Lung Segmentation in Chest X-ray Images using the Segment Anything Model (SAM)

• Gabriel Bellon de Carvalho UFSCar
• Jurandy Almeida UFSCar

DOI: https://doi.org/10.5753/sibgrapi.est.2024.31661

Resumo

The Segment Anything Model (SAM), introduced by Meta AI in April 2023, represents a cutting-edge tool designed to identify and separate individual objects within images through semantic interpretation. The advanced capabilities of SAM stem from its training on millions of images and masks. Shortly after its release, researchers began evaluating the model’s performance on medical images. With a focus on optimizing work in the healthcare field, this study proposes using SAM to evaluate and analyze X-ray images. To enhance the model’s performance on medical images, a transfer learning approach was employed, specifically through fine-tuning. This adjustment led to a substantial improvement in the evaluation metrics used to assess SAM’s performance compared to the masks provided by the datasets. The results achieved by the model after fine-tuning were satisfactory, demonstrating performance close to that of renowned neural networks for this task, such as U-Net.

Referências

A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W. Lo, P. Dollár, and R. B. Girshick, “Segment anything,” CoRR, vol. abs/2304.02643, 2023. [Online]. Available: DOI: 10.48550/arXiv.2304.02643

Y. Huang, X. Yang, L. Liu, H. Zhou, A. Chang, X. Zhou, R. Chen, J. Yu, J. Chen, C. Chen, S. Liu, H. Chi, X. Hu, K. Yue, L. Li, V. Grau, D. Fan, F. Dong, and D. Ni, “Segment anything model for medical images?” Medical Image Anal., vol. 92, p. 103061, 2024. [Online]. Available: DOI: 10.1016/j.media.2023.103061

M. A. Mazurowski, H. Dong, H. Gu, J. Yang, N. Konz, and Y. Zhang, “Segment anything model for medical image analysis: An experimental study,” Medical Image Anal., vol. 89, p. 102918, 2023. [Online]. Available: DOI: 10.1016/j.media.2023.102918

S. Jaeger, S. Candemir, S. Antani, Y.-X. J. Wáng, P. X. Lu, and G. Thoma, “Two public chest X-ray datasets for computer-aided screening of pulmonary diseases,” Quant Imaging Med Surg, vol. 4, no. 6, pp. 475–477, Dec 2014.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 - 18th International Conference Munich, Germany, October 5 - 9, 2015, Proceedings, Part III, ser. Lecture Notes in Computer Science, N. Navab, J. Hornegger, W. M. W. III, and A. F. Frangi, Eds., vol. 9351. Springer, 2015, pp. 234–241. [Online]. Available: DOI: 10.1007/978-3-319-24574-4_28

J. Ma, Y. He, F. Li, L. Han, C. You, and B. Wang, “Segment anything in medical images,” Nature Communications, vol. 15, no. 1, p. 654, 2024. [Online]. Available: DOI: 10.1038/s41467-024-44824-z

S. He, R. Bao, J. Li, P. E. Grant, and Y. Ou, “Accuracy of segment-anything model (SAM) in medical image segmentation tasks,” CoRR, vol. abs/2304.09324, 2023. [Online]. Available: DOI: 10.48550/arXiv.2304.09324

E. R. C. Q. Brioso, “Anatomical segmentation in automated chest radiography screening,” Ph.D. dissertation, Faculdade de Engenharia da Universidade do Porto, Porto, Portugal, July 2022, outras ciências da engenharia e tecnologias, openAccess. [Online]. Available: [link]