Keywords: computer vision, medical images, classification, detection, segmentation, neural networks, computed tomography, urolithiasis
The use of artificial neural networks to search for objects in medical images
UDC 004.931
DOI: 10.26102/2310-6018/2024.46.3.013
The article is devoted to the use of artificial neural network technologies to identify objects in medical images, including images of human internal organs obtained as a result of a computed tomography procedure. The purpose of this study was to select a method for analyzing medical images and its implementation in a decision support system in surgery and urology when diagnosing human urolithiasis. The article examines the applicability of classification, detection and segmentation methods for solving various problems of object detection in medical images. It has been shown that detection is best suited for use in a medical decision support system for diagnosing urolithiasis for the purpose of planning further surgical intervention. Therefore, the article discusses the main modern neural network architectures applicable to solving the detection problem. To solve the problem of detecting objects in medical images obtained from the results of computed tomography of human internal organs, the feasibility of using a neural network of the YOLO architecture is justified. Based on the results of a computational experiment, problem areas associated with the detection of kidney objects and stones by the YOLO network were identified. To increase the accuracy of the method, it is proposed to use an algorithm for fuzzy estimation of object detection results using a neural network of the YOLO architecture. The results of image detection by the YOLO neural network after its modification allow further calculations of the parameters of the found objects for planning surgical intervention.
1. Meldo A.A., Utkin L.V., Trofimova T.N. Artificial intelligence in medicine: current state and main directions of development of the intellectual diagnostics. Luchevaya diagnostika i terapiya = Diagnostic radiology and radiotherapy. 2020;11(1):9–17. (In Russ.). https://doi.org/10.22328/2079-5343-2020-11-1-9-17
2. Abbasov I.B., Deshmukh R.R. Application of artificial intelligence for medical imaging. Mezhdunarodnyi nauchno-issledovatel'skii zhurnal = International Research Journal. 2021;(12-1):43–49. (In Russ.). https://doi.org/10.23670/IRJ.2021.114.12.005
3. Kozar R.V., Naurotsky A.A., Gourinovitch A.B. Recognition methods for medical images in tasks of computer diagnostics. Izvestiya Gomel'skogo gosudarstvennogo universiteta imeni F. Skoriny = Proceedings of Francisk Scorina Gomel State University. 2020;(3):116–121. (In Russ.).
4. Huynh Q.T., Nguyen P.H., Le H.X., Ngo L.T., Trinh N.-T., Tran M.T.-T., Nguyen H.T., Vu N.T., Nguyen A.T., Suda K. et al. Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence. Diagnostics. 2022;12(8). https://doi.org/10.3390/diagnostics12081879
5. Burdin D.V., Rudenko M.A. An Intelligent System for Analyzing and Evaluating Medical Images to Support Medical Decision-making. Nanoindustriya = Nanoindustry. 2021;14(S7):821–822. (In Russ.). https://doi.org/10.22184/1993-8578.2021.14.7s.821.822
6. Rudenko M.A., Rudenko A.V. Fuzzy model for classification of medical images based on neural networks. Mezhdunarodnaya konferentsiya po myagkim vychisleniyam i izmereniyam. 2021;1:336–339. (In Russ.).
7. Rudenko M.A., Rudenko A.V., Krapivina M.A., Lisovsky V.S. System for detecting and analyzing objects on CT images in urology. In: III Mezhdunarodnaya konferentsiya po neironnym setyam i neirotekhnologiyam (NEURONT'2022), 16 June 2022, Saint Petersburg, Russia. Saint Petersburg: Saint Petersburg Electrotechnical University "LETI"; 2022. pp. 38–42. (In Russ.).
8. Shubkin E.O. Obzor metodov segmentatsii meditsinskikh izobrazhenii. In: Molodezh' i sovremennye informatsionnye tekhnologii: Sbornik trudov XVIII Mezhdunarodnoi nauchno-prakticheskoi konferentsii studentov, aspirantov i molodykh uchenykh, 22–26 March 2021, Tomsk, Russia. Tomsk: National Research Tomsk Polytechnic University; 2021. pp. 90–91. (In Russ.).
9. Belozerov I.A., Sudakov V.A. Investigation of machine learning models for medical image segmentation. Preprinty IPM im. M.V. Keldysha = Keldysh Institute Preprints. 2022;(37). (In Russ.). https://doi.org/10.20948/prepr-2022-37
10. Maguolo G., Nanni L. A critic evaluation of methods for COVID-19 automatic detection from X-ray images. Information Fusion. 2021;76:1–7. https://doi.org/10.1016/j.inffus.2021.04.008
11. Tse Z.T.H., Hovet S., Ren H., Barrett T., Xu S., Turkbey B., Wood B.J. AI-Assisted CT as a Clinical and Research Tool for COVID-19. Frontiers in Artificial Intelligence. 2021;4. https://doi.org/10.3389/frai.2021.590189
12. Shagalova P.A., Erofeeva A.D., Orlova M.M., Chistyakova Yu.S., Sokolova E.S. Research of application of imaging preprocessing algorithms for improving efficiency of recognition of medical pictures. Trudy NGTU im. R.E. Alekseeva = Transactions of NNSTU n.a. R.E. Alekseev. 2020;(1):25–32. (In Russ.). https://doi.org/10.46960/1816-210X_2020_1_25
13. Boominathan L., Kruthiventi S.S., BabuvR.V. CrowdNet: A Deep Convolutional Network for Dense Crowd Counting. In: MM '16: ACM Multimedia Conference: Proceedings of the 24th ACM international conference on Multimedia, 15–19 October 2016, Amsterdam, The Netherlands. New York: Association for Computing Machinery; 2016. pp. 640–644. https://doi.org/10.1145/2964284.2967300
14. Wang C.-Y., Yeh I.-H., Liao H.-Y.M. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. URL: https://doi.org/10.48550/arXiv.2402.13616 [Accessed 12th June 2024].
15. Pranovich A.A., Ismailov A.K., Karelskaya N.A., Kostin A.A., Karmazanovsky G.G., Gritskevich A.A. Artificial intelligence in the diagnosis and treatment of kidney stone disease. Rossiiskii zhurnal telemeditsiny i elektronnogo zdravookhraneniya = Russian Journal of Telemedicine and E-Health. 2022;8(1):42–57. (In Russ.). https://doi.org/10.29188/2712-9217-2022-8-1-42-57
16. Rudenko A.V., Rudenko M.A., Kashirina I.L. Mechanism for evaluating the results of detection and classification of objects in medical images. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyi analiz i informatsionnye tekhnologii = Proceedings of Voronezh State University. Series: Systems Analysis and Information Technologies. 2024;(1):137–148. (In Russ.). https://doi.org/10.17308/sait/1995-5499/2024/1/137-148
17. Rudenko A.V., Rudenko M.A., Kashirina I.L. Algorithms for 3D reconstruction and calculation of object parameters based on the results of detection in medical images. Modelirovanie, optimizatsiya i informatsionnye tekhnologii = Modeling, Optimization and Information Technology. 2024;12(2). (In Russ.). URL: https://moitvivt.ru/ru/journal/pdf?id=1594
Keywords: computer vision, medical images, classification, detection, segmentation, neural networks, computed tomography, urolithiasis
For citation: Rudenko A.V. Rudenko M.A. Kashirina I.L. The use of artificial neural networks to search for objects in medical images. Modeling, Optimization and Information Technology. 2024;12(3). Available from: https://moitvivt.ru/ru/journal/pdf?id=1630 DOI: 10.26102/2310-6018/2024.46.3.013 (In Russ).
Received 14.07.2024
Revised 22.07.2024
Accepted 30.07.2024