Журнал «» Том 19, №1-2, 2026
Вернуться к номеру
Штучний інтелект у кількісній КТ-денситометрії та волюметрії в інтеграції з функціональними легеневими тестами для оцінки тяжкості легеневої гіпертензії: огляд літератури
Авторы: Прогонов С.О.
ДУ «ННЦ «Інститут кардіології, клінічної та регенеративної медицини імені акад. М.Д. Стражеска» НАМН України», м. Київ, Україна
Рубрики: Кардиология
Разделы: Справочник специалиста
Версия для печати
Резюме
Оцінка респіраторної функції та структурних змін легеневої паренхіми у пацієнтів із легеневою гіпертензією (ЛГ) залишається складним діагностичним завданням, оскільки класичні респіраторні тести часто демонструють обмежену самостійну прогностичну цінність через вплив позалегеневих коморбідних факторів. Метою цього огляду було проаналізувати сучасні тенденції, патофізіологічні обмеження та технологічні перспективи інтеграції методів дослідження легеневої функції (ДЛФ), кількісного комп’ютерно-томографічного (КТ) аналізу паренхіми та алгоритмів штучного інтелекту (ШІ) в оцінці перебігу та прогнозу ЛГ. У роботі деталізовано патофізіолого-метаболічний вплив системного залізодефіциту та анемічного синдрому на результати ДЛФ, зокрема через механізм вторинної міопатії дихальної мускулатури, що призводить до хибно знижених показників респіраторного тестування. Висвітлено еволюцію променевої діагностики ЛГ з переходом до кількісного КТ-аналізу, коли спільне застосування КТ-денситометрії та волюметрії дозволяє верифікувати тривимірні об’єми паренхіми, приховану гіперінфляцію та повітряні пастки, що мають незалежне прогностичне значення. Оцінено роль архітектур глибокого навчання та конволютивних нейронних мереж в автоматизації сегментації легень. Висновки. Прогностичний потенціал класичних респіраторних тестів суттєво лімітується системним залізодефіцитом, що потребує обов’язкового моніторингу ферокінетики. Максимальна точність предиктивного моделювання при ЛГ досягається завдяки синергічному підходу — поєднанню ШІ-метрик КТ-волюметрії та денситометрії з традиційним клінічним досвідом і метаболічним профілем пацієнта.
Assessing respiratory function and structural alterations of the lung parenchyma in patients with pulmonary hypertension (PH) remains a complex diagnostic challenge, as classical respiratory tests often exhibit limited independent prognostic value due to the confounding effects of extrapulmonary comorbidities. The purpose was to analyze current trends, pathophysiological limitations, and technological prospects of integrating pulmonary function testing, quantitative computed tomography (CT) parenchymal analysis, and artificial intelligence (AI) algorithms in evaluating the clinical course and prognosis of PH. This review details the pathophysiologic and metabolic impact of systemic iron deficiency and anemia on pulmonary function testing results, specifically via the mechanism of secondary respiratory muscle myopathy, which leads to falsely reduced respiratory testing parameters. The evolution of PH radiologic imaging towards quantitative CT analysis is highlighted, where the combined application of CT densitometry and volumetry enables verifying three-dimensional parenchymal volumes, occult hyperinflation, and air trapping, all carrying independent prognostic significance. The role of deep learning architectures and convolutional neural networks in automating lung segmentation is evaluated. Conclusions. The prognostic potential of classical respiratory tests is significantly limited by systemic iron deficiency, necessitating mandatory iron status monitoring. Maximum predictive modeling accuracy in PH is achieved through a synergistic approach — combining AI-driven metrics of CT volumetry and densitometry with traditional clinical expertise and the patient’s systemic metabolic profile.
Ключевые слова
легенева гіпертензія; спірометрія; комп’ютерна томографія; штучний інтелект; залізодефіцит
pulmonary hypertension; spirometry; computed tomography; artificial intelligence; iron deficiency
Для ознакомления с полным содержанием статьи необходимо оформить подписку на журнал.
