Yulia S. Busygina

Yulia S. Busygina

Auto-generated profile, based on publicly available information

Yulia S. Busygina

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2024 in Quantitative Imaging in Medicine and Surgery
Verified
Journal Article
Open access
PDF file
KAKirill Arzamasov
Kirill Arzamasov
YVYuriy Vasilev
Yuriy Vasilev
MZMaria A Zelenova
Maria A Zelenova
LPLev Pestrenin
Lev Pestrenin
YBYulia Busygina
Yulia Busygina
OOOlga Omelyanskaya
Olga Omelyanskaya
Background: The integration of artificial intelligence (AI) into medicine is growing, with some experts predicting its standalone use soon. However, skepticism remains due to limited positive outcomes from independent validations. This research evaluates AI software’s effectiveness in analyzing chest X-rays (CXR) to identify lung nodules, a possible lung cancer indicator. Methods: This retrospective study analyzed 7,670,212 record pairs from radiological exams conducted between 2020 and 2022 during the Moscow Computer Vision Experiment, focusing on CXR and computed tomography (CT) scans. All images were acquired during clinical routine. The final dataset comprised 100 CXR images (50 with lung nodules, 50 without), selected consecutively and based on inclusion and exclusion criteria, to evaluate the performance of all five AI-based solutions, participating in the Moscow Computer Vision Experiment and analyzing CXR. The evaluation was performed in 3 stages. In the first stage, the probability of a nodule in the lung obtained from AI services was compared with the Ground Truth (1—there is a nodule, 0—there is no nodule). In the second stage, 3 radiologists evaluated the segmentation of nodules performed by the AI services (1—nodule correctly segmented, 0—nodule incorrectly segmented or not segmented at all). In the third stage, the same radiologists additionally evaluated the classification of the nodules (1—nodule correctly segmented and classified, 0—all other cases). The results obtained in stages 2 and 3 were compared with Ground Truth, which was common to all three stages. For each stage, diagnostic accuracy metrics were calculated for each AI service. Results: Three software solutions (Celsus, Lunit INSIGHT CXR, and qXR) demonstrated diagnostic metrics that matched or surpassed the vendor specifications, and achieved the highest area under the receiver operating characteristic curve (AUC) of 0.956 [95% confidence interval (CI): 0.918 to 0.994]. However, when evaluated by three radiologists for accurate nodule segmentation and classification, all solutions performed below the vendor-declared metrics, with the highest AUC reaching 0.812 (95% CI: 0.744 to 0.879). Meanwhile, all AI services demonstrated 100% specificity at stages 2 and 3 of the study. Conclusions: To ensure the reliability and applicability of AI-based software, it is crucial to validate performance metrics using high-quality datasets and engage radiologists in the evaluation process. Developers are recommended to improve the accuracy of the underlying models before allowing the standalone use of the software for lung nodule detection. The dataset created during the study may be accessed at https://mosmed.ai/datasets/mosmeddatargogksnalichiemiotsutstviemlegochnihuzlovtipvii/.

3 March 2026 in Digital Diagnostics
Verified
Journal Article
Open access
PDF file
YVYuriy Vasilev
Yuriy Vasilev
AVAnton Vladzymyrskyy
Anton Vladzymyrskyy
OOOlga Omelyanskaya
Olga Omelyanskaya
IRIrina Raznitsyna
Irina Raznitsyna
YBYulia S. Busygina
Yulia S. Busygina
KAKirill Arzamasov
Kirill Arzamasov
BACKGROUND: Chest X-ray is a widely used and accessible screening method for lung pathology. However, its diagnostic capabilities, particularly for visualizing pulmonary nodules, are limited. Suboptimal detection of pulmonary nodules by radiologists on chest X-rays affects the timeliness of diagnosis and therapeutic outcomes. One approach to improving lung nodule detection in chest X-rays involves adopting novel techniques, particularly those based on artificial intelligence. Nevertheless, the diagnostic value of these technologies in clinical practice remains largely unresolved due to limited data on radiologists’ performance conventional metrics. AIM: To evaluate the diagnostic performance of 100 radiologists in identifying pulmonary nodules on chest X-rays. METHODS: Each of the 100 radiologists was asked to evaluate 100 chest radiographs, of which 50 showed abnormal findings and 50 were normal. The presence of pulmonary nodules was assessed using the following scale: Absent (0 on the probability scale), likely absent (0.25), uncertain (0.50), likely present (0.75), present (1.00). Validation of nodule presence or absence was performed by three expert physicians using a binary scale (0/1) based on chest CT performed within 14 days after chest X-ray. We assessed image interpretation time, the difference in performance between radiologists and expert physicians (expressed in absolute units as D), and the primary diagnostic accuracy metrics of the radiologists. RESULTS: The study yielded the following: ROC AUC: 0.858 ± 0.059, accuracy: 0.822 ± 0.048, sensitivity: 0.779 ± 0.097, and specificity: 0.864 ± 0.095. A negligible positive correlation was observed between expert accuracy and mean image interpretation time (Spearman correlation coefficient rs = 0.189) and a low positive correlation (rs = 0.344) between image interpretation time and the D value. CONCLUSION: These results can be used to assess the quality of automated detection systems under development and to evaluate the efficacy of alternative methods and approaches for pulmonary nodule detection.