Experience in using artificial intelligence technologies to identify adrenal tumors on computed tomography

The paper provides an overview of the software available for the first quarter of 2024 based on artificial intelligence technologies (AI-based software) for identifying adrenal tumors on computed tomography of the chest and abdominal organs, used as part of an experiment on the use of innovative technologies in the field of computer vision for the analysis of medical images and further application in the healthcare system of the city of Moscow.Based on the results of testing on a prepared data set with signs of adrenal tumors, software based on AI achieved high levels of diagnostic accuracy metrics exceeding the stated indicators: area under the curve (AUC) up to 0.995 (AI-2 monoservice for analyzing ABP), specificity (C) up to 1.000 (AI-2 complex service for analysis of OGK), sensitivity (H) up to 1,000 (AI-2 monoservice for analysis of OBP and AI-2 complex for analysis of OBP).Thus, software based on AI for detecting adrenal tumors, having high sensitivity rates, can be used as an assistant to a radiologist to reduce the number of missed adrenal formations on CT of the abdominal organs and on CT of the chest, because during a CT scan of this area, the adrenal glands, as a rule, fall into the scanning field.