Список литературы
1. Simonneau, G., Montani, O., Celermajer, A.D., Denton, N., Gali, N., Ghofrani, I.A., et al. (2019). Haemodynamic definitions and updated clinical classification of pulmonary hypertension. European Respiratory Journal, 53(1), 1801913. https://doi.org/10.1183/13993003.01913-2018.
2. Humbert, M., Kovacs, G., Hoeper, M.M., Badagliacca, R., Berger, R.M.F., Brida, M., et al. (2022). 2022 ESC/ERS Guidelines for the diagnosis and treatment of pulmonary hypertension. Eurn Heart J., 43(38). http://doi.org/10.1093/eurheartj/ehac237.
3. Yoon, D.W., Yoon, Y.E., Hwang, I.C., Lee, W., Lee, K.Y., & Chun, E.J. (2025). CT imaging biomarkers to predict seve–rity and prognosis of pulmonary hypertension. PloS Оne, 20(2), e0313235. https://doi.org/10.1371/journal.pone.0313235.
4. Benza, R.L., Gomberg-Maitland, M., Miller, D.P., Frost, A., Frantz, R.P., Foreman, A.J., et al. (2012). The REVEAL Registry Risk Score Calculator in Patients Newly Diagnosed With Pulmonary Arterial Hypertension. Chest, 141(2), 354-62. http://doi.org/10.1378/chest.11-0676.
5. Benza, R.L., Farber, H.W., Frost, A., Hossein-Ardeschir Ghofrani, Gmez-Snchez, M.A., Langleben, D., et al. (2018). REVEAL risk scores applied to riociguat-treated patients in –PATENT-2: Impact of changes in risk score on survival. The Journal of Heart and Lung Transplantation, 37(4), 513-9. http://doi.org/10.1016/j.healun.2017.11.006.
6. Benza, R.L., Gomberg-Maitland, M., Elliott, C.G., Farber, H.W., Foreman, A.J., Frost, A.E., et al. (2019). Predicting Survival in Patients With Pulmonary Arterial Hypertension. Chest, 156(2), 323-37. http://doi.org/10.1016/j.chest.2019.02.004.
7. Poor, H.D., Zhang, J., Hannah-Clark, S., Saini, S., Eisenberg, E., Wang, J., et al. (2025). Sotatercept Improves Small Airway Disease and Hyperinflation in Patients with Pulmonary Hypertension. medRxiv: the preprint server for health sciences, 2025.10.08.25337393. https://doi.org/10.1101/2025.10.08.25337393.
8. Almubarek, M., Louw, E.H., Griffith-Richards, S., –Ackermann, C., Baines, N., Thomson, H., et al. (2025). Computed tomography chest imaging for the detection of pulmonary hypertension in patients with post-tuberculosis lung disease. African Journal оf Thoracic аnd Critical Care Medicine, 31(1), e1948. https://doi.org/10.7196/AJTCCM.2025.v31i1.1948.
9. Swift, A.J., Wild, J.M., Rajaram, S., Metherall, P., Elliot, C.A., Condliffe, R., et al. (2012). Serial magnetic resonance imaging of pulmonary artery flow in patients with pulmonary hypertension: a longitudinal study. Circulation: Cardiovascular Imaging, 5(6), 795-802. https://doi.org/10.1161/CIRCIMAGING.112.977413.
10. Chan, A.L., Juarez, M.M., Shelton, D.K., MacDonald, T., Li, C.S., Lin, T.C., & Albertson, T.E. (2011). Novel computed tomographic chest metrics to detect pulmonary hypertension. BMC Medical Imaging, 11, 7. https://doi.org/10.1186/1471-2342-11-7.
11. Dwivedi, K., Sharkey, M., Condliffe, R., Uthoff, J.M., –Alabed, S., Metherall, P., et al. (2021). Pulmonary Hypertension in Association with Lung Disease: Quantitative CT and Artificial Intelligence to the Rescue? State-of-the-Art Review. Diagnostics (Basel, Switzerland), 11(4), 679. https://doi.org/10.3390/diagnostics11040679.
