021. — Vol. 31. — P. 6096–
6104.
6. Brady A.P. Error and discrepancy in radiology: inevitable or avoidable? //
Insights into Imaging. — 2017. — Vol. 8, No. 1. — P. 171–182.
7. Litjens G., Kooi T., Bejnordi B.E., et al. A survey on deep learning in medical
image analysis // Medical Image Analysis. — 2017. — Vol. 42. — P. 60–88.
8. Esteva A., Robicquet A., Ramsundar B., et al. A guide to deep learning in
healthcare // Nature Medicine. — 2019. — Vol. 25, No. 1. — P. 24–29.
9. Setio A.A.A., Traverso A., de Bel T., et al. Validation, comparison, and
combination of algorithms for automatic detection of pulmonary nodules in CT
images: The LUNA16 challenge // Medical Image Analysis. — 2017. — Vol.
42. — P. 1–13.
10. Krizhevsky A., Sutskever I., Hinton G. ImageNet classification with deep
convolutional neural networks // NeurIPS. — 2012. — Vol. 25. — P. 1097–
1105.
11. Woo S., Park J., Lee J.Y., Kweon I.S. CBAM: Convolutional Block Attention
Module // European Conference on Computer Vision (ECCV). — 2018. — P.
3–19.
12. Lin T.Y., Goyal P., Girshick R., He K., Dollár P. Focal loss for dense object
detection // IEEE International Conference on Computer Vision (ICCV). —
2017. — P. 2980–2988.
13. Huang G., Liu Z., Van Der Maaten L., Weinberger K.Q. Densely connected
convolutional networks // IEEE Conference on Computer Vision and Pattern
Recognition (CVPR). — 2017. — P. 4700–4708.
14. Tan M., Le Q. EfficientNet: Rethinking model scaling for convolutional neural
networks // International Conference on Machine Learning (ICML). — 2019.
— P. 6105–6114.
15. Milletari F., Navab N., Ahmadi S.A. V-Net: Fully convolutional neural
networks for volumetric medical image segmentation // International
Conference on 3D Vision (3DV). — 2016. — P. 565–571.
16. Selvaraju R.R., Cogswell M., Das A., et al. Grad-CAM: Visual explanations
from deep networks via gradient-based localization // IEEE International
Conference on Computer Vision (ICCV). — 2017. — P. 618–626.
17. Oʻzbekiston Respublikasi Prezidentining 2020-yil 5-oktyabrdagi PF-6079-son
«Raqamli Oʻzbekiston-2030 strategiyasini tasdiqlash toʻgʻrisida»gi Farmoni. —
Toshkent, 2020.
18. Morozov S.P., Andreychenko A.E., Pavlov N.A., et al. MosMedData: Chest
CT Scans with COVID-19 Related Findings Dataset // arXiv preprint. — 2020.
— arXiv:2005.06465.
19. Armato S.G., McLennan G., Bidaut L., et al. The Lung Image Database
Consortium (LIDC) and Image Database Resource Initiative (IDRI): A
completed reference database of lung nodules on CT scans // Medical Physics.
— 2011. — Vol. 38, No. 2. — P. 915–931.
20. Dosovitskiy A., Beyer L., Kolesnikov A., et al. An image is worth 16×16
words: Transformers for image recognition at scale // International Conference
on Learning Representations (ICLR). — 2021.