Algorithm for lung pathology detection in X-ray images using binary classification with emphasis on preprocessing

O b j e c t i v e s. The purpose of the work is automatic detection of lung lesions: cavities, infiltrates, and nodules on chest X-ray images. Also, the possibility of spatial localization of these lesions on the image is investigated.

M e t h o d s. Binary classification using deep convolutional neural networks and the Grad-CAM method are used. Re s u lt s. For the Xception model, the binary classification accuracy on the test dataset is 73.1% for cavities, 71.9% for infiltrates, and 72.8% for nodules. Heat maps with true positive outcomes for cavities and nodules are mostly understandable to radiologists. More research is needed to get heat maps for infiltrates that are understandable to experts.

Co n c l u s i o n. The average classification accuracy of the Xception model for three lesion types (cavities, infiltrates, and nodules) is equal to 72.6%. Heat maps associated with pathological processes in the lungs and lesion localization were constructed. Obtained results are good, but not excellent. Thus, further investigation should be done to improve the classification accuracy and quality of the heat maps.

1. Hansun S., Argha A., Liaw S.-T., Celler B. G., Marks G. B. Machine and deep learning for tuberculosis detection on chest X-rays: systematic literature review. Journal of Medical Internet Research, 3 July 2023, vol. 25, р. e43154. DOI: 10.2196/43154.

2. Acharya V., Dhiman G., Prakasha K., Bahadur P., Choraria A., …, Kautish S. AI-assisted tuberculosis detection and classification from chest X-rays using a deep learning normalization-free network model. Computational Intelligence and Neuroscience, 3 October 2022, vol. 2022, р. 2399428. DOI: 10.1155/2022/2399428.

3. Guo R., Passi K., Jain C. K. Tuberculosis diagnostics and localization in chest X-rays via deep learning models. Frontiers in Artificial Intelligence, 5 October 2020, vol. 3, р. 583427. DOI: 10.3389/frai.2020.583427.

4. Thomsen K., Christensen A. L., Iversen L., Lomholt H. B., Winther O. Deep learning for diagnostic binary classification of multiple-lesion skin diseases. Frontiers in Medicine, 2020, vol. 7, р. 574329. DOI: 10.3389/fmed.2020.574329.

5. Selvaraju R. R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, October 2019, vol. 128, no. 2, pp. 336–359. DOI: 10.1007/s11263-019-01228-7.

6. Rosenthal A., Gabrielian A., Engle E., Hurt D. E., Alexandru S., …, Tartakovsky M. The TB Portals: an open-access, web-based platform for global drug-resistant-tuberculosis data sharing and analysis. Journal of Clinical Microbiology, 2017, vol. 55, no. 11, pp. 3267–3282. DOI: 10.1128/jcm.01013-17.

7. Gabrielian A., Engle E., Harris M., Wollenberg K., Juarez-Espinosa O., ..., Tartakovsky M. TB DEPOT (Data Exploration Portal): A multi-domain tuberculosis data analysis resource. PLOS ONE, May 2019, vol. 14, no. 5, pp. 1–23. DOI: 10.1371/journal.pone.0217410.

8. Kosareva A., Paulenka D., Snezhko E. Chest X-ray image processing based on radiologists’ textual annotations. Open Semantic Technologies for Intelligent Systems (OSTIS): Conference Proceedings, Minsk, Belarus, 18–20 April 2024. Editorial board: V. V. Golenkov [et al.]. Belarusian State University of Informatics and Radioelectronics, vol. 8, pp. 293–302.

9. Snezhko E. V., Kovalev V. A., Kosareva A. A., Paulenka D. A. AI-based software for computer-assisted diagnosis of lung diseases using chest X-Ray and CT images. The 1st Exhibition-forum of the IT-academgrad "Artificial Intelligence in Belarus": Conference Proceedings, Minsk, 13–14 October 2022, pp. 80–87 (In Russ.).

10. Kovalev V. A., Tuzikov A. V., Snezhko E. V., Paulenka D. A. Software "AI-based software for computer-assisted diagnosis of lung diseases using chest X-Ray and CT images" (LungExpert). Computer program registration certificate No. 1619 dated 02.08.2023 (In Russ.). Available at: http://search.ncip.by/depon/index.php?pref=1&lng=ru&page=3&target=1771 (accessed 15.09.2024)

11. Chollet F. Xception: deep learning with depthwise separable convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017, рр. 1251–1258.

12. Nillmani, Sharma N., Saba L., Khanna N., Kalra M., …, Suri J. Segmentation-based classification deep learning model embedded with explainable AI for COVID-19 detection in chest X-ray scans. Diagnostics, September 2022, vol. 12, p. 2132. DOI: 10.3390/diagnostics12092132.