Архив номеров
Медицинская Техника / Медицинская техника №6, 2019 / с. 50-55

Использование нейронных сетей в системах визуального ассистирования имплантации транскатетерного протеза клапана аорты

Н.А. Гейдаров, К.Ю. Клышников, Е.А. Овчаренко


Аннотация

Анализируется современное состояние подходов к анализу медицинских данных, получаемых в результате ангиографического исследования в рамках различных вмешательств на сосудистом русле человека. Рассмотрены основные подходы: image- based алгоритмы, алгоритмы машинного обучения и глубокое обучение нейросетей, как с позиции отдельных научных исследований, так и с прикладной точки зрения – с позиции создания систем визуального ассистирования медицинских процедур. Кроме того, представлен собственный взгляд авторов на перспективы и потенциальные решения трудностей при создании подобных комплексов для сердечно-сосудистой хирургии, в частности процедуры транскатетерного протезирования клапана аорты.


Вернуться к содержанию

Сведения об авторах

Назим Абульфат-оглы Гейдаров, канд. физ.-мат. наук, ст. преподаватель, математический факультет, ФГБОУ ВО «Кемеровский государственный университет»,
Кирилл Юрьевич Клышников, научный сотрудник,
Евгений Андреевич Овчаренко, канд. техн. наук, зав. лабораторией, лаборатория новых биоматериалов, ФГБНУ «Научно-исследовательский институт комплексных проблем сердечно-сосудистых заболеваний», г. Кемерово,

