Kai Wang

Kai Wang

Auto-generated profile, based on publicly available information

Kai Wang

Department of Radiation Oncology, UMMC, United States of America

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
13 July 2020 in Medical Physics
Verified
Journal Article
Closed access
PDF file
KWKai Wang
Kai Wang
ZZZhiguo Zhou
Zhiguo Zhou
RWRongfang Wang
Rongfang Wang
LCLiyuan Chen
Liyuan Chen
QZQiongwen Zhang
Qiongwen Zhang
JWJing Wang
Jing Wang

31 July 2020 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
ZZZhiguo Zhou
Zhiguo Zhou
KWKai Wang
Kai Wang
MFMichael Folkert
Michael Folkert
HLHui Liu
Hui Liu
SJSteve Jiang
Steve Jiang
JWJing Wang
Jing Wang
Accurately predicting distant metastasis in head & neck cancer has the potential to improve patient survival by allowing early treatment intensification with systemic therapy for high-risk patients. By extracting large amounts of quantitative features and mining them, radiomics has achieved success in predicting treatment outcomes for various diseases. However, there are several challenges associated with conventional radiomic approaches, including: (1) how to optimally combine information extracted from multiple modalities; (2) how to construct models emphasizing different objectives for different clinical applications; and (3) how to utilize and fuse output obtained by multiple classifiers. To overcome these challenges, we propose a unified model termed as multifaceted radiomics (M-radiomics). In M-radiomics, a deep learning with stacked sparse autoencoder is first utilized to fuse features extracted from different modalities into one representation feature set. A multi-objective optimization model is then introduced into M-radiomics where probability-based objective functions are designed to maximize the similarity between the probability output and the true label vector. Finally, M-radiomics employs multiple base classifiers to get a diverse Pareto-optimal model set and then fuses the output probabilities of all the Pareto-optimal models through an evidential reasoning rule fusion (ERRF) strategy in the testing stage to obtain the final output probability. Experimental results show that M-radiomics with the stacked autoencoder outperforms the model without the autoencoder. M-radiomics obtained more accurate results with a better balance between sensitivity and specificity than other single-objective or single-classifier-based models.

29 June 2022 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
HSHua-Chieh Shao
Hua-Chieh Shao
TLTian Li
Tian Li
MDMichael J Dohopolski
Michael J Dohopolski
JWJing Wang
Jing Wang
JCJing Cai
Jing Cai
YZYou Zhang
You Zhang
Purpose . Real-time three-dimensional (3D) magnetic resonance (MR) imaging is challenging because of slow MR signal acquisition, leading to highly under-sampled k-space data. Here, we proposed a deep learning-based, k-space-driven deformable registration network (KS-RegNet) for real-time 3D MR imaging. By incorporating prior information, KS-RegNet performs a deformable image registration between a fully-sampled prior image and on-board images acquired from highly-under-sampled k-space data, to generate high-quality on-board images for real-time motion tracking. Methods . KS-RegNet is an end-to-end, unsupervised network consisting of an input data generation block, a subsequent U-Net core block, and following operations to compute data fidelity and regularization losses. The input data involved a fully-sampled, complex-valued prior image, and the k-space data of an on-board, real-time MR image (MRI). From the k-space data, under-sampled real-time MRI was reconstructed by the data generation block to input into the U-Net core. In addition, to train the U-Net core to learn the under-sampling artifacts, the k-space data of the prior image was intentionally under-sampled using the same readout trajectory as the real-time MRI, and reconstructed to serve an additional input. The U-Net core predicted a deformation vector field that deforms the prior MRI to on-board real-time MRI. To avoid adverse effects of quantifying image similarity on the artifacts-ridden images, the data fidelity loss of deformation was evaluated directly in k-space. Results . Compared with Elastix and other deep learning network architectures, KS-RegNet demonstrated better and more stable performance. The average (±s.d.) DICE coefficients of KS-RegNet on a cardiac dataset for the 5- , 9- , and 13-spoke k-space acquisitions were 0.884 ± 0.025, 0.889 ± 0.024, and 0.894 ± 0.022, respectively; and the corresponding average (±s.d.) center-of-mass errors (COMEs) were 1.21 ± 1.09, 1.29 ± 1.22, and 1.01 ± 0.86 mm, respectively. KS-RegNet also provided the best performance on an abdominal dataset. Conclusion . KS-RegNet allows real-time MRI generation with sub-second latency. It enables potential real-time MR-guided soft tissue tracking, tumor localization, and radiotherapy plan adaptation.

10 December 2022 in The Laryngoscope
Verified
Journal Article
Closed access
KWKai Wang
Kai Wang
NGNicholas A. George‐Jones
Nicholas A. George‐Jones
LCLiyuan Chen
Liyuan Chen
JHJacob B. Hunter
Jacob B. Hunter
JWJing Wang
Jing Wang

18 April 2020 in The Laryngoscope
Verified
Journal Article
Closed access
PDF file
NGNicholas A. George‐Jones
Nicholas A. George‐Jones
KWKai Wang
Kai Wang
JWJing Wang
Jing Wang
JHJacob B. Hunter
Jacob B. Hunter

18 June 2020 in IEEE Access
Verified
Journal Article
Open access
YDYiting Duan
Yiting Duan
HCHaitao Cheng
Haitao Cheng
KWKai Wang
Kai Wang
XMXuanqin Mou
Xuanqin Mou
With the introduction of cold electron sources such as nanotubes, X-ray sources became small in size so that many sources are installed in array to form stationary CT, which brings benefits of simplicity in mechanism and fast response. However, the nanotube-based X-ray source is still singly packaged and hence density of X-ray sources is limited, which introduces severe sparse-view artifacts and could not be used in practice. With the invention of X-ray sources device based on ZnO nanowires as cold electron emitters, a large amount of X-ray sources is first integrated in a flat panel device. In this study, we design a stationary CT architecture using high-density sources devices, called HD-SCT, and develop corresponding reconstruction algorithm. Specifically, several flat panel detectors and X-ray sources devices are spliced together to form a source-detector plate. Multiple source-detector plates are organized as a polygon that encloses object to complete CT scanning. In HD-SCT, X-ray sources are close to object which can significantly decrease CT device volume. The X-ray beam emitted by each source just cover part of object and the spot sources alternately light to completely scan object. Simultaneously, we propose a reconstruction method for the specific configuration which adopts an iterative algorithm to resolve the reconstruction based on alterative part projections, as well as a novel correction process of projection completion for the shadowed area of placing X-ray source devices. To validate the design of the proposed HD-SCT, we execute a series of simulation experiments, which show that the proposed HD-SCT and corresponding reconstruction method effectively remove the artifacts caused by the embed X-ray source device. The results also disclose that with the increase of density of X-ray sources, the resolution of reconstruction has been dramatically improved, which demonstrates the practical value of introducing high-density X-ray sources device into stationary CT design.