Русский
Automated system for supporting medical decision-making in the treatment of patients with renal parenchyma neoplasms – first experience of using the web-platform «Sechenov.AI_nephro» – results of multicenter testing
DOI: https://dx.doi.org/10.18565/urology.2024.5.12-22
Zholdubaev A.A., Glybochko P.V., Alyaev Yu.G., Butnaru D.V., Shpot E.V., Chernenky M.M., Chernenky I.M., Fiev D.N., Proskura A .V., Konyshev A.V., Sirota E.S., Ismailov Kh.M., Shurygina R.K., Amrakhov S.A., Izmailova A.A., Sarkisyan I.P., Suvorov A.Yu., Pavlov V.N., Kabirov I.R., Urmantsev M.F., Baykov D.E., Itkulov A.F., Khafizov M.M., Gilmetdinov R.F., Antipina A.A., Rossolovsky A.N., Durnov D.A., Bobylev D.A., Ivanov S.D.
1) Institute of Urology and Reproductive Health, FGAOU VO I.M. Sechenov First Moscow State Medical University, Moscow, Russia; 2) Bashkir State Medical University of the Ministry of Health of Russia, Ufa, Russia; 3) Saratov State Medical University named after V.I. Razumovsky of the Ministry of Health of Russia, Saratov, Russia
Aim. To evaluate the automated medical decision support system «Sechenov.AI_nephro» in the treatment of patients with renal parenchymal tumors.
Materials and methods: The beta version of the web-platform «Sechenov.AI_nephro» consists of a neural network based on MONAI (Medical open network for AI) and a web interface, with algorithms classified based on segmentation data in manual mode using the 3D modeling program «Amira». A total of 441 patients with renal parenchymal tumors were included in the multicenter prospective study. Testing was carried out over 12 months in 3 urological centers: 358 (81.2%) patients from I.M. Sechenov First Moscow State Medical University, Moscow; 73 (16.6%) patients from Bashkir State Medical University; and 10 (2.3%) patients from Saratov State Medical University named after V.I. Razumovsky. In all cases, contrast-enhanced computed tomography (CT) was performed preoperatively. DICOM (Digital Imaging and Communications in Medicine) data of each patient's CT was uploaded to the web-platform «Sechenov.AI_nephro» for automatic construction of a 3D model of the tumor. The work of the web-platform «Sechenov.AI_nephro» was evaluated based on a questionnaire completed by surgeons who performed the surgical intervention. The questionnaire consisted of 14 questions, with a scoring system from 1 to 10 points. It was divided into 3 main sections, including first for assessment of the quality of work of the web-platform «Sechenov.AI_nephro»; second for evaluation of the use of the 3D model in communication with the patient, for surgical planning and intraoperative navigation; and third for analysis of the choice of useful data display mode, errors in constructing the 3D model.
Results. The questionnaire was completed in 253 (57.37% of 441) cases. The quality of 3D models was rated 7.8–9.4 points, and the use of the 3D model in communication with the patient, for surgical planning and intraoperative navigation was rated 7.8–9.4 points. The 3D models were constructed correctly in 70% of cases. The area of interest was the useful mode of 3D models display in surgical planning. Incorrectly constructed anatomical elements were veins in 25.5% and the tumor in 26.4% of cases, respectively.
Conclusion. The automated medical decision support system in the treatment of patients with renal parenchymal tumors «Sechenov.AI_nephro» demonstrated satisfactory quality of 3D reconstruction of pathological process. 3D models allow for personalized determination of the surgical tactic for treating patients with renal tumors.
Materials and methods: The beta version of the web-platform «Sechenov.AI_nephro» consists of a neural network based on MONAI (Medical open network for AI) and a web interface, with algorithms classified based on segmentation data in manual mode using the 3D modeling program «Amira». A total of 441 patients with renal parenchymal tumors were included in the multicenter prospective study. Testing was carried out over 12 months in 3 urological centers: 358 (81.2%) patients from I.M. Sechenov First Moscow State Medical University, Moscow; 73 (16.6%) patients from Bashkir State Medical University; and 10 (2.3%) patients from Saratov State Medical University named after V.I. Razumovsky. In all cases, contrast-enhanced computed tomography (CT) was performed preoperatively. DICOM (Digital Imaging and Communications in Medicine) data of each patient's CT was uploaded to the web-platform «Sechenov.AI_nephro» for automatic construction of a 3D model of the tumor. The work of the web-platform «Sechenov.AI_nephro» was evaluated based on a questionnaire completed by surgeons who performed the surgical intervention. The questionnaire consisted of 14 questions, with a scoring system from 1 to 10 points. It was divided into 3 main sections, including first for assessment of the quality of work of the web-platform «Sechenov.AI_nephro»; second for evaluation of the use of the 3D model in communication with the patient, for surgical planning and intraoperative navigation; and third for analysis of the choice of useful data display mode, errors in constructing the 3D model.
Results. The questionnaire was completed in 253 (57.37% of 441) cases. The quality of 3D models was rated 7.8–9.4 points, and the use of the 3D model in communication with the patient, for surgical planning and intraoperative navigation was rated 7.8–9.4 points. The 3D models were constructed correctly in 70% of cases. The area of interest was the useful mode of 3D models display in surgical planning. Incorrectly constructed anatomical elements were veins in 25.5% and the tumor in 26.4% of cases, respectively.
Conclusion. The automated medical decision support system in the treatment of patients with renal parenchymal tumors «Sechenov.AI_nephro» demonstrated satisfactory quality of 3D reconstruction of pathological process. 3D models allow for personalized determination of the surgical tactic for treating patients with renal tumors.
Keywords: computer vision, machine learning, artificial intelligence, 3D modeling, partial nephrectomy, kidney cancer
About the Autors
Corresponding author: A.A. Zholdubaev – urologist, Ph.D. student, Institute of Urology and Reproductive Health, FGAOU VO I.M. Sechenov First Moscow State Medical University, Moscow, Russia; е-mail: dr_agabek@mail.ru
Similar Articles
