期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 39, 期 6, 页码 2277-2286出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.2970867
关键词
Clinical ultrasound; CycleGAN; image enhancement; MimickNet; ultrasound post-processing
类别
资金
- National Institute of Biomedical Imaging and Bioengineering [R01-EB026574]
- National Institute of Health [5T32GM007171-44]
Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast). These post-processing techniques vary across manufacturers and are generally kept proprietary, which presents a challenge for researchers looking to match current clinical-grade workflows. We introduce a deep learning framework, MimickNet, that transforms conventional delay-and-summed (DAS) beams into the approximate Dynamic Tissue Contrast Enhanced (DTCE (TM)) post-processed images found on Siemens clinical-grade scanners. Training MimickNet only requires post-processed image samples from a scanner of interest without the need for explicit pairing to DAS data. This flexibility allows MimickNet to hypothetically approximate any manufacturer's post-processing without access to the pre-processed data. MimickNet post-processing achieves a 0.940 +/- 0.018 structural similarity index measurement (SSIM) compared to clinical-grade post-processing on a 400 cine-loop test set, 0.937 +/- 0.025 SSIM on a prospectively acquired dataset, and 0.928 +/- 0.003 SSIM on an out-of-distribution cardiac cine-loop after gain adjustment. To our knowledge, this is the first work to establish deep learning models that closely approximate ultrasound post-processing found in current medical practice. MimickNet serves as a clinical post-processing baseline for future works in ultrasound image formation to compare against. Additionally, it can be used as a pretrained model for fine-tuning towards different post-processing techniques. To this end, we have made the MimickNet software, phantom data, and permitted in vivo data open-source at https://github.com/ouwen/MimickNet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据