Application of image processing algorithms to improve visualization of pancreatic structures

The purpose of the research is to develop and compare various methods of processing medical images in order to optimize visualization of pancreatic structures. The main task is to identify the most effective image processing method to achieve the best visualization quality, which, in turn, is important for the accurate diagnosis and treatment of patients with pancreatic pathologies.
Methods. As part of our research, various methods were applied, including the analysis of a huge bibliographic material, the use of various tools for data collection, and the involvement of expert knowledge and approaches.
Results. The results obtained are discussed taking into account their practical significance for medicine. Optimization of visualization of the pancreas using various image processing methods can significantly improve the accuracy of diagnosis of its diseases. Improved visualization makes it possible to more accurately identify and analyze pathological changes, which contributes to the early detection of diseases and more effective treatment of patients. This can contribute to further improvement of methods of diagnosis and treatment of pancreatic diseases, improving the quality of medical care.
Conclusion. Different segmentation methods, such as threshold processing, machine learning, and active contours, have their advantages and limitations in visualizing pancreatic structures. The choice of the optimal method depends on the specific task and the requirements for the accuracy and speed of image processing. Further research should focus on developing more efficient segmentation algorithms and their applicability in clinical practice to improve diagnosis and treatment of pancreatic diseases.

1. Yukina M.Y., Nuralieva N.F., Troshina E.A., et al. Diffusion-weighted magnetic resonance imaging in the diagnosis of pancreatic insulinoma: a clinical case. Al'manakh klinicheskoi meditsiny = Almanac of Clinical Medicine. 2018;46(3):289–295. (In Russ.) EDN XULSYH. https://doi.org/10.18786/2072-0505-2018-46-3-289-295

2. Gubergits N.B., Krylova E.A., Gravirovskaya N.G. Structural features of the pancreas in patients with various clinical and morphological forms of chronic pancreatitis. Meditsinskii alfavit = The Medical Alphabet. 2019;2(13):34–38. (In Russ.) EDN QTPGGI. https://doi.org/10.33667/2078-5631-2019-2-13(388)-34-38

3. Belozerov V.A., Okhotnikov O.I., Korenevsky N.A., Grigoriev N.N. Models and algorithms of differential diagnosis of pancreatic nodules based on the results of endosonography using soft computing technology. Diagnosticheskaya i interventsionnaya radiologiya = Diagnostic and Interventional Radiology. 2023;17(1):49–58. (In Russ.) EDN OUQVUT. https://doi.org/10.25512/DIR.2023.17.1.05

4. Maksimova A.A. Analysis of medical data processing methods. Modelirovanie, optimizatsiya i informatsionnye tekhnologii = Modeling, Optimization and Information Technologies. 2016;(2):5. (In Russ.) EDN WHAYLP

5. Nesterov D.V., Rozengauz E.V. Comparative assessment of the image quality of the pancreas in spiral and dynamic computed tomography. Luchevaya diagnostika i terapiya = Radiation Diagnostics and Therapy. 2013;(1):58–62. (In Russ.) EDN PYZLBN

6. Nikolaeva I.V., Ramazan A B., Tsoi O.G. Ultrasound diagnosis of pancreatic cancer. Astana Medical Journal. 2019;(2):154–160. (In Russ.) EDN LPSYTM

7. Kandurova K.Y., Dremin V.V., Zherebtsov E.A., et al. Optical biopsy methods and their application prospects for intraoperative analysis of tissue metabolism and blood microcirculation in minimally invasive surgery. Regionarnoe krovoobrashchenie i mikrotsirkulyatsiya = Regional Blood Circulation and Microcirculation. 2018;17:(3):71–79. (In Russ.) EDN YAUORV. https://doi.org/10.24884/1682-6655-2018-17-3-71-79

8. Barzenkov A.V. Hybrid intelligent system with elements of cognitive modeling for the diagnosis of pancreatic diseases. Perspektivy nauki = Perspectives of Science. 2019;(5):191–194. (In Russ.) EDN IAFBWC

