AUTOMATIC CHEST X-RAY REGION EXTRACTION FROM SMARTPHONE-CAPTURED IMAGES FOR AI-BASED CLINICAL DECISION SUPPORT

Esbergenov H. S.


Annotatsiya

Chest X-ray imaging is essential for diagnosing pulmonary diseases, but the increasing use of smartphone-captured images in resource-limited settings introduces distortions and noise that degrade AI diagnostic accuracy. This study presents an automated framework for chest X-ray region extraction designed to segment the clinically relevant area from photographs of films or screens. By isolating the chest region and removing irrelevant backgrounds, this preprocessing module provides standardized, high-quality inputs for downstream AI models. Experimental results demonstrate that this segmentation significantly enhances model robustness, interpretability, and diagnostic performance, offering a practical solution for improving AI-driven clinical tools in real-world environments.


Adabiyotlar

  1. World Health Organization, Chest Radiography in Tuberculosis Detection, WHO Press, 2020.
  2. R. M. Summers, “Pulmonary imaging and diagnosis,” Radiology, vol. 298, no. 2, pp. 345–357, 2021.
  3. P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, 2017.
  4. L. Oakden-Rayner, “Exploring the limitations of deep learning for medical image analysis,” Journal of Digital Imaging, vol. 33, pp. 150–160, 2020.
  5. J. Irvin et al., “CheXpert: A large chest radiograph dataset with uncertainty labels,” AAAI, 2019.
  6. S. Winkler et al., “Impact of image quality on deep learning in radiology,” European Radiology, vol. 31, pp. 6852–6861, 2021.
  7. R. Gonzalez and R. Woods, Digital Image Processing, 4th ed., Pearson, 2018.
  8. O. Ronneberger et al., “U-Net: Convolutional networks for biomedical image segmentation,” MICCAI, 2015.
  9. S. Candemir et al., “Lung boundary detection in chest X-rays,” IEEE Transactions on Medical Imaging, vol. 34, no. 10, 2015.
  10. A. Kumar et al., “Smartphone-based medical imaging: A review,” Healthcare Technology Letters, vol. 6, no. 5, 2019.
  11. J. Redmon et al., “You Only Look Once: Unified, real-time object detection,” CVPR, 2016.
  12. K. T. Schlegel et al., “Interpretability in deep learning for medical imaging,” Nature Machine Intelligence, 2022.