12. Sharkey, M.J., Taylor, J.C., Alabed, S., Dwivedi, K., Karunasaagarar, K., Johns, C.S., et al. (2022). Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning. Frontiers in Cardiovascular Medicine, 9, 983859. https://doi.org/10.3389/fcvm.2022.983859.
13. Sharkey, M.J., Checkley, E.W., & Swift, A.J. (2024). Applications of artificial intelligence in computed tomography imaging for phenotyping pulmonary hypertension. Current Opinion іn Pulmonary Medicine, 30(5), 464-472. https://doi.org/10.1097/MCP.0000000000001103.
14. Abdulaal, L., Maiter, A., Salehi, M., Sharkey, M., Alnasser, T., Garg, P., et al. (2024). A systematic review of artificial intelligence tools for chronic pulmonary embolism on CT pulmonary angiography. Frontiers in Radiology, 4, 1335349. https://doi.org/10.3389/fradi.2024.1335349.
15. Pu, J., Gezer, N.S., Ren, S., Alpaydin, A.O., Avci, E.R., Risbano, M.G., et al. (2023). Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without ma–nual outlining. Medical image analysis, 89, 102882. https://doi.org/10.1016/j.media.2023.102882.
16. Arunthari, V., Burger, C.D., Lee, A.S. Correlation of pulmonary function variables with hemodynamic measurements in patients with pulmonary arterial hypertension. The Clinical Respiratory Journal. 2010 Dec 15;5(1):35-43. http://doi.org/10.1111/j.1752-699X.2010.00188.x.
17. Progonov, S., Radchenko, G., Bortkevych, O. (2025). Pulmonary function and lung diffusion capacity in patients with pulmonary hypertension associated with systemic connective tissue diseases compared with other forms of pulmonary hypertension. Ukrainian Journal of Rheumatology, 100(2), Own observations [Ukrainian]. http://doi.org/10.32471/rheumatology.2707-6970.19793.
18. Progonov, S., Torbas, O., Kushnir, S., Sirenko, Yu., Radchenko, G. Pulmonary function and lung diffusion capacity in patients with different forms of pulmonary hypertension. Cardiac Surgery and Interventional Cardiology, 13(3), 53-63 [Ukrainian]. http://doi.org/10.31928/2664-3790-2024.3.5363.
19. Szturmowicz, M., Kacprzak, A., Franczuk, M., Burakowska, B., Kurzyna, M., Fijakowska, A., et al. (2016). Low DLCO in idiopathic pulmonary arterial hypertension — clinical correlates and prognostic significance. Pneumonol Alergol Pol [Internet], 84(2), 87-94. Available from: http://doi.org/10.5603/PiAP.2016.0006.
20. Graham, B.L., Brusasco, V., Burgos, F., Cooper, B.G., Jensen, R., Kendrick, A., et al. (2017). 2017 ERS/ATS standards for single-breath carbon monoxide uptake in the lung. The European Respiratory Journal, 49(1), 1600016. https://doi.org/10.1183/13993003.00016-2016.
21. Tsai, Ming-Ju, Yang, Chih-Jen, Hwang, Jhi-Jhu, Huang, Ming-Shyan (2013). Adjusting diffusing capacity of the lung for carbon monoxide for haemoglobin level. The European Respiratory Journal: official journal of the European Society for Clinical Respiratory Physiology, 41, 489. https://doi.org/10.1183/09031936.00152212.
22. Nguyen, L.P., Harper, R.W., Louie, S. (2016). Using and interpreting carbon monoxide diffusing capacity (Dlco) correctly. Consultant, 56(5), 440-445.
23. Quatredeniers, M., Mendes-Ferreira, P., Santos-Ribeiro, D., Nakhleh, M.K., Ghigna, M.R., Cohen-Kaminsky, S., & Perros, F. (2021). Iron Deficiency in Pulmonary Arterial Hypertension: A Deep Dive into the Mechanisms. Cells, 10(2), 477. https://doi.org/10.3390/cells10020477.