9. Kozhukhar B.V. Fundamentals of medical image processing. Novaya nauka: Sovremennoe sostoyanie i puti razvitiya = New Science: Current State and Development Paths. 2016;(5-2):189–192. (In Russ.) EDN VVVPPB

10. Karmazanovsky G.G., Nrestyuk Y.I., Krieger A.G., Khairieva A.V. Diagnostic significance of three-dimensional CT image reconstructions in patients with ductal adenocarcinoma of the pancreas. Rossiiskii elektronnyi zhurnal luchevoi diagnostiki = Russian Electronic Journal of Radiation Diagnostics. 2017;7(1):69–76. (In Russ.) EDN YMFRXX. https://doi.org/10.21569/2222-7415-2017-7-1-69-76

11. Khoruzhik S.A., Mikhailov A.N. Fundamentals of CT imaging Part 2. Postprocessing image processing. Radiologiya – praktika = Radiology – Practice. 2011;(4):52–65. (In Russ.) EDN NYBQMX

12. Kondratova G.M., Mitkov V.V., Bryukhovetsky Y.A. Technology of three-dimensional ultrasound examination of the gallbladder. Ul'trazvukovaya i funktsional'naya diagnostika = Ultrasound and Functional Diagnostics. 2007;(3):14–27. (In Russ.) EDN JWWSNZ

13. Boyko D.A., Filatova A.E. Method of visualization of pathological structures on mammograms. Vestnik Natsional'nogo tekhnicheskogo universiteta Khar'kovskii politekhnicheskii institut. Seriya: Informatika i modelirovanie = Bulletin of the National Technical University Kharkiv Polytechnic Institute. Series: Computer Science and Modeling. 2013;(39):9–14. (In Russ.) EDN RCNMQJ

14. Dubrovin A.V., Koshkarov A.A. From PACS to teleradiology. Vrach i informatsionnye tekhnologii = Doctor and Information Technologies. 2017;(3):106–111. (In Russ.) EDN ZGYVPN

15. Kovalenko A.S., Pesentsali A.A., Tsarenko E.K. Preparation of medical images for processing in large information repositories. Kibernetika i vychislitel'naya tekhnika = Cybernetics and Computer Engineering. 2014;(2):46–53. (In Russ.) EDN QRQXTB

16. Holeva A.A., Aghababyan T.A., Nevolskikh A.A., et al. Possibilities of computed tomography in assessing the quality of surgical treatment in patients with tumors of the right half of the colon. Koloproktologiya = Coloproctology. 2024;23(3):87–99. (In Russ.) EDN YLQXDK. https://doi.org/10.33878/2073-7556-2024-23-3-87-99

17. Litvin A.A., Burkin D.A., Kropinov A.A., Paramzin F.N. Radiomics and texture analysis of digital images in oncology (review). Sovremennye tekhnologii v meditsine = Modern Technologies in Medicine. 2021;13(2):97–106. (In Russ.) EDN AITKVR. https://doi.org/10.17691/stm2021.13.2.11

18. Obukhova N.A., Motyko A.A. Methods of processing and analyzing medical TV images. Televidenie: peredacha i obrabotka izobrazhenii = Television: Transmission and Image Processing. 2016;(1):10–15. (In Russ.) EDN XINNSJ

19. Svyatnenko A.V., Demko A.E., Surov D.A., et al. The first experience of using augmented digital reality (AR) technology in reconstructive surgery of the bile ducts. Vestnik Natsional'nogo mediko-khirurgicheskogo tsentra im. N.I. Pirogova = Bulletin of the National Medical and Surgical Center named after N.I. Pirogov. 2024;19(2):159–163. (In Russ.) EDN XWMXXS. https://doi.org/10.25881/20728255_2024_19_2_159

20. Kozar R.V., Navrotsky A.A., Gurinovich A.B. Methods of recognition of medical images in computer diagnostics problems. Izvestiya Gomel'skogo gosudarstvennogo universiteta imeni F. Skoriny = Proceedings of Gomel State University named after F. Skoriny. 2020;(3):116–121. EDN HJRPNR