CHAPTER


DOI :10.26650/B/T3.2024.40.006   IUP :10.26650/B/T3.2024.40.006    Full Text (PDF)

Generative Adversarial Network and Convolutional Neural Networks in Prediction of Carotid Artery Disease Prognosis

Nilgün BozbuğaMurat GezerSevinç GülseçenÇağla Canbay Sarılarİlke KeleşUfuk Alpagut

It is of great importance to ensure patient management by predicting the disease prognosis in terms of early diagnosis of chronic, progressive carotid artery diseases, implementation of treatment options, and prevention or reduction of mortality, morbidity, and complication risks in long-term follow-up. Atherosclerotic carotid artery diseases are the most important cause of stroke, and the risk of stroke increases in proportion to the degree of stenosis. The prevalence of carotid stenosis in the general population is 3%, it increases with advanced age and is more common in men than women. The gold standard treatment for symptomatic disease is carotid endarterectomy. The main goal of surgery is to minimize the risk of recurrent stroke from an unstable plaque. The role of surgery in asymptomatic disease is controversial. Therefore, it is of great importance to predict what kind of disease structure may lead to carotid artery pathologies in the future. Carotid Doppler ultrasound (DUS) and computed tomographic (CT) angiography are imaging techniques that are used to diagnose carotid artery disease. These techniques are particularly helpful in estimating the degree of stenosis. It is crucial to study the different types of vascular structure that will emerge through the modeling of existing images using a machine-learning and image-processing algorithm that supports the identification of early diagnosis from the analysis of carotid artery imaging data. It is crucial to report the results in retrospect and to investigate the aging of the vascular system in the future based on these findings and to create a prototype for a decision support application that could be used to predict the onset of prospective early detection. Convolutional neural networks (CNN) are used for classification and segmentation of images. Creating generative adversarial network (GAN) models can be shown as generating new data with similar properties from a datum. Apart from classification, the GAN method will also be used to generate synthetic data. Thus, it is aimed to produce the development of atherosclerosis synthetically as a time series, to develop the diagnostic support system from the synthetically created image, to train the GAN network, and to train the CNN model. Prognosis prediction of carotid artery diseases with GAN method, long-term follow-up and remote patient management methods to determine risk factors for the disease, to control and reduce them, to carry out regular treatment, to predict the need for urgent or urgent vascular intervention, to prevent adverse events. These methods contribute to reducing the rate and duration of hospitalization, to alleviate the great burden on the health economy due to complications in chronic diseases, and to increase the quality of life of patients. In conclusion, the GAN method will contribute to the risk scoring of cerebrovascular diseases, the prediction of the success and effects of the treatment modalities (preventive, medical, interventional, surgical) with the diagnostic classification approach, the creation of a long-term uncomplicated survival and also the application of personalized medicine.


DOI :10.26650/B/T3.2024.40.006   IUP :10.26650/B/T3.2024.40.006    Full Text (PDF)

Karoti̇s Arter Hastalıkları Prognozunun Tahmi̇ni̇nde Üretken Çeki̇şmeli̇ Ağ ve Evri̇şi̇msel Si̇ni̇r Ağları

Nilgün BozbuğaMurat GezerSevinç GülseçenÇağla Canbay Sarılarİlke KeleşUfuk Alpagut

