Khalid Youssef

Khalid Youssef

Auto-generated profile, based on publicly available information

Khalid Youssef

Department of Chemistry and Biochemistry, University of California, Los Angeles, CA, USA

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
11 November 2018 in IEEE Journal of Radio Frequency Identification
Verified
Journal Article
Closed access
KYKhalid Youssef
Khalid Youssef
LBLouis Bouchard
Louis Bouchard
KHKaren Haigh
Karen Haigh
JSJan Silovsky
Jan Silovsky
BTBishal Thapa
Bishal Thapa
CVChris Vander Valk
Chris Vander Valk
With the increasing domain and widespread use of wireless devices in recent years (mobile phones, Internet of Things, Wi-Fi), the electromagnetic spectrum has become extremely crowded. To counter security threats posed by rogue or unknown transmitters, we must identify RF transmitters not only by the data content of the transmissions but also based on the intrinsic physical characteristics of the transmitters. RF waveforms represent a particular challenge because of the extremely high data rates involved and the potentially large number of transmitters sharing a channel in a given location. These factors outline the need for rapid fingerprinting and identification methods that go beyond the traditional hand-engineered approaches. In this paper, we investigate the use of machine learning strategies to the classification and identification problem. We evaluate four different strategies: conventional deep neural nets, convolutional neural nets, support vector machines, and deep neural nets with multi-stage training. The latter was by far the most accurate, achieving 100% classification accuracy of 12 transmitters, and showing remarkable potential for scalability to large transmitter populations.

1 December 2024 in Radiology: Cardiothoracic Imaging
Verified
Journal Article
Closed access
YHYuheng Huang
Yuheng Huang
XGXingmin Guan
Xingmin Guan
XZXinheng Zhang
Xinheng Zhang
GYGhazal Yoosefian
Ghazal Yoosefian
HHHao Ho
Hao Ho
HYHsin-Jung Yang
Hsin-Jung Yang
Free-running cardiac quantitative susceptibility mapping allows for accurate detection and quantification of intramyocardial hemorrhage in the setting of acute myocardial infarction.

31 October 2022 in IEEE Antennas and Propagation Magazine
Verified
Journal Article
Closed access
KYKhalid Youssef
Khalid Youssef
GSGreg Schuette
Greg Schuette
YCYubin Cai
Yubin Cai
DZDaisong Zhang
Daisong Zhang
YHYikun Huang
Yikun Huang
LBLouis-S. Bouchard
Louis-S. Bouchard
Unlike areas such as computer vision and speech recognition, where convolutional and recurrent neural network (NN)-based approaches have proven effective due to the nature of the respective areas of application, deep learning (DL) still lacks a general approach suitable for the unique nature and challenges of radiofrequency (RF) systems such as radar, signals intelligence, electronic warfare, and communications. Existing approaches face problems in robustness, consistency, efficiency, repeatability, and scalability. Some of the main challenges in radiofrequency (RF) sensing such as radar target identification are the difficulty and cost of obtaining data. Hundreds to thousands of samples per class are typically used when training for classifying signals into 2–12 classes with reported accuracy ranging from 87% to 99%, where accuracy generally decreases with more classes added. In this article, we present a new DL approach based on multistage training (MST) and demonstrate it on RF sensing signal classification. We consistently achieve more than 99% accuracy for up to 17 diverse classes using only 11 samples per class for training, a substantial improvement over standard DL approaches.

18 July 2018 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
BABrian J. Archer
Brian J. Archer
TUTill Uberruck
Till Uberruck
JMJulia J. Mack
Julia J. Mack
KYKhalid Youssef
Khalid Youssef
NJNanette N. Jarenwattananon
Nanette N. Jarenwattananon
LBLouis-S. Bouchard
Louis-S. Bouchard
Objective: For tissue engineering, there is a need for quantitative methods to map cell density inside three-dimensional (3-D) bioreactors to assess tissue growth over time. The current cell mapping methods in 2-D cultures are based on optical microscopy. However, optical methods fail in 3-D due to increased opacity of the tissue. We present an approach for measuring the density of cells embedded in a hydrogel to generate quantitative maps of cell density in a living, 3-D tissue culture sample. Methods: Quantification of cell density was obtained by calibrating the 1 H T 2 , magnetization transfer (MT) and diffusion-weighted nuclear magnetic resonance (NMR) signals to samples of known cell density. Maps of cell density were generated by weighting NMR images by these parameters post-calibration. Results: The highest sensitivity weighting arose from MT experiments, which yielded a limit of detection (LOD) of 2.5 × 10 8 cells/mL/√Hz in a 400 MHz (9.4 T) magnet. Conclusion: This mapping technique provides a noninvasive means of visualizing cell growth within optically opaque bioreactors. Significance: We anticipate that such readouts of tissue culture growth will provide valuable feedback for controlled cell growth in bioreactors.

1 August 2024 in Radiology: Cardiothoracic Imaging
Verified
Journal Article
Closed access
KYKhalid Youssef
Khalid Youssef
XZXinheng Zhang
Xinheng Zhang
GYGhazal Yoosefian
Ghazal Yoosefian
YCYinyin Chen
Yinyin Chen
SCShing Fai Chan
Shing Fai Chan
RDRohan Dharmakumar
Rohan Dharmakumar
Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and t-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as data-driven native mapping (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; P < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; P = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (R2 = 0.71 for native T1 maps vs LGE; R2 = 0.85 for DNM vs LGE; P < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. Keywords: Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping Supplemental material is available for this article. © RSNA, 2024.

20 September 2021 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
BABrian J. Archer
Brian J. Archer
JMJulia J. Mack
Julia J. Mack
SASara Acosta
Sara Acosta
RNRussell Nakasone
Russell Nakasone
FDFadi Dahoud
Fadi Dahoud
LBLouis-S. Bouchard
Louis-S. Bouchard
Objective: In biomanufacturing there is a need for quantitative methods to map cell viability and density inside 3D bioreactors to assess health and proliferation over time. Recently, noninvasive MRI readouts of cell density have been achieved. However, the ratio of live to dead cells was not varied. Herein we present an approach for measuring the viability of cells embedded in a hydrogel independently from cell density to map cell number and health. Methods: Independent quantification of cell viability and density was achieved by calibrating the 1H magnetization transfer- (MT) and diffusion-weighted NMR signals to samples of known cell density and viability using a multivariate approach. Maps of cell viability and density were generated by weighting NMR images by these parameters post-calibration. Results: Using this method, the limits of detection (LODs) of total cell density and viable cell density were found to be 3.88x10^8 cells mL^-1 Hz^-1/2 and 2.36x10^9 viable cells mL^-1 Hz^-1/2 respectively. Conclusion: This mapping technique provides a noninvasive means of visualizing cell viability and number density within optically opaque bioreactors. Significance: We anticipate that such nondestructive readouts will provide valuable feedback for monitoring and controlling cell populations in bioreactors.