Hong Liu

Hong Liu

Auto-generated profile, based on publicly available information

Hong Liu

Advanced Medical Imaging Center and School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2005 in Optics Letters
Verified
Journal Article
Closed access
PDF file
XWXizeng Wu
Xizeng Wu
HLHong Liu
Hong Liu
AYAimin Yan
Aimin Yan
Phase retrieval is the key to quantitative x-ray phase-contrast imaging. To retrieve the phase image of an x-ray wave field, in general one needs multiple phase-contrast images. We have made a new observation of phase-attenuation duality for soft tissues, and we show how only a single phase-contrast image is needed for successful phase retrieval based on this duality. The phase-retrieval formula based on a single phase-contrast image of inhomogeneous soft tissue is derived and presented. We show the striking enhancement of the tissue contrast in simulated phase images that this new approach produces.

25 June 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
XCXuxin Chen
Xuxin Chen
KZKe Zhang
Ke Zhang
NANeman Abdoli
Neman Abdoli
PGPatrik Gilley
Patrik Gilley
XWXimin Wang
Ximin Wang
YQYuchen Qiu
Yuchen Qiu
Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operations, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying or mapping corresponding breast lesion features computed from unregistered multiple mammograms. This motivated us to leverage the architecture of Multi-view Vision Transformers to capture long-range relationships of multiple mammograms from the same patient in one examination. For this purpose, we employed local transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts. The outputs from different views and sides were concatenated and fed into global transformer blocks, to jointly learn patch relationships between four images representing two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of mammograms, which included 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our four-image (two-view-two-side) transformer-based model achieves case classification performance with an area under ROC curve (AUC = 0.818 ± 0.039), which significantly outperforms AUC = 0.784 ± 0.016 achieved by the state-of-the-art multi-view CNNs (p = 0.009). It also outperforms two one-view-two-side models that achieve AUC of 0.724 ± 0.013 (CC view) and 0.769 ± 0.036 (MLO view), respectively. The study demonstrates the potential of using transformers to develop high-performing computer-aided diagnosis schemes that combine four mammograms.

16 November 2017 in Journal of X-Ray Science and Technology
Verified
Journal Article
Closed access
PDF file
LRLiqiang Ren
Liqiang Ren
BZBin Zheng
Bin Zheng
HLHong Liu
Hong Liu
BACKGROUND: Recent advances in photon counting detection technology have led to significant research interest in X-ray imaging. OBJECTIVE: As a tutorial level review, this paper covers a wide range of aspects related to X-ray photon counting detector characterization. METHODS: The tutorial begins with a detailed description of the working principle and operating modes of a pixelated X-ray photon counting detector with basic architecture and detection mechanism. Currently available methods and techniques for charactering major aspects including energy response, noise floor, energy resolution, count rate performance (detector efficiency), and charge sharing effect of photon counting detectors are comprehensively reviewed. Other characterization aspects such as point spread function (PSF), line spread function (LSF), contrast transfer function (CTF), modulation transfer function (MTF), noise power spectrum (NPS), detective quantum efficiency (DQE), bias voltage, radiation damage, and polarization effect are also remarked. RESULTS: A cadmium telluride (CdTe) pixelated photon counting detector is employed for part of the characterization demonstration and the results are presented. CONCLUSIONS: This review can serve as a tutorial for X-ray imaging researchers and investigators to understand, operate, characterize, and optimize photon counting detectors for a variety of applications.

1 February 2009 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
XWXingwei Wang
Xingwei Wang
Bin ZhengBin Zheng
Bin Zheng
SLShibo Li
Shibo Li
JMJohn J. Mulvihill
John J. Mulvihill
MWMarc C. Wood
Marc C. Wood
HLHong Liu
Hong Liu

9 October 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
MHMorteza Heidari
Morteza Heidari
SMSeyedehnafiseh Mirniaharikandehei
Seyedehnafiseh Mirniaharikandehei
WLWei Liu
Wei Liu
AHAlan B. Hollingsworth
Alan B. Hollingsworth
HLHong Liu
Hong Liu
Bin ZhengBin Zheng
Bin Zheng
This study aims to develop and evaluate a new computer-aided diagnosis (CADx) scheme based on analysis of global mammographic image features to predict likelihood of cases being malignant. An image dataset involving 1,959 cases was retrospectively assembled. Suspicious lesions were detected and biopsied in each case. Among them, 737 cases are malignant and 1,222 are benign. Each case includes four mammograms of craniocaudal and mediolateral oblique view of left and right breasts. CADx scheme is applied to pre-process mammograms, generate two image maps in frequency domain using discrete cosine transform and fast Fourier transform, compute bilateral image feature differences from left and right breasts, and apply a support vector machine (SVM) to predict likelihood of the case being malignant. Three sub-groups of image features were computed from the original mammograms and two transformation maps. Four SVMs using three sub-groups of image features and fusion of all features were trained and tested using a 10-fold cross-validation method. The computed areas under receiver operating characteristic curves (AUCs) range from 0.85 to 0.91 using image features computed from one of three sub-groups, respectively. By fusion of all image features computed in three sub-groups, the fourth SVM yields a significantly higher performance with AUC = 0.96±0.01 (p<; 0.01). This study demonstrates feasibility of developing a new global image feature analysis based CADx scheme of mammograms with high performance. By avoiding difficulty and possible errors in breast lesion segmentation, this new CADx approach is more efficient in development and potentially more robust in future application.

1 January 2016 in Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
Verified
Journal Article
Closed access
MGMuhammad U. Ghani
Muhammad U. Ghani
ZZZhongxing Zhou
Zhongxing Zhou
LRLiqiang Ren
Liqiang Ren
MWMolly Wong
Molly Wong
YLYuhua Li
Yuhua Li
HLHong Liu
Hong Liu