Self-supervised learning for accelerated 3D high-resolution ultrasound imaging

Published on Jul 1, 2021in Medical Physics4.071
· DOI :10.1002/MP.14946
Xiaofeng Yang29
Estimated H-index: 29
(Emory University)
Sources
Abstract
Purpose Ultrasound (US) imaging has been widely used in diagnosis, image-guided intervention and therapy, where high-quality three-dimensional (3D) images are highly desired from sparsely acquired two-dimensional (2D) images. This study aims to develop a deep learning-based algorithm to reconstruct high-resolution 3D US images only reliant on the acquired sparsely distributed 2D images. Methods We propose a self-supervised learning framework using cycle consistent generative adversarial network (cycleGAN), where two independent cycleGAN models are respectively trained with paired original US images and two sets of low-resolution US images. The two sets of low-resolution US images are respectively obtained through down sampling the original US images along the two axes. In US imaging, in-plane spatial resolution is generally much higher than through-plane resolution. By learning the mapping from down-sampled in-plane low-resolution images to original high-resolution US images, cycleGAN can generate through-plane high-resolution images from original sparely distributed 2D images. Finally, high-resolution 3D US images are reconstructed by combining the generated 2D images from the two cycleGAN models. Results The proposed method was assessed on two different datasets. One is automatic breast ultrasound (ABUS) images from 70 breast cancer patients, the other is collected from 45 prostate cancer patients. By applying a spatial resolution enhancement factor of 3 to the breast cases, our proposed method achieved the mean absolute error (MAE) value of 0.90±0.15, the peak signal-to-noise ratio (PSNR) value of 37.88±0.88 dB, and the visual information fidelity (VIF) value of 0.69±0.01, which significantly outperforms bicubic interpolation. Similar performances have been achieved using the enhancement factor of 5 in these breast cases and using the enhancement factor of 5 and 10 in the prostate cases. Conclusions We have proposed and investigated a new deep learning-based algorithm for reconstructing high-resolution 3D US images from sparely acquired 2D images. Significant improvement on through-plane resolution has been achieved by only using the acquired 2D images without any external atlas images. Its self-supervision capability could accelerate high-resolution US imaging.
📖 Papers frequently viewed together
2020
7 Authors (Xiaofeng Yang)
2021
7 Authors (Xiaofeng Yang)
2020
8 Authors (Xiaofeng Yang)
References48
Newest
#1Meghan G. Lubner (UW: University of Wisconsin-Madison)H-Index: 31
#2Lori Mankowski Gettle (UW: University of Wisconsin-Madison)H-Index: 9
Last. Perry J. Pickhardt (UW: University of Wisconsin-Madison)H-Index: 76
view all 6 authors...
Intraoperative ultrasound (IOUS) is a valuable adjunctive tool that can provide real-time diagnostic information in surgery that has the potential to alter patient management and decrease complications. Lesion localization, characterization and staging can be performed, as well as surveying for additional lesions and metastatic disease. IOUS is commonly used in the liver for hepatic metastatic disease and hepatocellular carcinoma, in the pancreas for neuroendocrine tumors, and in the kidney for ...
Source
#4Jacob F. Wynne (Emory University)H-Index: 6
#7Xiaofeng Yang (Emory University)H-Index: 29
This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were then summarized with discussion.
Source
#1Jovan Mitrovic (UR: University of Rochester)H-Index: 2
#2Zeljko Ignjatovic (UR: University of Rochester)H-Index: 10
Last. Vikram S. Dogra (UR: University of Rochester)H-Index: 33
view all 5 authors...
Abstract In this work, a compressed sensing method to reduce hardware complexity of ultrasound imaging systems is proposed and experimentally verified. We provide clinical evaluation of the method with a possible high compression rates (up to 64 RF signals compressed into a single channel on receive) which uses elastic net estimation for decoding stage. This allows a reduction in size and power consumption of the front-end electronics with only a minor loss in image quality. We demonstrate an 8-...
