Ultrasound Speckle Reduction via L0 Minimization
文献类型：会议论文
| 作者 | Lei Zhu; Weiming Wang; Xiaomeng Li; Qiong Wang; Jing Qin; Kin-Hong Wong; Pheng-Ann Heng |
| 出版日期 | 2016 |
| 会议名称 | ACCV |
| 会议地点 | 台北，台湾 |
| 英文摘要 | Speckle reduction is a crucial prerequisite of many computeraided ultrasound diagnosis and treatment systems. However, most of existing speckle reduction lters concentrate the blurring near features and introduced the hole artifacts, making the subsequent processing procedures complicated. Optimization-based methods can globally distribute such blurring, leading to better feature preservation. Motivated by this, we propose a novel optimization framework based on L0 minimization for feature preserving ultrasound speckle reduction. We observed that the GAP, which integrates gradient and phase information, is extremely sparser in despeckled images than in speckled images. Based on this observation, we propose the L0 minimization framework to remove speckle noise and simultaneously preserve features in ultrasound images. It seeks for the L0 sparsity of the GAP values, and such sparsity is achieved by reducing small GAP values to zero in an iterative manner. Since features have larger GAP magnitudes than speckle noise, the proposed L0 minimization is capable of e ectively suppressing the speckle noise. Meanwhile, the rest of GAP values corresponding to prominent features are kept unchanged, leading to better preservation of those features. In addition, we propose an e cient and robust numerical scheme to transform the original intractable L0 minimization into several sub-optimizations, from which we can quickly nd their closed-form solutions. Experiments on synthetic and clinical ultrasound images demonstrate that our approach outperforms other state-of-the-art despeckling methods in terms of noise removal and feature preservation. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10051]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2016 |
| 推荐引用方式 GB/T 7714 | Lei Zhu,Weiming Wang,Xiaomeng Li,et al. Ultrasound Speckle Reduction via L0 Minimization[C]. 见:ACCV. 台北，台湾. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。