Kronik, ilerleyici karotis arter hastalıklarının erken tanısında, tedavi seçeneklerinin uygulanmasında, uzun dönem takiplerinde mortalite, morbidite, komplikasyon risklerinin önlenmesi veya azaltılması açısından hastalık prognozunun tahmin edilmesi yoluyla hasta yönetiminin sağlanması büyük önem taşımaktadır. Aterosklerotik karotis arter hastalıkları inmenin en önemli sebebidir ve darlığın derecesi ile orantılı olarak inme riski de artar. Karotis arter darlığının genel popülasyonda görülme sıklığı %3 olup, ileri yaşla birlikte artar ve erkeklerde kadınlara göre daha sık görülür. Semptomatik hastalık için altın standart tedavi karotis endarterektomidir. Ameliyatın asıl amacı,dengesiz plaktan kaynaklanan tekrarlayan felç riskini en aza indirmektir. Asemptomatik hastalıkta cerrahinin rolü tartışmalıdır. Bu nedenle gelecekte nasıl bir hastalık yapısının karotis arter patolojilerine yol açabileceğinin tahmin edilmesi büyük önem taşımaktadır. Karotis Doppler ultrason (DUS) ve bilgisayarlı tomografik (BT) anjiyografi, karotis arter hastalığını teşhis etmek için kullanılan görüntüleme teknikleridir ve bu teknikler özellikle darlığın derecesinin tahmin edilmesinde faydalıdır. Karotis arter görüntüleme verilerinin analizinden erken tanının belirlenmesini destekleyen bir makine öğrenimi ve görüntü işleme algoritması kullanılarak mevcut görüntülerin modellenmesi yoluyla ortaya çıkacak farklı damar yapısı türlerinin incelenmesi çok önemlidir. Sonuçların geriye dönük olarak raporlanması ve bu bulgulara dayanarak damar sisteminin gelecekteki yaşlanmasının araştırılması ve ileriye yönelik erken teşhisin başlangıcını tahmin etmek için kullanılabilecek bir karar destek uygulaması için prototip oluşturulması büyük önem taşımaktadır. Evrişimsel sinir ağları (CNN), görüntülerin sınıflandırılması ve bölümlendirilmesi için kullanılır. Üretken çekişmeli ağ (GAN) modellerinin oluşturulması, bir veriden benzer özelliklere sahip yeni verilerin üretilmesi olarak gösterilebilir. GAN yöntemi, sınıflandırmanın yanı sıra sentetik veri üretmek için de kullanılabilir. Böylece ateroskleroz gelişiminin sentetik olarak bir zaman serisi olarak üretilmesi, sentetik olarak oluşturulan görüntüden tanısal destek sisteminin geliştirilmesi, GAN ağının eğitilmesi ve CNN modelinin eğitilmesi amaçlanmaktadır. GAN yöntemi ile karotis arter hastalıklarının prognoz tahmini, derin öğrenme yöntemleri ile uzun süreli takip ve uzaktan hasta yönetimi ile hastalığa yönelik risk faktörlerinin belirlenmesi, kontrol altına alınması ve azaltılması, düzenli tedavi yapılması, acil veya acil müdahale ihtiyacının öngörülmesi ve acil damar müdahalesinin yapılmasıyla olumsuz olayların önlenmesi için olanak sağlayacaktır. Hastanede yatış oranlarının ve sürelerinin azaltılması, kronik hastalıklarda ortaya çıkan komplikasyonların sağlık ekonomisi üzerindeki büyük yükünün hafifletilmesi ve hastaların yaşam kalitesinin artırılması na katkı sağlayacaktır. Sonuçta GAN yöntemi, serebrovasküler hastalıkların risk skorlamasına, tanısal sınıflandırma yaklaşımıyla tedavi yöntemlerinin (koruyucu, medikal, girişimsel, cerrahi) başarısının ve etkilerinin öngörülmesine, uzun süreli komplikasyonsuz sağkalım yaratılmasına ve ayrıca kişiselleştirilmiş tıp uygulaması katkı sağlayacaktır. 



