КОНФЕРЕНЦІЇ ВНТУ електронні наукові видання, 
Міжнародна науково-технічна конференція з оптико-електронних інформаційних технологій "ФОТОНІКА − ODS 2025"

Розмір шрифта: 
INTELLIGENT SYSTEM FOR DETERMINING THE DEGREE OF STENOSIS IN PATIENTS WITH CORONARY ARTERY DISEASE
Синєглазов Віктор Михайлович, Михайло Русланович Головацький

Остання редакція: 2025-04-09

Анотація


The paper presents an intelligence-based approach for detecting and grading coronary stenosis in ischemic heart disease, combining coronary artery segmentation, stenosis segmentation, and multi-class classification of lesion severity within a unified deep learning pipeline. A U-Net model highlights vessels, a second U-Net model isolates narrowing, and a ResNet classifier assigns stenosis degrees. Semi-supervised principles reduce the need for extensive annotations, gradually refining pseudo-labels for higher accuracy.

Ключові слова


coronary artery disease;stenosis;deep learning;classification

Посилання


[1]Taras Hutsul, Vladyslav Tkach and Mykola Khobzei, Humanitarian demining: How can UAVs and Internet of Things help? Security and Infocommunicatiom Systems and Internet of Things, vol.1, No.2, 2023, pp.1–6. https://doi.org/10.31861/sisiot2023.2.02004 [2]Sineglazov, V.M., Ischenko, V.P. Integrated navigation complex of UAV on basis of flight controller. 2015 IEEE 3rd International Conference Actual Problems of Unmanned Aerial Vehicles Developments, APUAVD 2015 - Proceedings, pp. 20–25, 7346547, 2015. https://doi.org/10.1109/APUAVD.2015.7346547 [3]Sineglazov, V.M. Computer aided-design problems of unmanned aerial vehicles integrated navigation complexes. 2014 IEEE 3rd International Conference on Methods and Systems of Navigation and Motion Control, MSNMC 2014  Proceedings, pp. 9–14, 6979716, 2014. https://doi.org/10.1109/MSNMC.2014.6979716 [4]Sineglazov, V., Kot, A. Design of Hybrid Neural Networks of the Ensemble Structure. Eastern-European Journal of Enterprise Technologies, 1, pp. 31–45, 2021. https://doi.org/10.15587/1729-4061.2021.225301 [5]Ma, X.; Wang, H.; Wang, J. Semisupervised Classification for Hyperspectral Image Based on Multi-Decision Labeling and Deep Feature Learning. J. Photogram. Remote Sens. 2016, 120, pp. 99–107. https://doi.org/10.1016/j.isprsjprs.2016.09.001 [6]Duan, P., Kang, X., Li, S., Benediktsson, J.A. Multi-Scale Structure Extraction for Hyperspectral Image Classification. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Valencia, Spain, 22-27 July 2018, pp. 5724–5727. https://doi.org/10.1109/IGARSS.2018.8519425 [7]Senthilnath, J.; Kulkarni, S.; Benediktsson, J.A.; Yang, X.S. A Novel Approach for Multispectral Satellite Image Classification Based on the Bat Algorithm. IEEE Geosci. Remote Sens. Lett. 2016, 13, pp. 599–603. https://doi.org/10.1109/LGRS.2016.2530724 [8]Yue Wu,, Guifeng Mu, Can Qin, Qiguang Miao, Wenping Ma, Xiangrong Zhang. Semi-Supervised Hyperspectral Image Classification via Spatial-Regulated Self-Training. Remote Sens. 2020, 12, 159, pp. 1–20. https://doi.org/10.3390/rs12010159 [9]Hao, W., & Prasad, S. (2017). Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Transactions on Image Processing, (99), 1. [10]He, X. (2021). Weakly supervised classification of hyperspectral image based on complementary learning. Remote Sensing, 13(24), 5009. https://doi.org/10.3390/rs13245009 [11]Song, L., Feng, Z., Yang, S., et al. (2022). Self-supervised assisted semi-supervised residual network for hyperspectral image classification. Remote Sensing, 14(13), 2997. https://doi.org/10.3390/rs14132997 [12]Zheng, X., Jia, J., Chen, J., et al. (2022). Hyperspectral image classification with imbalanced data based on semi-supervised learning. Applied Sciences, 12(8), 3943. https://doi.org/10.3390/app12083943 [13]K. Tan, E. Li, D. Qian, An efficient semi-supervised classification approach for hyperspectral imagery, ISPRS J. Photogramm. Remote Sens., 97, (2014), pp. 36–45. https://doi.org/10.1016/j.isprsjprs.2014.08.003 [14]S. Zhou, Z. Xue, P. Du, Semisupervised stacked autoencoder with cotraining for hyperspectral image classification, IEEE Trans. Geosci. Remote Sensi., 57, (2019), pp. 3813–3826. https://doi.org/10.1109/TGRS.2018.2888485 [15]K. Lee, J. Shin, Y.-H. Lee, J. Ku and H.-W. Kim, SSASS: Semi-Supervised Approach for Stenosis Segmentation, arXiv preprint arXiv:2311.10281v1, 2023, https://arxiv.org/abs/2311.10281 

