Victor Sineglazov; Kirill Ryazanovskiy; Andrew Sheruda

Intelligent Infective Endocarditis Diagnostic System Based on Echocardiography

PDF (1243KB), PP.105-120

Views: 0 Downloads: 0

Author(s)

Victor Sineglazov ^1,* Kirill Ryazanovskiy ² Andrew Sheruda ²

1. Department of Aviation Computer Integrated Complexes, National Aviation University, Kyiv, Ukraine

2. Department of Artificial Intelligence, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2024.05.08

Received: 8 May 2024 / Revised: 10 Jul. 2024 / Accepted: 22 Aug. 2024 / Published: 8 Oct. 2024

Index Terms

CNN, ViT, semantic segmentation, echocardiography, infective endocarditis, vegetation, hybrid models

Abstract

In this paper, we developed a new approach to solve the problem of infective endocarditis (IE) diagnostics based on intelligent analysis of patients’ echocardiography images. The approach is based on echocardiography segmentation results and detection of valvular anomalies (namely vegetations). In this article for the first time investigates CNNs and Visual Transformers (ViT) based segmentation methods within the framework of the vegetation segmentation task on echocardiography images. Additionally, ensemble methods for combining segmentation models using a new method of models competition for data points were proposed. Furthermore, we investigated methods for aggregating the results of the ensemble based on a new meta-model, pointwise weighted aggregation, which weighs the results of each model pixel by pixel. The last proposed step was to automatically calculate the volume of segmented vegetation to determine the degree of disease and the need for urgent surgical intervention. For the studied and proposed methods, the following ensemble segmentation accuracy was achieved on the test dataset: iou 0.7822, dice score 0.886. The proposed empirical algorithm for calculating the volume of vegetations provided the basis for further improvements of the studied approach. The results obtained indicate the great potential of the developed approaches in clinical practice.

Cite This Paper

Victor Sineglazov, Kirill Ryazanovskiy, Andrew Sheruda, "Intelligent Infective Endocarditis Diagnostic System Based on Echocardiography", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.16, No.5, pp. 105-120, 2024. DOI:10.5815/ijigsp.2024.05.08

