Application of digital processing methods for automated cardiac segmentation from computed tomography data

Abstract

Computed tomography is now widely used in cardiac surgery as a method of non-destructive study of internal structure of objects, including specific tasks, such as mathematical modeling of physiological processes, surgical interventions in augmented reality, 3D printing, and radiomics. One of the key steps in creating a 3D model from computed tomography data is segmentation – the process of selecting objects in the image. Currently, there are several approaches to automating the segmentation process, including image processing methods, texture analysis and machine learning algorithms (in particular, clustering). Image processing methods are the simplest of the presented approaches and are found in various applications for segmentation of tomographic data. This paper reviews the advantages and disadvantages of various image processing methods (threshold, region growing, contour detection, and morphological watersheds) as tools for automated cardiac segmentation from computed tomography data. It was revealed that computed tomography images have characteristic features affecting the segmentation process (presence of noise, partial volume effect, etc.). The choice of the segmentation method is based on the brightness characteristics of the area of interest and also requires knowledge of the subject area, so it should be performed by a specialist with competence in anatomy and digital image processing. As independent methods of automated segmentation, the listed methods are applicable only in relatively simple cases (selection of homogeneous or high-contrast areas), otherwise, a combination of these methods, the use of machine learning algorithms or manual correction of the results is required.

Keywords

automation / cardiac radiology / computed tomography / digital processing / medical imaging / segmentation / 3D modeling

References

[1] Shumakov IV, Sukhova MV. MSCT Coronary Angiography in Diagnosis of Chronic Coronary Occlusions. Sovremennye tehnologii v medicine. 2018;10(2):118–124. DOI: 10.17691/stm2018.10.2.13

[2] Shumakov I.V., Sukhova M.B. MSCT Coronary Angiography in Diagnosis of Chronic Coronary Occlusions // Sovremennye tehnologii v medicine. 2018. Vol. 10, No. 2. P. 118–124. DOI: 10.17691/stm2018.10.2.13

[3] Latina J, Shabani M, Kapoor K, et al. Ultra-High-Resolution Coronary CT Angiography for Assessment of Patients with Severe Coronary Artery Calcification: Initial Experience. Radiol Cardiothorac Imaging. 2021;3(4): e210053. DOI:10.1148/ryct.2021210053

[4] Latina J., Shabani M., Kapoor K., et al. Ultra-High-Resolution Coronary CT Angiography for Assessment of Patients with Severe Coronary Artery Calcification: Initial Experience // Radiol. Cardiothorac. Imaging. 2021. Vol. 3, No. 4. P. e210053. DOI: 10.1148/ryct.2021210053

[5] Niederer SA, Lumens J, Trayanova NA. Computational models in cardiology. Nat Rev Cardiol. 2019;16(2):100–111. DOI: 10.1038/s41569-018-0104-y

[6] Niederer S.A., Lumens J., Trayanova N.A. Computational models in cardiology // Nat. Rev. Cardiol. 2019. Vol. 16, No. 2. P. 100–111. DOI: 10.1038/s41569-018-0104-y

[7] Arjomandi Rad A, Vardanyan R, Thavarajasingam SG, et al. Extended, virtual and augmented reality in thoracic surgery: a systematic review. Interact Cardiovasc Thorac Surg. 2022;34(2):201–211. DOI: 10.1093/icvts/ivab241

[8] Arjomandi Rad A., Vardanyan R., Thavarajasingam S.G., et al. Extended, virtual and augmented reality in thoracic surgery: a systematic review // Interact. Cardiovasc. Thorac. Surg. 2022. Vol. 34, No. 2. P. 201–211. DOI: 10.1093/icvts/ivab241

[9] Vukicevic M, Mosadegh B, Min JK, Little SH. Cardiac 3D Printing and its Future Directions. JACC Cardiovasc Imaging. 2017;10(2): 171–184. DOI: 10.1016/j.jcmg.2016.12.001

[10] Vukicevic M., Mosadegh B., Min J.K., Little S.H. Cardiac 3D Printing and its Future Directions // JACC Cardiovasc. Imaging. 2017. Vol. 10, No. 2. P. 171–184. DOI: 10.1016/j.jcmg.2016.12.001

[11] Oikonomou EK, Williams MC, Kotanidis CP, et al. A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography. Eur Heart J. 2019;40(43):3529–3543. DOI: 10.1093/eurheartj/ehz592

[12] Oikonomou E.K., Williams M.C., Kotanidis C.P., et al. A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography // Eur. Heart J. 2019. Vol. 40, No. 43. P. 3529–3543. DOI: 10.1093/eurheartj/ehz592

[13] Sadykova GK, Zheleznyak IS, Ipatov VV, Ryazanov VV. The possibilities of computed tomography heart-axis-oriented multiplanar reformations in diagnostics of common arterial trunk. Vestnik of Russian Military Medical Academy. 2018;1(61):132–138. (In Russ.)

