Andrew Hoang

Mr. Andrew Hoang

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
21 June 2025 in Cancer
Verified
Journal Article
Closed access
RSRaj Singh
Raj Singh
JRJohn G. Roubil
John G. Roubil
GBGreg Bowden
Greg Bowden
DMDavid Mathieu
David Mathieu
LCLouis Carrier
Louis Carrier
JSJason P. Sheehan
Jason P. Sheehan

27 October 2022 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
AAArian Azarang
Arian Azarang
DLDavid Q. Le
David Q. Le
AHAndrew Hoang
Andrew Hoang
SBS. Lesley Blogg
S. Lesley Blogg
PDPaul Dayton
Paul Dayton
VPVirginie Papadopoulou
Virginie Papadopoulou
Objective: Doppler ultrasound (DU) is used to detect venous gas emboli (VGE) post dive as a marker of decompression stress for diving physiology research as well as new decompression procedure validation to minimize decompression sickness risk. In this paper, we propose the first deep learning model for VGE grading in DU audio recordings. Methods: A database of real-world data was assembled and labeled for the purpose of developing the algorithm, totaling 274 recordings comprising both subclavian and precordial measurements. Synthetic data was also generated by acquiring baseline DU signals from human volunteers and superimposing laboratory-acquired DU signals of bubbles flowing in a tissue mimicking material. A novel squeeze-and-excitation deep learning model was designed to effectively classify recordings on the 5-class Spencer scoring system used by trained human raters. Results: On the real-data test set, we show that synthetic data pretraining achieves average ordinal accuracy of 84.9% for precordial and 90.4% for subclavian DU which is a 24.6% and 26.2% increase over training with real-data and time-series augmentation only. The weighted kappa coefficients of agreement between the model and human ground truth were 0.74 and 0.69 for precordial and subclavian respectively, indicating substantial agreement similar to human inter-rater agreement for this type of data. Conclusion: The present work demonstrates the first application of deep-learning for DU VGE grading using a combination of synthetic and real-world data. Significance: The proposed method can contribute to accelerating DU analysis for decompression research.

27 April 2023 in PLOS ONE
Verified
Journal Article
Open access
PDF file
DLDavid Q Le
David Q Le
AHAndrew Hoang
Andrew Hoang
AAArian Azarang
Arian Azarang
RLRachel M Lance
Rachel M Lance
MNMichael Natoli
Michael Natoli
VPVirginie Papadopoulou
Virginie Papadopoulou
Doppler ultrasound (DU) measurements are used to detect and evaluate venous gas emboli (VGE) formed after decompression. Automated methodologies for assessing VGE presence using signal processing have been developed on varying real-world datasets of limited size and without ground truth values preventing objective evaluation. We develop and report a method to generate synthetic post-dive data using DU signals collected in both precordium and subclavian vein with varying degrees of bubbling matching field-standard grading metrics. This method is adaptable, modifiable, and reproducible, allowing for researchers to tune the produced dataset for their desired purpose. We provide the baseline Doppler recordings and code required to generate synthetic data for researchers to reproduce our work and improve upon it. We also provide a set of pre-made synthetic post-dive DU data spanning six scenarios representing the Spencer and Kisman-Masurel (KM) grading scales as well as precordial and subclavian DU recordings. By providing a method for synthetic post-dive DU data generation, we aim to improve and accelerate the development of signal processing techniques for VGE analysis in Doppler ultrasound.

24 June 2025 in Cancers
Verified
Journal Article
Open access
PDF file
AHAndrew Hoang
Andrew Hoang
ZWZhishuo Wei
Zhishuo Wei
CHConstantinos G. Hadjipanayis
Constantinos G. Hadjipanayis
ANAjay Niranjan
Ajay Niranjan
LLL. Dade Lunsford
L. Dade Lunsford
Purpose: We present our single-institution experience of sarcomatous brain metastasis patients who underwent stereotactic radiosurgery (SRS) over the past 35 years. Methods: In total, 31 patients (16 males) who underwent SRS for sarcoma brain metastases were identified. Median age at presentation to SRS was 47 (range: 4–78) months. Common histopathologies included leiomyosarcoma (eight patients), osteosarcoma (six patients), alveolar sarcoma (three patients), Ewing sarcoma (three patients), and undifferentiated/unclassified sarcoma (three patients). The median Karnofsky Performance Score (KPS) was 90. Nine patients underwent pre-SRS craniotomy. The median dose prescribed was 18 Gy. The median cumulative tumor volume was 1.4 cc. Results: Median patient overall survival (OS) after SRS was 7 (range: 0–155) months. Local tumor control (LTC) was achieved in 105 out of 113 tumors, at a median time of 3 (range: 0–17) months between SRS and progression. LTC rates per patient and per tumor were 74.2% and 92.9%, respectively. Following SRS, 10 patients (32.3%) developed new tumors at a median time of 6 (range: 1–25) months. Four patients experienced adverse radiation effects (AREs). At the last follow-up, all patients died, one patient from intracranial progression, 27 from systemic disease progression, and the remaining from unrelated medical conditions. Conclusions: Given high LTC and low ARE rates, this suggests SRS as a strong candidate for the non-invasive management of sarcomatous brain metastases, which typically present late following initial presentation of the primary disease.

29 May 2026 in Journal of Clinical Neuroscience
Verified
Journal Article
Closed access
AHAndrew Hoang
Andrew Hoang
CWChris Z. Wei
Chris Z. Wei
HDHansen Deng
Hansen Deng
CHConstantinos G. Hadjipanayis
Constantinos G. Hadjipanayis
MLMichael J. Lang
Michael J. Lang
LLL. Dade Lunsford
L. Dade Lunsford