TY - GEN

T1 - Computer Vision and Explainable Approaches for Chest Tuberculosis Screenings

AU - Benedichuk, Margarita

AU - Bashkova, Polina

AU - Tuchinov, Bair

N1 - Conference code: 3

PY - 2024

Y1 - 2024

N2 - 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.

AB - 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.

KW - Artificial Intelligence

KW - Chest X-Ray

KW - Explainable AI

KW - Medical Imaging

KW - Tuberculosis Screening

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85216579767&origin=inward&txGid=e3d2c0a79a2a9f80ab62e97f4c08041c

UR - https://www.mendeley.com/catalogue/dc883612-f133-335a-ba09-4e128bb054f0/

U2 - 10.1109/PIERE62470.2024.10804967

DO - 10.1109/PIERE62470.2024.10804967

M3 - Conference contribution

SN - 979-8-3315-1633-8

SP - 820

EP - 823

BT - Proceedings of the IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering, PIERE 2024

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Problems of Informatics, Electronics and Radio Engineering

Y2 - 15 November 2024 through 17 November 2024

ER -