[14] Садыкова Г.К., Железняк И.С., Ипатов В.В., Рязанов В.В. Возможности применения многоплоскостных реформаций, ориентированных на оси сердца, в диагностике общего артериального ствола при рентгеновской компьютерной томографии // Вестник Российской Военно-медицинской академии. 2018. № 1(61). С. 132–138.

[15] Abdulrakeb ARA. Modification of thresholding based segmentation for half-tone images. Radio Engineering and Telecommunications Systems. 2017;2(26):50–58. (In Russ.)

[16] Абдулракеб А.Р.А. Модификация порогового метода сегментации полутоновых изображений // Радиотехнические и телекоммуникационные системы. 2017. № 2 (26). С. 50–58.

[17] Borrelli P, Kaboteh R, Enqvist O, et al. Artificial intelligence-aided CT segmentation for body composition analysis: a validation study. Eur Radiol Exp. 2021;5(1):11. DOI: 10.1186/s41747-021-00210-8

[18] Borrelli P., Kaboteh R., Enqvist O., et al. Artificial intelligence-aided CT segmentation for body composition analysis: a validation study // Eur. Radiol. Exp. 2021. Vol. 5, No. 1. P. 11. DOI: 10.1186/s41747-021-00210-8

[19] Fedorov A, Beichel R, Kalpathy-Cramer J, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. 2012;30(9):1323–1341. DOI: 10.1016/j.mri.2012.05.001

[20] Fedorov A., Beichel R., Kalpathy-Cramer J., et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network // Magn. Reason. Imaging. 2012. Vol. 30, No. 9. P. 1323–1341. DOI: 10.1016/j.mri.2012.05.001

[21] Yushkevich PA, Piven J, Hazlett HC, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage. 2006;31(3):1116–1128. DOI: 10.1016/j.neuroimage.2006.01.015

[22] Yushkevich P.A., Piven J., Hazlett H.C., et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability // Neuroimage. 2006. Vol. 31, No. 3. P. 1116–1128. DOI: 10.1016/j.neuroimage.2006.01.015

[23] Gonzalez RC, Woods RE. Digital Image Processing, Global Edition. 4th ed. London: Pearson; 2018.

[24] Gonzalez R.C., Woods R.E. Digital Image Processing, Global Edition. 4th ed. London: Pearson, 2018.

[25] Matlakhov VP, Ignatov AN, Suslov AG. Software module development for definition of percentage composition in antiwear coatings. The Bryansk State University Herald. 2016;2(50):46–51. (In Russ.) DOI: 10.12737/20243

[26] Матлахов В.П., Игнатов А.Н., Суслов А.Г. Разработка программного модуля для определения процентного состава компонентов износостойких покрытий // Вестник Брянского государственного технического университета. 2016. № 2 (50). С. 46–51.DOI: 10.12737/20243

[27] Pashina TA, Gaidel AV, Zelter PM, et al. Automatic highlighting of the region of interest in computed tomography images of the lungs. Computer Optics. 2020;44(1):74–81. (In Russ.) DOI: 10.18287/2412-6179-CO-659

[28] Пашина Т.А., Гайдель А.В., Зельтер П.М., и др. Сравнение алгоритмов выделения области интереса на компьютерных томограммах легких // Компьютерная оптика. 2020. Т. 44, № 1. С. 74–81. DOI: 10.18287/2412-6179-CO-659

[29] Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell. 1986;8(6):679–698.

[30] Canny J. A computational approach to edge detection // IEEE Trans. Pattern Anal. Mach. Intell. 1986. Vol. 8, No. 6. P. 679–698.

[31] Zhu L, Gao Y, Appia V, et al. Automatic delineation of the myocardial wall from CT images via shape segmentation and variational region growing. IEEE Trans Biomed Eng. 2013;60(10):2887–2895. DOI: 10.1109/TBME.2013.2266118

[32] Zhu L., Gao Y., Appia V., et al. Automatic delineation of the myocardial wall from CT images via shape segmentation and variational region growing // IEEE Trans. Biomed Eng. 2013. Vol. 60, No. 10. P. 2887–2895. DOI: 10.1109/TBME.2013.2266118

[33] Sakly H, Said M, Tagina M. Evaluation of the active contour and topographic watershed segmentation «assessment of the systolic ejection fraction in the left ventricular for medical assistance in 5D short axis cine MRI». Heliyon. 2020;6(11): e05547. DOI: 10.1016/j.heliyon.2020.e05547

[34] Sakly H., Said M., Tagina M. Evaluation of the active contour and topographic watershed segmentation “assessment of the systolic ejection fraction in the left ventricular for medical assistance in 5D short axis cine MRI” // Heliyon. 2020. Vol. 6, No. 11. P. e05547. DOI: 10.1016/j.heliyon.2020.e05547

RIGHTS & PERMISSIONS

Shirshin A.V., Boikov I.V., Malakhovskiy V.N., Rameshvili T.E., Kushnarev S.V.