Reference

[1]E.A. Ashley and J. Niebauer, Cardiology Explained. Explained Series. Remedica, 2004. ISBN: 9781901346220.
[2]Alberto Cresti et al., “Epidemiological and mortality trends in infective endocarditis, a 17-year population-based prospective study”. In: Cardiovascular Diagnosis and Therapy 7.1 (Feb. 2017), pp. 27–35. DOI: 10.21037/ cdt.2016.08.09.
[3]Richard Rezar et al., “Infective endocarditis – A review of current therapy and future challenges”. In: Hellenic Journal of Cardiology 62.3 (2021), pp. 190–200. ISSN: 1109-9666. DOI: 10.1016/j.hjc.2020.10.007.
[4]David Adams and Emily Forsberg, “Conducting a Cardiac Ultrasound Examination”. In: Echocardiography. Lon- don: Springer London, 2009, pp. 31–46. ISBN: 978-1-84882-293-1. DOI: 10.1007/978-1-84882-293-1_2.
[5]A Evangelista and M T Gonzalez-Alujas, “Echocardiography in infective endocarditis”. In: Heart 90.6 (2004), pp. 614–617. ISSN: 1355-6037. DOI: 10.1136/hrt.2003.029868.
[6]Zuning Ren et al., “Preoperative false-negative transthoracic echocardiographic results in native valve infective endocarditis patients: a retrospective study from 2001 to 2018”. In: Cardiovascular Ultrasound 19 (Jan. 2021). DOI: 10.1186/s12947-020-00229-8.
[7]Guillermo Cuervo et al., “Current Challenges in the Management of Infective Endocarditis”. In: Frontiers in Medicine 8 (2021). ISSN: 2296-858X. DOI: 10.3389/fmed.2021.641243.
[8]R Netzer et al., “Infective endocarditis: Determinants of long term outcome”. In: Heart (British Cardiac Society) 88 (July 2002), pp. 61–6.
[9]Y.P. Ostrovsky, F.J. Yanovsky, and H. Rohling, “Turbulence and Precipitation Classification based on Doppler- Polarimetric Radar Data”. In: 2006 International Radar Symposium. 2006, pp. 1–4. DOI: 10.1109/IRS.2006. 4338026.
[10]Oleksandr Solomentsev et al., “Substantiation of Probability Characteristics for Efficiency Analysis in the Process of Radio Equipment Diagnostics”. In: IEEE 3rd Ukraine Conference on Electrical and Computer Engineering (Aug. 2021), pp. 535–540. DOI: 10.1109/UKRCON53503.2021.9575603.
[11]Olga Shcherbyna et al., “Diagnostic Process Efficiency Analysis for Block Diagram of Electric Field Parameters Meter”. In: 2021 IEEE 12th International Conference on Electronics and Information Technologies (ELIT). 2021, pp. 5–9. DOI: 10.1109/ELIT53502.2021.9501136.
[12]Timothy Barry et al., “The Role of Artificial Intelligence in Echocardiography”. In: Journal of Imaging 9.2 (2023). ISSN: 2313-433X. DOI: 10.3390/jimaging9020050.
[13]Fei Liu et al., “Deep pyramid local attention neural network for cardiac structure segmentation in two-dimensional echocardiography”. In: Medical Image Analysis 67 (2021), p. 101873. ISSN: 1361-8415. DOI: 10. 1016/j.media.2020.101873.
[14]Amirata Ghorbani el al. “Deep learning interpretation of echocardiograms”. In: NPJ Digital Medicine 3 (Dec. 2020), p. 10. DOI: 10.1038/s41746-019-0216-8.
[15]Moomal Farhad et al., “Cardiac phase detection in echocardiography using convolutional neural networks”. In: Scientific Reports 13.1 (June 2023), p. 8908. DOI: 10.1038/s41598-023-36047-x.
[16]James Howard et al., “Improving ultrasound video classification: an evaluation of novel deep learning methods in echocardiography”. In: Journal of Medical Artificial Intelligence 3 (Mar. 2020), pp. 4–4. DOI: 10.21037/jmai. 2019.10.03.
[17]T. Shirakawa et al., “Automated heart segmentation using a convolutional neural network accelerates 3D model creation for cardiac surgery”. In: European Heart Journal - Cardiovascular Imaging 22 (Feb. 2021). DOI: 10. 1093/ehjci/jeaa356.353.
[18]Chayakrit Krittanawong et al., “Deep Learning for Echocardiography: Introduction for Clinicians and Future Vision: State-of-the-Art Review”. In: Life 13 (Apr. 2023), p. 1029. DOI: 10.3390/life13041029.
[19]L Vogel et al., “Neuronal nets and logistic regression analysis provide improved prediction of infective endocarditis compared to the modified Duke Score: a post-hoc analysis of the prospective PRO-ENDOCARDITIS study”. In: European Heart Journal - Digital Health 3 (Dec. 2022). DOI: 10.1093/ehjdh/ztac076.2776.
[20]Li Luo et al., “Machine Learning–Based Risk Model for Predicting Early Mortality After Surgery for Infective Endocarditis”. In: Journal of the American Heart Association 11 (June 2022). DOI: 10.1161/JAHA.122. 025433.
[21]V Sineglazov et al., “Intelligent tuberculosis activity assessment system based on an ensemble of neural networks”. In: Computers in biology and medicine 147 (2022), p. 105800. DOI: 10.1016/j.compbiomed.2022.105800.
