Improved Lesion Detection Using Nonlocal Means Post-Processing
| Autor: | Ole Marius Hoel Rindal, Tore Gruner Bjastad, Svein-Erik Måsøy, Alfonso Rodriguez-Molares |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Beamforming
Noise (signal processing) business.industry Computer science Pattern recognition Image processing 01 natural sciences Speckle pattern Signal-to-noise ratio 0103 physical sciences Coherence (signal processing) Artificial intelligence business 010301 acoustics Adaptive beamformer Coherence (physics) |
| Zdroj: | 2019-October Proceedings-IEEE Ultrasonics Symposium |
| ISSN: | 1948-5719 |
| Popis: | Software beamforming allows more flexible and complex algorithms, often referred to as adaptive beamforming techniques, that are blurring the boundaries between beamforming and image processing. Many adaptive beamforming algorithms claim to improve lesion detectability. Based on recent advances, we hypothesize that image processing techniques that reduce speckle variability yield better lesion detectability than state-of-the-art adaptive beamformers.This hypothesis is investigated on six algorithms: two image processing techniques, and four adaptive beamformers. As a target we use Field II simulations of a hypoechoic cyst with noise added to simulate different SNR conditions. Lesion detectability is estimated using the Generalized Contrast-to-Noise Ratio (GCNR). The results support our hypothesis. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|