[1]  Taras Hutsul, Vladyslav Tkach and Mykola Khobzei, Humanitarian demining: How can UAVs and Internet of Things help? Security and Infocommunicatiom Systems and Internet of Things, vol.1, No.2, 2023, pp.1–6. https://doi.org/10.31861/sisiot2023.2.02004

[2]  Sineglazov, V.M., Ischenko, V.P.Integrated navigation complex of UAV on basis of flight controller. 2015 IEEE 3rd International Conference Actual Problems of Unmanned Aerial Vehicles Developments, APUAVD 2015 - Proceedings, pp. 20–25, 7346547, 2015.https://doi.org/10.1109/APUAVD.2015.7346547

[3]  Sineglazov, V.M. Computer aided-design problems of unmanned aerial vehicles integrated navigation complexes. 2014 IEEE 3rd International Conference on Methods and Systems of Navigation and Motion Control, MSNMC 2014  Proceedings, pp. 9–14, 6979716, 2014.https://doi.org/10.1109/MSNMC.2014.6979716

[4]  Sineglazov, V., Kot, A. Design of Hybrid Neural Networks of the Ensemble Structure. Eastern-European Journal of Enterprise Technologies, 1, pp. 31–45, 2021.https://doi.org/10.15587/1729-4061.2021.225301

[5]  Ma, X.; Wang, H.; Wang, J. Semisupervised Classification for Hyperspectral Image Based on Multi-DecisionLabeling and Deep Feature Learning. J. Photogram. Remote Sens. 2016, 120, pp. 99–107. https://doi.org/10.1016/j.isprsjprs.2016.09.001

[6]  Duan, P., Kang, X., Li, S., Benediktsson, J.A. Multi-Scale Structure Extraction for Hyperspectral ImageClassification. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS),Valencia, Spain, 22-27 July 2018, pp. 5724–5727.https://doi.org/10.1109/IGARSS.2018.8519425

[7]  Senthilnath, J.; Kulkarni, S.; Benediktsson, J.A.; Yang, X.S. A Novel Approach for Multispectral Satellite ImageClassification Based on the Bat Algorithm. IEEE Geosci. Remote Sens. Lett. 2016, 13, pp. 599–603. https://doi.org/10.1109/LGRS.2016.2530724

[8]  Yue Wu,, Guifeng Mu, Can Qin, Qiguang Miao, Wenping Ma, Xiangrong Zhang. Semi-Supervised Hyperspectral Image Classification via Spatial-Regulated Self-Training. Remote Sens. 2020, 12, 159, pp. 1–20.https://doi.org/10.3390/rs12010159

[9]  Hao, W., & Prasad, S. (2017). Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Transactions on Image Processing, (99), 1.

[10]    He, X. (2021). Weakly supervised classification of hyperspectral image based on complementary learning. Remote Sensing, 13(24), 5009.https://doi.org/10.3390/rs13245009

[11]    Song, L., Feng, Z., Yang, S., et al. (2022). Self-supervised assisted semi-supervised residual network for hyperspectral image classification. Remote Sensing, 14(13), 2997.https://doi.org/10.3390/rs14132997

[12]    Zheng, X., Jia, J., Chen, J., et al. (2022). Hyperspectral image classification with imbalanced data based on semi-supervised learning. Applied Sciences, 12(8), 3943.https://doi.org/10.3390/app12083943

[13]    K. Tan, E. Li, D. Qian, An efficient semi-supervised classification approach for hyperspectral imagery, ISPRS J. Photogramm. Remote Sens., 97, (2014), pp. 36–45. https://doi.org/10.1016/j.isprsjprs.2014.08.003

[14]    S. Zhou, Z. Xue, P. Du, Semisupervised stacked autoencoder with cotraining for hyperspectral image classification, IEEE Trans. Geosci. Remote Sensi., 57, (2019), pp. 3813–3826. https://doi.org/10.1109/TGRS.2018.2888485

K. Lee, J. Shin, Y.-H. Lee, J. Ku and H.-W. Kim, SSASS: Semi-Supervised Approach for Stenosis Segmentation, arXiv preprint arXiv:2311.10281v1, 2023, https://arxiv.org/abs/2311.10281

Повний текст: PDF