Segmentation of ultrasound images with speckle modeling

Biomedical ultrasound is a popular modality for clinical diagnosis and treatment planning. In addition to low signal-to-noise ratio, ultrasound B-scans are characterized by speckle, which is also present in the ultrasound RF signal. Speckle has statistical properties that make them useful for potential clinical applications. This paper presents an approach to B-scan segmentation based on parameter maps of Nakagami and K distribution parameters. This approach, demonstrated on a simulated ultrasound envelope, may be used to complement B-scans to convey additional information from ultrasonographic data.