Skip to main content
Journal cover image

Lung segment anything model (LuSAM): a decoupled prompt-integrated framework for automated lung segmentation on chest x-Ray images.

Publication ,  Journal Article
Iytha Sridhar, R; Kamaleswaran, R
Published in: Biomed Phys Eng Express
July 10, 2024

Accurate lung segmentation in chest x-ray images plays a pivotal role in early disease detection and clinical decision-making. In this study, we introduce an innovative approach to enhance the precision of lung segmentation using the Segment Anything Model (SAM). Despite its versatility, SAM faces the challenge of prompt decoupling, often resulting in misclassifications, especially with intricate structures like the clavicle. Our research focuses on the integration of spatial attention mechanisms within SAM. This approach enables the model to concentrate specifically on the lung region, fostering adaptability to image variations and reducing the likelihood of false positives. This work has the potential to significantly advance lung segmentation, improving the identification and quantification of lung anomalies across diverse clinical contexts.

Duke Scholars

Published In

Biomed Phys Eng Express

DOI

EISSN

2057-1976

Publication Date

July 10, 2024

Volume

10

Issue

5

Location

England

Related Subject Headings

  • Tomography, X-Ray Computed
  • Radiography, Thoracic
  • Radiographic Image Interpretation, Computer-Assisted
  • Lung
  • Image Processing, Computer-Assisted
  • Humans
  • Algorithms
  • 4003 Biomedical engineering
  • 3206 Medical biotechnology
  • 1004 Medical Biotechnology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Iytha Sridhar, R., & Kamaleswaran, R. (2024). Lung segment anything model (LuSAM): a decoupled prompt-integrated framework for automated lung segmentation on chest x-Ray images. Biomed Phys Eng Express, 10(5). https://doi.org/10.1088/2057-1976/ad4f8f
Iytha Sridhar, Rishika, and Rishikesan Kamaleswaran. “Lung segment anything model (LuSAM): a decoupled prompt-integrated framework for automated lung segmentation on chest x-Ray images.Biomed Phys Eng Express 10, no. 5 (July 10, 2024). https://doi.org/10.1088/2057-1976/ad4f8f.
Iytha Sridhar, Rishika, and Rishikesan Kamaleswaran. “Lung segment anything model (LuSAM): a decoupled prompt-integrated framework for automated lung segmentation on chest x-Ray images.Biomed Phys Eng Express, vol. 10, no. 5, July 2024. Pubmed, doi:10.1088/2057-1976/ad4f8f.
Journal cover image

Published In

Biomed Phys Eng Express

DOI

EISSN

2057-1976

Publication Date

July 10, 2024

Volume

10

Issue

5

Location

England

Related Subject Headings

  • Tomography, X-Ray Computed
  • Radiography, Thoracic
  • Radiographic Image Interpretation, Computer-Assisted
  • Lung
  • Image Processing, Computer-Assisted
  • Humans
  • Algorithms
  • 4003 Biomedical engineering
  • 3206 Medical biotechnology
  • 1004 Medical Biotechnology