24. Sonnweber, T., Nairz, M., Theurl, I., Petzer, V., Tymoszuk, P., Haschka, D., et al. (2018). The crucial impact of iron deficiency definition for the course of precapillary pulmonary hypertension. PloS Оne, 13(8), e0203396. https://doi.org/10.1371/journal.pone.0203396.
25. Rhodes, C.J., Howard, L.S., Busbridge, M., Ashby, D., Kondili, E., Gibbs, J.S., et al. (2011). Iron deficiency and raised hepcidin in idiopathic pulmonary arterial hypertension: clinical prevalence, outcomes, and mechanistic insights. Journal of the American College of Cardiology, 58(3), 300-309. https://doi.org/10.1016/j.jacc.2011.02.057.
26. Rhodes, C.J., Wharton, J., Ghataorhe, P., Watson, G., Girerd, B., Howard, L.S., et al. (2017). Plasma proteome analysis in patients with pulmonary arterial hypertension: an observational cohort study. The Lancet. Respiratory Medicine, 5(9), 717-726. https://doi.org/10.1016/S2213-2600(17)30161-3.
27. Sonnweber, T., Pizzini, A., Tancevski, I., Lffler-Ragg, J., & Weiss, G. (2020). Anaemia, iron homeostasis and pulmonary hypertension: a review. Internal and Emergency Medicine, 15(4), 573-585. https://doi.org/10.1007/s11739-020-02288-1.
28. Tkaczyszyn, M., Drozd, M., Wgrzynowska-Teodorczyk, K., Flinta, I., Kobak, K., Banasiak, W., et al. (2018). Depleted iron stores are associated with inspiratory muscle weakness independently of skeletal muscle mass in men with systolic chronic heart failure. Journal of Cachexia, Sarcopenia аnd Muscle, 9(3), 547-556. https://doi.org/10.1002/jcsm.12282.
29. Bodenberger, A.L., Konietzke, P., Weinheimer, O., Wagner, W.L., Stiller, W., Weber, T.F., et al. (2023). Quantification of airway wall contrast enhancement on virtual monoenergetic images from spectral computed tomography. European Radiology, 33(8), 5557-5567. https://doi.org/10.1007/s00330-023-09514-2.
30. Andersen, A., Jelsness-Jrgensen, L.P., Kofod, H., Christensen, K.M., & Haug, M.K. (2019). Quantitative CT analysis of lung density in patients with pulmonary hypertension: relationship to clinical and hemodynamic parameters. European Journal of Radiology, 118, 201-207. https://doi.org/10.1016/j.ejrad.2019.06.012.
31. Matsuoka, S., Oshima, Y., Kurihara, Y., Yagihashi, K., & Nakajima, Y. (2011). Quantitative assessment of lung abnormalities on computed tomography in patients with pulmonary hypertension: relationship with hemodynamic parameters. Journal of Computer Assisted Tomography, 35(2), 241-247. https://doi.org/10.1097/RCT.0b013e31820b33c0.
32. Baruah, D., Sonavane, S., Goodman, L., Nath, H., Presberg, K., & Shahir, K. (2021). Correlation of Computed Tomography Test Bolus Dynamics and Conventional Computed Tomography Parameters With Pulmonary Vascular Resistance in Patients With Pulmonary Arterial Hypertension. Cureus, 13(2), e13577. https://doi.org/10.7759/cureus.13577.
33. Dwivedi, K., Sharkey, M., Delaney, L., Alabed, S., Rajaram, S., Hill, C., et al. (2024). Improving Prognostication in Pulmonary Hypertension Using AI-quantified Fibrosis and Radiolo–gic Severity Scoring at Baseline CT. Radiology, 310(2), e231718. https://doi.org/10.1148/radiol.231718.
