Tuberculosis Detection in X-Ray Images Using Deep Learning and Contrast-Enhanced Sharp Edge Detection
Keywords:
Canny edge detection, Contrast-enhanced, Deep learning, Ensemble classification, Medical imaging, Tuberculosis diagnosisAbstract
Tuberculosis (TB) is a life-threatening disease if not diagnosed and treated promptly. The use of ensemble deep learning processes has shown promise for the early noticing of TB. Traditionally, ensemble classifiers were skilled using images with similar characteristics, which limited their performance. Effective ensemble learning requires diverse error sources, which can be achieved through varying classification methods or input feature sets. This study emphasizes the latter approach by introducing a method for TB finding using deep learning with X-ray images enhanced through contrast Canny Edge Detection (CEED-Canny). CEED-Canny generated edge-detected lung radiographs, providing two distinct feature sets: one obtained from the enhanced X-ray images and the different` from the edge-detected versions. This feature diversity improved error variation among base classifiers, leading to enhanced detection accuracy.
References
C. Dubois,D. Eigen, E. Delmas, M. Einfalt, “Deep learning in medical image analysis: introduction to underlying principles and reviewer guide using diagnostic case studies in paediatrics,” BMJ, pp. e076703–e076703, Nov. 2024, doi: https://doi.org/10.1136/bmj-2023-076703.
C.-F. Chen et al., “A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography,” Scientific Reports, vol. 14, no. 1, Jun. 2024, doi: https://doi.org/10.1038/s41598-024-65703-z.
D. Capellán-Martín, J. J. Gómez-Valverde, D. Bermejo-Peláez, and M. J. Ledesma-Carbayo, “A Lightweight, Rapid and Efficient Deep Convolutional Network for Chest X-Ray Tuberculosis Detection,” 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1–5, Apr. 2023, doi: https://doi.org/10.1109/isbi53787.2023.10230500.
D. Capellán-Martín et al., “Deep learning-based lung segmentation and automatic regional template in chest x-ray images for pediatric tuberculosis,” Medical Imaging 2018: Computer-Aided Diagnosis, pp. 65–65, Apr. 2023, doi: https://doi.org/10.1117/12.2652626.
A. Tiwari and Alok Katiyar, “Hybrid deep learning assisted chest X-ray image segmentation and classification for tuberculosis disease diagnosis,” Intelligent Decision Technologies, vol. 18, no. 1, pp. 561–569, Feb. 2024, doi: https://doi.org/10.3233/idt-230286.
S.-J. Heo ,Y. Kim, S. Yun, S. Lim, J. Kim, “Deep Learning Algorithms with Demographic Information Help to Detect Tuberculosis in Chest Radiographs in Annual Workers’ Health Examination Data,” International Journal of Environmental Research and Public Health, vol. 16, no. 2, p. 250, Jan. 2019, doi: https://doi.org/10.3390/ijerph16020250.
E. J. Hwang ,S. Park,K. N. Jin,J. I. Kim,“Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs,” Clinical Infectious Diseases, vol. 69, no. 5, pp. 739–747, Nov. 2018, doi: https://doi.org/10.1093/cid/ciy967.
F. Pasa, V. Golkov, F. Pfeiffer, D. Cremers, and D. Pfeiffer, “Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization,” Scientific Reports, vol. 9, no. 1, Apr. 2019, doi: https://doi.org/10.1038/s41598-019-42557-4.
S. S. Meraj, R. Yaakob, A. Azman, S. N. Mohd Rum, and A. S. Ahmad Nazri, “Artificial Intelligence in Diagnosing Tuberculosis: A Review,” International Journal on Advanced Science, Engineering, and Information Technology, vol. 9, no. 1, p. 81, Jan. 2019, doi: https://doi.org/10.18517/ijaseit.9.1.7567.
Q. H. Nguyen.,B. P. Nguyen, S. D. Dao, B. Unnikrishnan, "Deep Learning Models for Tuberculosis Detection from Chest X-ray Images," 2019 26th International Conference on Telecommunications (ICT), Hanoi, Vietnam, 2019, pp. 381-385, doi: https://doi.org/10.1109/ICT.2019.8798798.
S. Vajda ,A. Karargyris,S. Jaeger, K. C. Santosh, S. Candemir, “Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs,” Journal of Medical Systems, vol. 42, no. 8, Jun. 2018, doi: https://doi.org/10.1007/s10916-018-0991-9.
R. Rashid, S. G. Khawaja, M. U. Akram and A. M. Khan, "Hybrid RID Network for Efficient Diagnosis of Tuberculosis from Chest X-rays," 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), Cairo, Egypt, 2018, pp. 167-170, doi: https://doi.org/10.1109/CIBEC.2018.8641816.
P. Lakhani and B. Sundaram, “Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks,” Radiology, vol. 284, no. 2, pp. 574–582, Aug. 2017, doi: https://doi.org/10.1148/radiol.2017162326.
M. T. Islam, A. Md Abdul, A. T. Minhaz, and K. Ashraf, “Abnormality Detection and Localization in Chest X-Rays using Deep Convolutional Neural Networks,” arXiv (Cornell University), Jan. 2017, doi: https://doi.org/10.48550/arxiv.1705.09850.
G. Litjens , T. Kooi, B. E. Bejnordi, A. A. A. Setio, “A Survey on Deep Learning in Medical Image Analysis,” Medical Image Analysis, vol. 42, no. 1, pp. 60–88, Dec. 2017, doi: https://doi.org/10.1016/j.media.2017.07.005.
