Pham Huy Hieu, PhD.
Browse by
Dr. Pham Huy Hieu is an Assistant Professor at the College of Engineering and Computer Science (CECS), VinUniversity, and a Research Fellow cum Associate Director at VinUni-Illinois Smart Health Center. He received his Ph.D. in Computer Science from the Toulouse Computer Science Research Institute (IRIT), University of Toulouse, France, in 2019. Previously, he earned the Degree of Engineer in Industrial Informatics from Hanoi University of Science and Technology (HUST), Vietnam, in 2016. His research interests include Computer Vision, Machine Learning, Medical Image Analysis, and their applications in Smart Healthcare. He is the author, co-author of 45 scientific articles appeared in about 30 conferences and journals such as Nature Scientific Data, Computer Vision and Image Understanding, Neurocomputing, PloS ONE, Medical Physics, Frontiers in Digital Health, Biomedical Signal Processing and Control, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Medical Imaging with Deep Learning (MIDL), IEEE International Conference on Image Processing (ICIP), and IEEE International Conference on Computer Vision (ICCV), Asian Conference on Computer Vision (ACCV). He is also currently serving as Reviewers for MICCAI, ICCV, CVPR, IEEE Journal of Biomedical and Health Informatics, and Nature Scientific Reports. Dr. Hieu Pham was recognized by the Federal Ministry of Education and Research (Germany) as an outstanding researcher in AI and Medical Imaging Research with DAAD Fellowship 2021. Recently, he received the AI Awards 2022 for the VAIPE project that he served as co-PI. He also co-authored the paper that won Best Paper Finalist Award in the 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2023). Before joining VinUniversity, Dr. Hieu worked at Vingroup Big Data Institute (VinBigData) as a Research Scientist and Head of the Fundamental Research Team. With this position, he led several research projects on Medical AI, including collecting various types of medical data, managing and annotating data, and developing new AI solutions for medical analysis.
Recent Submissions
-
Deployment and validation of an AI system for detecting abnormal chest radiographs in clinical settings
(2022-07-27)Background: The purpose of this paper is to demonstrate a mechanism for deploying and validating an AI-based system for detecting abnormalities on chest X-ray scans at the Phu Tho General Hospital, Vietnam. We aim to ... -
An accurate and explainable deep learning system improves interobserver agreement in the interpretation of chest radiograph
(2022-10-04)Interpretation of chest radiographs (CXR) is a difficult but essential task for detecting thoracic abnormalities. Recent artificial intelligence (AI) algorithms have achieved radiologist-level performance on various medical ... -
Detecting COVID-19 from digitized ECG printouts using 1D convolutional neural networks
(2022-11)The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, raising the need to develop novel tools to provide rapid and cost-effective screening and diagnosis. Clinical reports indicated that ... -
VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations
(2022-12)Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and ... -
LightX3ECG: A lightweight and explainable deep learning system for 3-lead electrocardiogram classification
(2022-07-25)Cardiovascular diseases (CVDs) are a group of heart and blood vessel disorders that is one of the most serious dangers to human health, and the number of such patients is still growing. Early and accurate detection plays ... -
High accurate and explainable multi-pill detection framework with graph neural network-assisted multimodal data fusion
(2023-09-28)Due to the significant resemblance in visual appearance, pill misuse is prevalent and has become a critical issue, responsible for one-third of all deaths worldwide. Pill identification, thus, is a crucial concern that ... -
PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children
(2023)Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the advent of high-performance supervised learning ... -
VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography
(2023)Mammography, or breast X-ray imaging, is the most widely used imaging modality to detect cancer and other breast diseases. Recent studies have shown that deep learning-based computer-assisted detection and diagnosis (CADe/x) ... -
A novel approach for pill-prescription matching with GNN assistance and contrastive learning
(2022)Medication mistaking is one of the risks that can result in unpredictable consequences for patients. To mitigate this risk, we develop an automatic system that correctly identifies pill-prescription from mobile images. ... -
Slice-level Detection of Intracranial Hemorrhage on CT Using Deep Descriptors of Adjacent Slices
(2023)We propose for the first time a new strategy to train slice-level classifiers on CT scans based on the descriptors of the adjacent slices along the axis. In particular, each of which is extracted through a convolutional ... -
Phase recognition in contrast-enhanced CT scans based on deep learning and random sampling
(2022-01-31)Purpose: A fully automated system for interpreting abdominal computed tomography (CT) scans with multiple phases of contrast enhancement requires accurate classification of the phases. Current approaches typically utilize ... -
PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children
(2023)Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the advent of high-performance supervised learning ... -
Multi-stream fusion for class incremental learning in pill image classification
(2022)Classifying pill categories from real-world images is crucial for various smart healthcare applications. Although existing approaches in image classification might achieve a good performance on fixed pill categories, they ... -
VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations
(2022)Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and ... -
VinDr-Mammo: A large-scale benchmark dataset for computer- aided diagnosis in full-feld digital mammography
(2023)Mammography, or breast X-ray imaging, is the most widely used imaging modality to detect cancer and other breast diseases. Recent studies have shown that deep learning-based computer-assisted detection and diagnosis (CADe/x) ... -
Learning from multiple expert annotators for enhancing anomaly detection in medical image analysis
(2023-04-10)Cardiovascular diseases (CVDs) are a group of heart and blood vessel disorders that is one of the most serious dangers to human health, and the number of such patients is still growing. Early and accurate detection plays ... -
Learning from multiple expert annotators for enhancing anomaly detection in medical image analysis
(2022-03-20)Building an accurate computer-aided diagnosis system based on data-driven approaches requires a large amount of high-quality labeled data. In medical imaging analysis, multiple expert annotators often produce subjective ... -
Image-based contextual pill recognition with medical knowledge graph assistance
(2022)In many healthcare applications, accurately identifying pills from images captured under varying conditions has become increasingly crucial. Despite numerous attempts to employ deep learning methods for pill recognition, ... -
FedDRL: Deep reinforcement learning-based adaptive aggregation for non-IID data in federated learning
(2022-08-04)The uneven distribution of local data across different edge devices (clients) results in slow model training and accuracy reduction in federated learning. Naive federated learning (FL) strategy and most alternative solutions ... -
Enhancing deep learning-based 3-lead ECG classification with heartbeat counting and demographic data integration
(2022-08-15)Nowadays, an increasing number of people are being diagnosed with cardiovascular diseases (CVDs), the leading cause of death globally. The gold standard for identifying these heart problems is via electrocardiogram (ECG). ...