References

  • AlAmir, M., & AlGhamdi, M. (2022). The Role of Generative Adversarial Network in Medical Image Analysis: An in-depth survey. Association for Computing Machinery Computing Surveys. https://doi. org/10.1145/3527849 google scholar
  • Arora, S., Ge, R., Liang, Y., Ma, T., & Zhang, Y. (2017). Generalization and Equilibrium in Generative Adversa-rial Nets (GANs). Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research, 70, 224-232. Available from https://proceedings.mlr.press/v70/arora17a.html. google scholar
  • Azhar, B., Wafi, A., Budge, J., & Loftua I. (2020). Timing of carotid endarterectomy and clinical outcomes. The Annals of Translational Medicine, 8(19), 1267. doi: 10.21037/atm-20-1130 google scholar
  • Beckman, J.A., Creager, M.A., & Libby, P. (2002). Diabetes and atherosclerosis: Epidemiology, pathophysiology and management. Journal of the American Medical Association, (JAMA) 287, 2570-2581. google scholar
  • Bullen C. (2008). Impact of tobacco smoking and smoking cessation on cardiovascular risk and disease. Expert Review of Respiratory Medicine, 6, 83-895. google scholar
  • Chauhan, R., Ghanshala, K. K., & Joshi, R. C. (2018). Convolutional Neural Network (CNN) for Image Detec-tion and Recognition. IEEE Xplore. https://doi.org/10.1109/ICSCCC.2018.8703316 google scholar
  • Chen, H. (2021). Challenges and Corresponding Solutions of Generative Adversarial Networks (GANs): A Survey Study. Journal of Physics: Conference Series, 1827(1), 012066. https://doi.org/10.1088/1742-6596/1827/1/012066 google scholar
  • Dash, A., Ye, J., & Wang, G. (2021). A Review of Generative Adversarial Networks (GANs) and Its Applications in a Wide Variety of Disciplines: From Medical to Remote Sensing. IEEE Access, 12, 18330-18357. google scholar
  • Dossabhoy, S., & Arya, S. (2021). Epidemiology of atherosclerotic carotid artery disease. Seminars in Vascular Surgery, 34(1), 3-9. google scholar
  • Durmaz Çelik, F.N., & Aykaç Ö. (2019). The effect of asymptomatic carotid artery stenosis on cognitive functi-ons. Türk Beyin Damar Hastalıkları Dergisi, 25(3), 140-144. doi 10.5505/tbdhd.2019.14890 google scholar
  • Economopoulos, K.P., Sergentanis, T.N., Tsivgoulis, G., Mariolis, A.D., & Stefanadis, C. (2011). Carotid artery stenting versus carotid endarterectomy: a comprehensive meta-analysis of short-term and long-term outco-mes. Stroke, 42, 687-692. google scholar
  • Engelter, S., Lyrer, P., & Cochrane Stroke Group. (2003). Antiplatelet therapy for preventing stroke and other vascular events after carotid endarterectomy. Cochrane Database System Review, 2003(3), CD001458. google scholar
  • Flaherty, M.L., Kissela, B., Khoury, J.C., Alwell, K., Moomaw, C.J., Woo, D., Khatri, P., Ferioli, S., Adeoye, O., Broderick, J.P., & Kleindorfer, D. (2013). Carotid Artery Stenosis as a Cause of Stroke. Neuroepidemiology, 40, 36-41. google scholar
  • Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. Advances in neural information processing systems. p./pp. 2672-2680. google scholar
  • Halliday, A., Mansfield, A., Marro, J., Peto, C., Peto, R., Potter, J., & Thomas, D. (2004). Prevention of disabling and fatal strokes by successful carotid endarterectomy in patients without recent neurological symptoms: randomised controlled trial. Lancet, 363, 1491-1502. google scholar
  • Hirsch, A. T., Criqui, M. H., Treat Jacobson, D., Regensteiner, J. G., Creager, M. A., Olin, J. W., et al. (2001). Peripheral arterial disease detection, awareness, and treatment in primary care. Journal of the American Medical Association (JAMA), 286(11), 1317-1324. google scholar
  • Hong, K.S., Yegiaian, S., Lee, M., Lee, J., & Saver, J.L. (2011). Declining stroke and vascular event recurrence rates in secondary prevention trials over the past 50 years and consequences for current trial design. Circu-lation, 123, 2111-2119. doi: 10.1161/CIRCULATIONAHA.109.934786 google scholar
  • Ismail, A., Ravipati, S., Gonzalez-Hernandez, D., Mahmood, H., Imran, A., Munoz, E.J., Neem, S., Abdin, Z.U., & Siddiqui, H.F. (2023). Carotid Artery Stenosis: A Look Into the Diagnostic and Management Strategies, and Related Complications. Cureus, 15(5), e38794. google scholar
  • Lindsey, T. & Garami, Z. (2019). “Automated Stenosis Classification of Carotid Artery Sonography using Deep Neural Networks,” 2019 18th IEEE International Conference On Machine Learning And Applications (ICM-LA), Boca Raton, FL, USA, 2019, pp. 1880-1884, doi: 10.1109/ICMLA.2019.00302. google scholar
