Ultrasound Confidence Maps of Intensity and Structure Based on Directed Acyclic Graphs and Artifact Models
This work aims to improve the reliability of ultrasound image analysis for medical professionals by assessing the certainty of individual pixel values, which is an incremental improvement to existing methods.
This paper addresses the challenge of inherent artifacts in ultrasound imaging by introducing novel confidence algorithms that analyze pixel values using a directed acyclic graph based on acoustic physical properties. The approach demonstrates unique capabilities compared to previous confidence-measurement algorithms in shadow-detection and image-compounding tasks.
Ultrasound imaging has been improving, but continues to suffer from inherent artifacts that are challenging to model, such as attenuation, shadowing, diffraction, speckle, etc. These artifacts can potentially confuse image analysis algorithms unless an attempt is made to assess the certainty of individual pixel values. Our novel confidence algorithms analyze pixel values using a directed acyclic graph based on acoustic physical properties of ultrasound imaging. We demonstrate unique capabilities of our approach and compare it against previous confidence-measurement algorithms for shadow-detection and image-compounding tasks.