Polina Bashkova

Polina Bashkova

Auto-generated profile, based on publicly available information

Polina Bashkova

Federal State Budgetary Institution “Novosibirsk Scientific Research Institute of Tuberculosis” of the Ministry of Health of the Russian Federation

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
15 November 2024
Verified
Conference Paper
Closed access
MBMargaret Benedichuk
Margaret Benedichuk
PBPolina Bashkova
Polina Bashkova
BTBair Nikolaevich Tuchinov
Bair Nikolaevich Tuchinov
This research delves into leveraging artificial intelligence for tuberculosis (TB) screening via chest radiography, addressing a persistent global health threat that impacts millions each year. The study's primary goal is to innovate remote diagnostic techniques that apply computer vision to facilitate early disease detection. This investigation critically evaluates convolutional neural networks, particularly ResNet50 and EfficientNet-B7, for their effectiveness in localizing and identifying pulmonary lesions. The findings reveal that ResNet50 excels in delineating lung structures, while EfficientNet-B7 outperforms in pathology identification. Both models, however, demonstrate pronounced sensitivity to image quality, often encountering difficulty in differentiating pathologies in complex anatomical regions. Achieving an impressive accuracy of approximately 99.6% on publicly accessible datasets, the models experienced a performance reduction to 79.3% on private clinical datasets, underscoring the variability in model efficacy across different data sources. The study underscores the critical role of explainable AI (XAI) methods, including Grad-CAM, Captum, and SHAP, in enhancing interpretability and aiding clinicians in comprehending the decision-making pathways of AI models. In sum, this research highlights AI's potential in advancing TB screening while addressing inherent challenges related to image fidelity and model generalizability.

18 February 2026 in PULMONOLOGIYA
Verified
Journal Article
Closed access
NSN. V. Stavitskaya
N. V. Stavitskaya
PBP. V. Bashkova
P. V. Bashkova
ERE. G. Ronzhina
E. G. Ronzhina
IMI. Yu. Mentyukova-Suzdaltseva
I. Yu. Mentyukova-Suzdaltseva
NTN. V. Tursunova
N. V. Tursunova
EZE. M. Zhukova
E. M. Zhukova
Echinococcosis and alveococcosis of the lungs are zoonotic infections caused by the larval stage of Echinococcus helminths. The difficulty of diagnosing these helminth infections is due to their slow development and their similarity to several diseases, including malignant neoplasms and tuberculosis. Delay in making the correct diagnosis leads to the development of advanced cases and longer treatment. The aim of the review was to inform physiatrists, pulmonologists, infectious disease specialists, therapists, and thoracic surgeons about the complexity of the differential diagnosis of echinococcosis with atypical limited localization (with isolated lung damage). Conclusion. Diagnosis of echinococcosis presents significant difficulties due to the absence of symptoms pathognomonic for the parasitic process and a typical clinical manifestation of the disease, due to similarity with a number of nosologies of infectious and non-infectious origin, and absence of liver lesions and multilocular cysts, usually detected by CT or MRI. An immunological blood test for specific IgG should be performed at the early stages of diagnosis in patients without bacterial excretion, with suspected tuberculosis, and with an ambiguous clinical picture of pulmonary lesions. However, sometimes this blood test can be false negative because of a weak immune response.