Список литературы

1. Barbanti M. et al. Transcatheter aortic valve implantation in 2017: State of the art // EuroIntervention. 2017. Vol. 24. № 13 (AA). PP. AA11-AA21.
2. Hecker F. et al. Transcatheter aortic valve implantation (TAVI) in 2018: Recent advances and future development // Minerva Cardioangiol. 2018. № 66. PP. 314-328.
3. Nguyen D.L. et al. Intraoperative tracking of aortic valve plane / 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Osaka. Piscataway. 2013. PP. 4378-4381.
4. Yan T.D. et al. Transcatheter Aortic Valve Implantation for High-Risk Patients with Severe Aortic Stenosis: A Systematic Review // The Journal of Thoracic and Cardiovascular Surgery. 2010. Vol. 139. № 6. PP. 1519-1528.
5. Hennemuth A. et al. One-click coronary tree segmentation in CT angiographic images / International Congress Series. Berlin. Elsevier. 2005. Vol. 1281. PP. 317-321.
6. Tek H. et al. Automatic coronary tree modeling // Princeton. The Insight Journal. 2008. PP. 1-8.
7. Merk D.R. et al. Image-guided transapical aortic valve implantation: Sensorless tracking of stenotic valve landmarks in live fluoroscopic images // Innovations (Phila). 2011. Vol. 6. № 4. PP. 231-236.
8. Karar M.E. et al. A simple and accurate method for computer- aided transapical aortic valve replacement // Comput. Med. Imaging. Graph. 2016. № 50. PP. 31-41.
9. Zheng Y. et al. Automatic aorta segmentation and valve landmark detection in C-arm CT: Application to aortic valve implantation // Med. Image Comput. Assist. Interv. 2010. Vol. 13 (Pt. 1). PP. 476-483.
10. Zheng Y. et al. Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features // IEEE Trans. Med. Imaging. 2008. Vol. 27. № 11. PP. 1668-1681.
11. Zheng Y. et al. Automatic aorta segmentation and valve landmark detection in C-arm CT for transcatheter aortic valve implantation // IEEE Trans. Med. Imaging. 2012. Vol. 31. № 12. PP. 2307-2321.
12. Al W.A. et al. Automatic aortic valve landmark localization in coronary CT angiography using colonial walk // PLoS ONE. 2018. Vol. 13. № 7. P. e0200317.
13. Stern D. et al. From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization / Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. Athens. Springer International Publishing. 2016. PP. 221-229.
14. Ng A. Deep Learning. / http://cs229.stanford.edu/materials/ CS229-DeepLearning.pdf (дата обращения: 15.01.2019).
15. Chawla N.V. et al. SMOTE: Synthetic Minority Over-sampling Technique // Journal of Artificial Intelligence Research. 2002. № 16. PP. 321-357.
16. Ramentol E. et al. SMOTE-RSB*: A Hybrid Preprocessing Approach based on Oversampling and Undersampling for High Imbalanced Data-Sets Using SMOTE and Rough Sets Theory // Knowledge and Information Systems. 2012. Vol. 33. № 2. PP. 245-265.
17. Sun A. et al. On strategies for imbalanced text classification using SVM: A comparative study // Decision Support Systems. 2009. Vol. 48. № 1. PP. 191-201.
18. Yang P. et al. A particle swarm based hybrid system for imbalanced medical data sampling // BMC Genomics. 2009. № 10. Suppl. 3. P. S34.
19. Ma H., Ambrosini P., Walsum T.V. Fast Prospective Detection of Contrast Inflow in X-ray Angiograms with Convolutional Neural Network and Recurrent Neural Network. Lecture Notes / Computer Science Medical Image Computing and Computer- Assisted Intervention – MICCAI 2017. Quebec City. Springer International Publishing. 2017. PP. 453-461.
20. Julia M.H. et al. CNN-based Landmark Detection in Cardiac CTA Scans / 1st Conference on Medical Imaging with Deep Learning (MIDL 2018). Amsterdam. CoRR. 2018. Abs/1804.04963.
21. Zhang J. et al. Detecting Anatomical Landmarks from Limited Medical Imaging Data Using Two-Stage Task-Oriented Deep Neural Networks // IEEE Transactions on Image Processing. 2017. Vol. 26. № 10. PP. 4753-4764.
22. Zheng Y. et al. 3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data. Lecture Notes / Computer Science Medical Image Computing and Computer- Assisted Intervention – MICCAI 2015. Munich. Springer International Publishing. 2015. PP. 565-572.
23. Kang E. Cycle-consistent adversarial denoising network for multiphase coronary CT angiography // Medical Physics. 2018. Epub ahead of print.
24. Xia Y. et al. Context region discovery for automatic motion compensation in fluoroscopy // International Journal of Computer Assisted Radiology and Surgery. 2016. Vol. 11. № 6. PP. 977-985.
25. Wang P. et al. Catheter tracking via online learning for dynamic motion compensation in transcatheter aortic valve implantation // Medical Image Computing and Computer-Assisted Intervention. 2012. № 15 (Pt. 2). PP. 17-24.
26. Kalal Z. et al. Tracking-Learning-Detection // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. Vol. 34. № 7. PP. 1409-1422.
27. John M. et al. System to Guide Transcatheter Aortic Valve Implantations Based on Interventional C-Arm CT Imaging / Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010. Lecture Notes in Computer Science. Beijing. Springer International Publishing. 2010. PP. 375-382.
28. Liao R. et al. Automatic and efficient contrast-based 2-D/3-D fusion for trans-catheter aortic valve implantation (TAVI) // Computerized Medical Imaging and Graphics. 2013. Vol. 37. № 2. PP. 150-161.
29. Franke S. et al. A surgical assistance system for transcatheter aortic valve implantation based on a magic lens concept / Proc. of Jahrestagung der Gesellschaft fьr computer- und robotergestьtzte Chirurgie (CURAC). Innsbruck. Univ. Prof. Dr. Mag. Wolfgang Freysinger. 2013. PP. 165-168.
30. Queiros S. et al. MITT: Medical Image Tracking Toolbox // IEEE Transactions on Medical Imaging. 2018. Vol. 37. № 11. PP. 2547-2557.
31. Rippela R.A. et al. The use of robotic endovascular catheters in the facilitationof transcatheter aortic valve implantation // Eur. J. Cardiothorac. Surg. 2014. Vol. 45. № 5. PP. 836-841.
32. Mahmud E. et al. First-in-Human Robotic Percutaneous Coronary Intervention for Unprotected Left Main Stenosis // Catheter. Cardiovasc. Interv. 2016. Vol. 11. № 2. PP. 12-18.
33. Mazomenos E.B. et al. Catheter manipulation analysis for objective performance and technical skills assessment in transcatheter aortic valve implantation // Int. J. Comput. Assist. Radiol. Surg. 2016. Vol. 11 (6). PP. 1121-1131.