[22]Felix Yanovsky et al., “Classification algorithms for weather radar”. In: 2008 12th International Conference on Mathematical Methods in Electromagnetic Theory. 2008, pp. 366–368. DOI: 10.1109/MMET.2008.4580996.
[23]Van Tho Dang and F.J. Yanovsky, “Fuzzy Detection and Classification of Dangerous Weather Phenomena Using Dual-Polarimetric Radar Measurements”. In: Proceedings of SPIE - The International Society for Optical Engi- neering 7502 (June 2009). DOI: 10.1117/12.838058.
[24]Olaf Ronneberger, Philipp Fischer, and Thomas Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation”. In: LNCS. Vol. 9351. Oct. 2015, pp. 234–241. ISBN: 978-3-319-24573-7. DOI: 10.1007/978- 3-319-24574-4_28.
[25]Liang-Chieh Chen et al., “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmenta- tion”. In: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII. Munich, Germany: Springer-Verlag, 2018, pp. 833–851. ISBN: 978-3-030-01233-5. DOI: 10.1007/978-3-030-01234-2_49.
[26]Alexey Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale”. In: International Conference on Learning Representations. 2021. DOI: 10.48550/arXiv.2010.11929.
[27]Bichen Wu et al., “Visual Transformers: Token-based Image Representation and Processing for Computer Vision”. In: CoRR abs/2006.03677 (2020). DOI: 10.48550/arXiv.2006.03677.
[28]Sixiao Zheng et al., “Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transform- ers”. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021, pp. 6877–6886. DOI: 10.1109/CVPR46437.2021.00681.
[29]Imran Ahmed et al., “Comparison of Deep-Learning-Based Segmentation Models: Using Top View Person Images”. In: IEEE Access 8 (2020), pp. 136361–136373. DOI: 10.1109/ACCESS.2020.3011406.
[30]Ashish Vaswani et al., “Attention is All you Need”. In: Advances in Neural Information Processing Systems. Ed. By I. Guyon et al. Vol. 30. Curran Associates, Inc., 2017. DOI: 10.48550/arXiv.1706.03762.
[31]Vajira Lasantha Thambawita et al., “DivergentNets:Medical Image Segmentation by Network Ensemble”. In: En- doCV@ISBI. 2021. DOI: 10.48550/arXiv.2107.00283.
[32]Dominik Muller, Inaki Soto-Rey, and Frank Kramer, “An Analysis on Ensemble Learning Optimized Medical Image Classification with Deep Convolutional Neural Networks”. In: IEEE Access 10 (2022), pp. 66467–66480. DOI: 10.48550/arXiv.2201.11440.
[33]Viktor Sineglazov and Anatoly Kot, “Design of hybrid neural networks of the ensemble structure”. In: Eastern- European Journal of Enterprise Technologies 1 (Feb. 2021), pp. 31–45. DOI: 10.15587/1729-4061.2021. 225301.
[34]Zongwei Zhou et al., “UNet++: A Nested U-Net Architecture for Medical Image Segmentation”. In: Deep Learn- ing in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer International Publishing, 2018, pp. 3–11. ISBN: 978-3-030-00889-5. DOI: 10.1007/978-3-030-00889-5_1.
[35]Enze Xie et al. “SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers”. In: CoRR (2021). DOI: 10.48550/arXiv.2105.15203.
[36]Dhruvin Gandhi, Vaishnavi Shah, and Pramila M. Chawan, “A Vision Transformer Approach for Classification an A Small-Sized Medical Image Dataset”. In: 2022 5th International Conference on Advances in Science and Technology (ICAST). 2022, pp. 519–524. DOI: 10.1109/ICAST55766.2022.10039593.
[37]Ali Hatamizadeh et al., “UNETR: Transformers for 3D Medical Image Segmentation”. In: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2022, pp. 1748–1758. DOI: 10.1109/WACV51458. 2022.00181.
[38]Rui Li et al., “Multiattention Network for Semantic Segmentation of Fine-Resolution Remote Sensing Images”. In: IEEE Transactions on Geoscience and Remote Sensing 60 (2022), pp. 1–13. DOI: 10.1109/TGRS.2021. 3093977.
[39]Garas Gendy et al., “A Deep Pyramid Attention Network for Single Image Super-resolution”. In: 2021 9th Interna- tional Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC). 2021, pp. 14–19. DOI: 10.1109/JAC-ECC54461.2021.9691443.
[40]M. Zgurovsky, V. Sineglazov, and E. Chumachenko, “Classification and Analysis of Multicriteria Optimization Methods”. In: Artificial Intelligence Systems Based on Hybrid Neural Networks. Vol. 904. Studies in Computational Intelligence. Springer, 2021. ISBN: 978-3-030-48452-1. DOI: 10.1007/978-3-030-48453-8_2.
[41]Viktor Sineglazov, Kirill Ryazanovskiy, and Olena Chumachenko, “Multicriteria conditional optimization based on genetic algorithms”. In: System research and information technologies (Dec. 2020), pp. 89–104. DOI: 10.20535/ SRIT.2308-8893.2020.3.07.
[42]Gopal Sharma et al., CSGNet: Neural Shape Parser for Constructive Solid Geometry. 2018. DOI: https://doi.org/10.48550/arXiv.1712.08290

International Journal of Image, Graphics and Signal Processing (IJIGSP)