34. Zambrano, B.A., McLean, N.A., Zhao, X., Tan, J.L., Zhong, L., Figueroa, C.A., et al. (2018). Image-based computational assessment of vascular wall mechanics and hemodynamics in pulmonary arterial hypertension patients. Journal of Biomecha–nics, 68, 84-92. https://doi.org/10.1016/j.jbiomech.2017.12.022.
35. Rahaghi, F.N., Ross, J.C., Agarwal, M., Gonzlez, G., Come, C.E., Diaz, A.A., et al. (2016). Pulmonary vascular morphology as an imaging biomarker in chronic thromboembolic pulmonary hypertension. Pulmonary Сirculation, 6(1), 70-81. https://doi.org/10.1086/685081.
36. Xu, W., Xi, L., Ni, Y., Wang, J., Yang, H., Liu, A., et al. (2025). Artificial intelligence-driven quantitative analysis of CT morphological differences between chronic thromboembolic pulmonary hypertension and chronic thromboembolic disease. Quantitative Imaging іn Medicine аnd Surgery, 15(2), 1101-1113. https://doi.org/10.21037/qims-24-1301.
37. Bird, E., Hasenstab, K., Kim, N., Madani, M., Malhotra, A., Hahn, L., et al. (2023). Mapping the Spatial Extent of Hypoperfusion in Chronic Thromboembolic Pulmonary Hypertension Using Multienergy CT. Radiology. Cardiothoracic Imaging, 5(4), e220221. https://doi.org/10.1148/ryct.220221.
38. zgven, S., Kesim, S., kszolu, K., Yanarta, M., Ta, S., en, F., et al. (2021). Correlation Between Perfusion Abnormalities Extent in Ventilation/Perfusion SPECT/CT with Hemodynamic Parameters in Patients with Chronic Thromboembolic Pulmonary Hypertension. Molecular Imaging аnd Radionuclide Therapy, 30(1), 28-33. https://doi.org/10.4274/mirt.galenos.2020.31932.
39. Yamaguchi, T., Ehara, S., Yoshida, H., Himoto, D., Izuta, S., Hayashi, O., et al. (2023). Quantification of pulmonary perfusion using LSIM-CT correlates with pulmonary hemodynamics in patients with CTEPD. Frontiers in Cardiovascular Medicine, 10, 1237296. https://doi.org/10.3389/fcvm.2023.1237296.
40. Shahin, Y., Alabed, S., Alkhanfar, D., Tschirren, J., Rothman, A.M.K., Condliffe, R., et al. (2022). Quantitative CT Evaluation of Small Pulmonary Vessels Has Functional and Prognostic Value in Pulmonary Hypertension. Radiology, 305(2), 431-440. https://doi.org/10.1148/radiol.210482.
41. Gertz, R.J., Gerhardt, F., Krger, J.R., Shahzad, R., Caldeira, L., Kottlors, J., et al. (2022). Spectral Detector CT-Derived Pulmonary Perfusion Maps and Pulmonary Parenchyma Cha–racteristics for the Semiautomated Classification of Pulmonary Hypertension. Frontiers in Cardiovascular Medicine, 9, 835732. https://doi.org/10.3389/fcvm.2022.835732.
42. Pienn, M., Gertz, R.J., Gerhardt, F., Krger, J.R., Zaytoun, H., Reimer, R.P., et al. (2024). CT-derived lung vessel morphology correlates with prognostic markers in precapillary pulmonary hypertension. The Journal of Heart аnd Lung Transplantation: the official publication of the International Society for Heart Transplantation, 43(1), 54-65. https://doi.org/10.1016/j.healun.2023.08.013.
43. Rahaghi, F.N., Nardelli, P., Harder, E., Singh, I., Snchez-Ferrero, G.V., Ross, J.C., et al. (2021). Quantification of Arterial and Venous Morphologic Markers in Pulmonary Arterial Hypertension Using CT Imaging. Chest, 160(6), 2220-2231. https://doi.org/10.1016/j.chest.2021.06.069.