  • Liu, R., & Shao J. (2022). Research progress on risk factors related to intracranial artery, carotid artery, and coronary artery stenosis. Cardiovascular Medical Section Atherosclerosis and Vascular Medicine, 9, 1-5. google scholar
  • McDermott, M.M., Greenland, P., Liu, K., Guralnik, J.M., Criqui, M.H., Dolan, N.C., Chan, C., Celic, L., Pearce, W.H., Schneider, J.R., Sharma, L., Clark, E., Gibson, D., & Martin, G.J. (2001). Leg symptoms in periphe-ral arterial disease: associated clinical characteristics and functional impairment. Journal of the American Medical Association (JAMA), 286(13), 1599-1606. doi: 10.1001/jama.286.13.1599. google scholar
  • Naylor, A.R., Sillesen, H., & Schroeder, T.V. (2015). Clinical and imaging features associated with an increased risk of early and late stroke in patients with symptomatic carotid disease. European Journal of Vascular and Endovascular Surgery, 49, 513-523. google scholar
  • Paraskevas, K.I., Nicolaides, A.N., & Kakis, S.K. (2020). Asymptomatic Carotid Stenosis and Risk of Stro-ke (ACSRS) study: what have we learned from it? The Annals of Translational Medicine, 8(19), 1271. doi: 10.21037/atm.2020.02.156 google scholar
  • Rothwell, P.M., Eliasziw, M., Gutnikov, S.A., Fox, A.J., Taylor, D.W., Mayberg, M.R., Warlow, C.P., & Barnett, H.J. (2003). Analysis of pooled data from the randomised controlled trials of endarterectomy for sympto-matic carotid stenosis. Lancet, 361, 107-116. google scholar
  • Rothwell, P.M., Eliasziw, M., Gutnikov, S.A., Warlow, C.P., & Barnett, H.J. (2004). Carotid Endarterectomy Trialists Collaboration. Endarterectomy for symptomatic carotid stenosis in relation to clinical subgroups and timing of surgery. Lancet, 363(9413), 915-924. doi: 10.1016/S0140-6736(04)15785-1. google scholar
  • Saxon, A., Ng, E.Y.K. & Lim, S.T. (2019). Imaging modalities to diagnose carotid artery stenosis: progress and prospect. Biomedical Engineering Journal Online, 18, 66. doi: 10.1186/s12938-019-0685-7 google scholar
  • Sorin, V., Barash, Y., Konen, E., & Klang, E. (2020). Creating Artificial Images for Radiology Applications, Using Generative Adversarial Networks (GANs) - A Systematic Review. Academic Radiology, https://doi. org/10.1016/j.acra.2019.12.024 google scholar
  • Tendera, M., Aboyans, V., Bartelink, M.L., Baumgartner, I., Clement, D., Collet, J.P., Cremonesi, A., De Carlo, M., Erbel, R., Fowkes, F.G., Heras, M., Kownator, S., Minar, E., Ostergren, J., Poldermans, D., Riambau, V., Roffi, M., Rother, J., Sievert, H., van Sambeek, M., & Zeller, T. (2011). ESC Guidelines on the diagnosis and treatment of peripheral artery diseases: Document covering atherosclerotic disease of extracranial carotid and vertebral, mesenteric, renal, upper and lower extremity arteries: the Task Force on the Diagnosis and Treatment of Peripheral Artery Diseases of the European Society of Cardiology (ESC). European Heart Journal, 32, 2851-2906. google scholar
  • Wardlaw, J.M., Chappell, F.M., Stevenson, M., De Nigris, E., Thomas, S., Gillard, J., Berry, E., Young, G., Rothwell, P., Roditi, G., Gough, M., Brennan, A., Bamford, J., & Best, J. (2006). Accurate, practical and cost-effective assessment of carotid stenosis in the UK. Health Technology Assess, 10, iii-iv, ix-x, 1 - 182. google scholar
  • Xu, B., Li, C., Gou, Y., Xu, K., Yang, Y., & Yu, J. (2018). Current understanding of chronic total occlusion of the internal carotid artery. Biomedical Repair, 8(2), 117-125. google scholar
  • Yuzhen L., Dong C., Ebenezer O., & Yanbo H. (2022). Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review. Computers and Electronics in Agriculture, 200, 107208. ISSN 0168-1699.https://doi.org/10.1016/j.compag.2022.107208. google scholar
  • Zhang, G., Hui, H., Ning, B., Dong, D., J. Tian, J.& He, W. (2021). “Self-Attention Based Virtual Staining for Bright-field Images of Label-free Human Carotid Atherosclerotic Plaque Tissue Section.” 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, 2021, pp. 3492-3495, doi: 10.1109/EMBC46164.2021.9630026. google scholar
  • Zhou, D.X. (2019). Universality of deep convolutional neural networks. Applied and Computational Harmonic Analysis. https://doi.org/10.1016/j.acha.2019.06.004 google scholar


SHARE




Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.