KHOA TRÍ TUỆ NHÂN TẠO

Học viện Công nghệ Bưu chính Viễn thông

Dr. Do Thanh Ha

Lecturer

Dr. Do Thanh Ha

Dr. Thanh-Ha Do is a lecturer and expert in artificial intelligence, working at the AI FacultyPosts and Telecommunications Institute of Technology. She strongly advocates collaborative work in AI. Her project on using AI to identify abdominal tumors, which has been transferred to the US company MedAid, is a result of her collaborative efforts with various stakeholders. This AI-based medical technology is currently being deployed in several hospitals, a testament to the power of teamwork. Beyond healthcare data, she also has collaborative projects with domestic enterprises to consult and solve problems related to applying AI in reconstructing data from medical image records, mining satellite image data, etc. In addition, she is the author and co-author of more than 25 scientific papers that have appeared in international conferences and journals, a reflection of her inclusive research approach.

Medical image processing, Satellite imagery, Document imaging, Autonomous vehicles.
dothanhha@ptit.edu.vn

Summary of Educational and Professional Background  


Dr. Do Thanh Ha received a PhD in Computer Science from the University of Lorraine, France (2014). With over 16 years of experience in teaching and research, Dr. Do Thanh Ha is a reputable expert in Computer Vision and Artificial Intelligence. She has authored numerous scientific works published in leading international conferences and journals. Dr. Ha is an experienced academic supervisor, having successfully mentored more than 10 Master’s students. Many of her former students now hold key positions at major technology corporations in Vietnam. Additionally, students with a strong research orientation have pursued postgraduate studies at prestigious universities in France, the USA, Australia, and Singapore (NUS). 

Research Projects and Collaborations in 2025 

  • Principal Investigator: Application of Artificial Intelligence in Cancer Diagnosis based on Histopathology Images. 
  • Research Collaboration: Partnering with the National Center for Hydro-Meteorological Forecasting on research and modeling for storm forecasting. 

Courses  

  • Image Processing
  • Data Mining
  • Big Data
  • Advanced Machine Learning
  • Artificial Intelligence
  • Discrete Mathematics
  • Database

Significant published research studies

Index Title Publisher Year
1 Multi-heat Keypoint Incorporation in Deep Learning Model for Tropical Cyclone Centering and Intensity Classification from Geostationary Satellite Images Scientific Reports, Nature 2025
2 Towards Robust Cancer Diagnosis: A Hybrid Deep Learning Pipeline for Imbalanced Multi-Label Microscopic Image Analysis Proceedings of MAPR, IEEE 2025
3 Adapting Vision-Language Models for Information Extraction from Bilingual Medical Invoices Proceedings of APSIPA ASC, IEEE 2025
4 Enhanced Object Detection on Aerial Cityscapes via Augmentation and YOLO Variants Proceedings of ICIP, IEEE 2025
5 Two-stage Pipeline for Automated Cell Segmentation: Integrating Semantic and Instance Learning APSIPA Transactions on Signal and Information Processing, Now Publishers 2025
6 Effective of Contrastive Learning Framework in Driver Behavior Analysis Journal of Computer Science and Cybernetics 2025
7 Deep Learning for Table Detection: A Comparative Stuy on Efficiency with Increased Data Proc. Of International Workshop on ADVANCEs in ICT Infrastructures and Services 2024
8 ViHealthNLI: A Dataset for Vietnamese Natural Language Inference in Healthcare Proc. of SIGUL @ LREC-COLING ELRA and ICCL 2024
9 Automated Pseudo-Label Generation and Parallel Computing for Enhanced Few-Shot Medical Image Segmentation Proc. of APSIPA ASC, IEEE 2024
10 Enhancing Cell Segmentation using Deep Learning Models by Custom Processing Techniques Proc. of APSIPA ASC, IEEE 2024
11 Enhanced Sparse Convolutional Detection Model for 3D Object Detection in Autonomous Vehicles Adapted to Traffic Conditions in Vietnam Proc. of APSIPA ASC, IEEE 2024
12 The U-ReACH Model for Ship Detection over Satellite Imagery Proc. of MAPR, IEEE 2024
13 Temporal Convolutional Network-based Approach for Forecasting Fluctuations Differential Pressure in Reverse Osmosis Systems Annual Conference of the PHM Society 2024
14 Enhanced Sparse Convolutional Detection Model for 3D Object Detection in Autonomous Vehicles Adapted to Traffic Conditions in Vietnam Proc. of APSIPA ASC, IEEE 2024
15 Hannotate: Flexible Annotation for Text Analytics from Anywhere LNCS, vol 13998. Springer 2023
16 COVID-Net Network and Application on Support Diagnosis COVID-19 over X-ray Images Proc. of MAPR, IEEE 2022
17 Supporting Thyroid Cancer Diagnosis based on Cell Classification over Microscopic Images Proc. of MAPR, IEEE 2022
18 Automated Classification of Lung Injury from X-ray Images using Deep Learning Network Proc. of APSIPA ASC, IEEE 2022
19 Image Captioning in Vietnamese Language Based on Deep Learning Network CCIS, vol 1287. Springer 2020
20 Generating Vietnamese Language Caption Automatically for Scene Images Proc. of MAPR, IEEE 2020
21 Extracting Handwritten Regions In Japanese Document Images Proc. of MAPR, IEEE 2020
22 Can We Understand Image Semantics from Conventional Neural Networks? CCIS, vol 1035. Springer 2019
23 Text Extraction Using Sparse Representation over Learning Dictionaries CCIS, vol 1035. Springer 2019
24 DSD: document sparse-based denoising algorithm Pattern Analysis and Applications, Springer 2018
25 Spotting Symbol over Graphical Documents Via Sparsity in Visual Vocabulary CCIS, vol 709. Springer 2017
26 A new approach for traffic-sign recognition using sparse representation over dictionary of local descriptors Proc. of KSE, IEEE 2017
27 Sparse representation over learned dictionary for symbol recognition Signal Processing, IEEE 2016
28 Spotting Symbol Using Sparsity over Learned Dictionary of Local Descriptors Proc. of DAS, Springer 2014
29 New Approach for Symbol Recognition Combining Shape Context of Interest Points with Sparse Representation Proc. of ICDAR, Springer 2013
30 Document noise removal using sparse representations over learned dictionary Proc. of DocEng ’13, ACM 2013
31 Noise suppression over bi-level graphical documents by sparse representation Proc. of CIFED 2012
32 Text/graphic separation using a sparse representation with multi-learned dictionaries Proc. of ICPR, IEEE 2012