Zobrazit v EDS

Fourier Transforms the way we see B-lines in Lung Ultrasound.

Uloženo v:
Podrobná bibliografie
Název: Fourier Transforms the way we see B-lines in Lung Ultrasound.
Autoři: Oliveira-Saraiva D, Leote J, Gonzalez FA, Cruz Garcia N, Ferreira HA
Zdroj: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference [Annu Int Conf IEEE Eng Med Biol Soc] 2025 Jul; Vol. 2025, pp. 1-6.
Způsob vydávání: Journal Article
Jazyk: English
Informace o časopise: Publisher: [IEEE] Country of Publication: United States NLM ID: 101763872 Publication Model: Print Cited Medium: Internet ISSN: 2694-0604 (Electronic) Linking ISSN: 23757477 NLM ISO Abbreviation: Annu Int Conf IEEE Eng Med Biol Soc Subsets: MEDLINE
Imprint Name(s): Original Publication: [Piscataway, NJ] : [IEEE], [2007]-
Výrazy ze slovníku MeSH: Fourier Analysis* , Lung*/diagnostic imaging , Image Processing, Computer-Assisted*/methods, Ultrasonography/methods ; Humans ; Algorithms
Abstrakt: This study presents a novel approach for identifying B-lines in lung ultrasound images using the fast Fourier transform and texture analysis. By analyzing the Fourier-transformed space (FT-space), we identified significant differences in energy distribution and pixel sum between images with and without B-lines. Selective filtering in the FT-space further confirmed that B-lines correspond to specific frequency components, enabling the extraction of three quantitative metrics: the pixel sum of the blocked FT-space region, the mean squared error between original and FT-filtered images, and the pixel sum of the corresponding difference image. This novel method offers a rapid, automated, and computationally efficient possible alternative to hardware-intensive methods, making it particularly suitable for point-of-care ultrasound (POCUS) applications in resource-limited settings. These findings highlight the potential of Fourier-based processing for identifying B-lines and supporting clinical decision-making.Clinical Relevance-This method provides a rapid, automated, and computationally efficient approach for identifying B-lines in lung ultrasound images, making it suitable for high-demand and resource-limited clinical settings.
Entry Date(s): Date Created: 20251203 Date Completed: 20251203 Latest Revision: 20251203
Update Code: 20251204
DOI: 10.1109/EMBC58623.2025.11251712
PMID: 41336465
Databáze: MEDLINE
Popis
Abstrakt:This study presents a novel approach for identifying B-lines in lung ultrasound images using the fast Fourier transform and texture analysis. By analyzing the Fourier-transformed space (FT-space), we identified significant differences in energy distribution and pixel sum between images with and without B-lines. Selective filtering in the FT-space further confirmed that B-lines correspond to specific frequency components, enabling the extraction of three quantitative metrics: the pixel sum of the blocked FT-space region, the mean squared error between original and FT-filtered images, and the pixel sum of the corresponding difference image. This novel method offers a rapid, automated, and computationally efficient possible alternative to hardware-intensive methods, making it particularly suitable for point-of-care ultrasound (POCUS) applications in resource-limited settings. These findings highlight the potential of Fourier-based processing for identifying B-lines and supporting clinical decision-making.Clinical Relevance-This method provides a rapid, automated, and computationally efficient approach for identifying B-lines in lung ultrasound images, making it suitable for high-demand and resource-limited clinical settings.
ISSN:2694-0604
DOI:10.1109/EMBC58623.2025.11251712