Source
#1Ge WangH-Index: 81
#2Jong Chul YeH-Index: 53
Last. Bruno De ManH-Index: 20
view all 3 authors...
Deep-learning-based tomographic imaging is an important application of artificial intelligence and a new frontier of machine learning. Deep learning has been widely used in computer vision and image analysis, which deal with existing images, improve these images, and produce features from them. Since 2016, deep learning techniques have been actively researched for tomographic imaging, especially in the context of biomedicine, with impressive results and great potential. Tomographic reconstructio...
Source
#7Xiaofeng Yang (Emory University)H-Index: 29
PURPOSE Complementary information obtained from multiple contrasts of tissue facilitates physicians assessing, diagnosing and planning treatment of a variety of diseases. However, acquiring multiple contrasts magnetic resonance images (MRI) for every patient using multiple pulse sequences is time-consuming and expensive, where, medical image synthesis has been demonstrated as an effective alternative. The purpose of this study is to develop a unified framework for multimodal MR image synthesis. ...
Source
Correcting or reducing the effects of voxel intensity non-uniformity (INU) within a given tissue type is a crucial issue for quantitative magnetic resonance (MR) image analysis in daily clinical practice. Although having no severe impact on visual diagnosis, the INU can highly degrade the performance of automatic quantitative analysis such as segmentation, registration, feature extraction and radiomics. In this study, we present an advanced deep learning based INU correction algorithm called res...
Source
#2Yang Lei (Emory University)H-Index: 8
#6Xiaofeng Yang (Emory University)H-Index: 29
This paper presents a review of deep learning (DL) based medical image registration methods. We summarized the latest developments and applications of DL-based registration methods in the medical field. These methods were classified into seven categories according to their methods, functions and popularity. A detailed review of each category was presented, highlighting important contributions and identifying specific challenges. A short assessment was presented following the detailed review of e...
Source
#10Xiaofeng Yang (Emory University)H-Index: 29
PURPOSE High-dose-rate (HDR) brachytherapy is an established technique to be used as monotherapy option or focal boost in conjunction with external beam radiation therapy (EBRT) for treating prostate cancer. Radiation source path reconstruction is a critical procedure in HDR treatment planning. Manually identifying the source path is labor intensive and timely inefficient. Recent years, magnetic resonance imaging (MRI) becomes a valuable imaging modality for image-guided HDR prostate brachythera...
Source
#1Shiying WangH-Index: 11
#2John A. HossackH-Index: 33
Last. Alexander L. KlibanovH-Index: 72
view all 3 authors...
Ultrasound is the most widely used medical imaging modality worldwide. It is abundant, extremely safe, portable, and inexpensive. In this review, we consider some of the current development trends for ultrasound imaging, which build upon its current strength and the popularity it experiences among medical imaging professional users.Ultrasound has rapidly expanded beyond traditional radiology departments and cardiology practices. Computing power and data processing capabilities of commonly availa...
Source
Limitations on bandwidth and power consumption impose strict bounds on data rates of diagnostic imaging systems. Consequently, the design of suitable (i.e. task- and data-aware) compression and reconstruction techniques has attracted considerable attention in recent years. Compressed sensing emerged as a popular framework for sparse signal reconstruction from a small set of compressed measurements. However, typical compressed sensing designs measure a (non)linearly weighted combination of all in...
Source
Cited By1
Newest
#10Xiaofeng Yang (Emory University)H-Index: 29
PURPOSE Auto-segmentation algorithms offer a potential solution to eliminate the labor-intensive, time-consuming, and observer-dependent manual delineation of organs-at-risk (OARs) in radiotherapy treatment planning. This study aimed to develop a deep learning-based automated OAR delineation method to tackle the current challenges remaining in achieving reliable expert performance with the state-of-the-art auto-delineation algorithms. METHODS The accuracy of OAR delineation is expected to be imp...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.