44. Ussavarungsi, K., Lee, A.S., & Burger, C.D. (2015). Mosaic Pattern of Lung Attenuation on Chest CT in Patients with Pulmonary Hypertension. Diseases (Basel, Switzerland), 3(3), 205-212. https://doi.org/10.3390/diseases3030205.
45. Papaioannou, A.I., Kostikas, K., Manali, E.D., Papadaki, G., Roussou, A., Kolilekas, L., et al. (2016). Combined pulmonary fibrosis and emphysema: The many aspects of a cohabitation contract. Respiratory Medicine, 117, 14-26. https://doi.org/10.1016/j.rmed.2016.05.005.
46. Hirano, A.C.G., Targueta, E.P., Ferraz de Campos, F.P., Martines, J.A.D.S., Andrade, D., Lovisolo, S.M., & Felipe-Silva, A. (2017). Severe pulmonary hypertension due to combined pulmonary fibrosis and emphysema: another cause of death among smokers. Autopsy & Case Reports, 7(2), 15-26. https://doi.org/10.4322/acr.2017.022.
47. Afloarei, C.A., Birladeanu, T., Pintilie, A.L., Toma, D., Marcu, D.T.M., Zabara Antal, A., et al. (2025). Combined Pulmonary Fibrosis and Emphysema (CPFE): A "New" Smoking-Related Interstitial Lung Disease (ILD). Biomedicines, 13(11), 2703. https://doi.org/10.3390/biomedicines13112703.
48. Calaras, D., Mathioudakis, A.G., Lazar, Z., & Corlateanu, A. (2023). Combined Pulmonary Fibrosis and Emphysema: Comparative Evidence on a Complex Condition. Biomedicines, 11(6), 1636. https://doi.org/10.3390/biomedicines11061636.
49. Coste, F., Benlala, I., Dournes, G., Dromer, C., Blanchard, E., Girodet, P.O., et al. (2019). Quantitative CT assessment of bronchial and vascular alterations in severe preca-pillary pulmonary hypertension. International Journal оf Chronic Obstructive Pulmonary Disease, 14, 381-389. https://doi.org/10.2147/COPD.S177638.
50. Szturmowicz, M., Kacprzak, A., Burakowska, B., Skoczylas, A., Bestry, I., Ku, J., et al. (2016). Centrilobular nodules in high resolution computed tomography of the lung in IPAH patients — preliminary data concerning clinico-radiological correlates. Pneumonologia i Alergologia Polska, 84(5), 265-270. https://doi.org/10.5603/PiAP.2016.0033.
51. Gawlitza, J., Endres, S., Fries, P., Graf, M., Wilkens, H., Stroeder, J., Buecker, A., et al. (2024). Machine learning assisted feature identification and prediction of hemodynamic endpoints using computed tomography in patients with CTEPH. The International Journal оf Cardiovascular Imaging, 40(3), 569-577. https://doi.org/10.1007/s10554-023-03026-2.
52. Skowasch, D., Pausch, C., Huscher, D., Pittrow, D., Wede, J., Kreimendahl, F., et al. (2025). Mono and combination therapies in pulmonary arterial hypertension patients with comorbidities: A COMPERA analysis. ESC Heart Failure, 12(4), 2726-2735. https://doi.org/10.1002/ehf2.15254.
53. Held, M., Pausch, C., Huscher, D., Pittrow, D., Halank, M., Beckmann, S., et al. (2025). Survival in patients with chronic thromboembolic pulmonary hypertension treated with riociguat versus other medications: a COMPERA analysis. ERJ Open Research, 11(6), 00230-2025. https://doi.org/10.1183/23120541.00230-2025.
54. Hoeper, M.M., Pausch, C., Olsson, K.M., Huscher, D., Pittrow, D., Grnig, E., et al. (2022). COMPERA 2.0: a refined four-stratum risk assessment model for pulmonary arterial hypertension. The European Respiratory Journal, 60(1), 2102311. https://doi.org/10.1183/13993003.02311-2021.