T. T. Duong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
T. T. Duong has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
B. N. Ha
Hanoi University of Science and Technology, No 1 Dai Co Viet, Hanoi 11615, Vietnam
2 shared publicationsC. V. Luong
Vietnam National Cancer Hospital, No.30 Cau Buou St., Tan Trieu Commue, Thanh Tri district, Hanoi 12511, Vietnam
1 shared publicationC. V. Tuynh
Hanoi Oncology Hospital, No.42A Thanh Nhan, Thanh Nhan ward, Hai Ba Trung district, Hanoi 11624, Vietnam
1 shared publicationD. T. M. Linh
Vietnam Atomic Energy Institute, No 59 Ly Thuong Kiet, Hanoi 11019, Vietnam
1 shared publicationD. T. Nhung
Vietnam Atomic Energy Institute, No 59 Ly Thuong Kiet, Hanoi 11019, Vietnam
1 shared publicationH. Q. Tuan
Vietnam Atomic Energy Institute, No 59 Ly Thuong Kiet, Hanoi 11019, Vietnam
1 shared publication
Latest Publications
- Open Access
- 14 April 2025
- Published by National Research and Innovation Agency in Atom Indonesia
- Vol. 51 (2) , 137-143
Development of a Vietnamese PET/CT Dataset for Machine Learning-Based Analysis of Non-Small Cell Lung Cancer Images
Positron Emission Tomography and Computed Tomography (PET/CT), a key imaging modality in nuclear medicine, Combines Anatomical (CT) and functional (PET) data for cancer diagnosis. Despite advancements in machine learning for automated medical image analysis, publicly available PET/CT datasets remain scarce, limiting Artificial Intelligence (AI) research compared to CT and MRI. This study built a publicly accessible PET/CT Vietnamese dataset for Non-Small Cell Lung Cancer (NSCLC). A total of 416 PET/CT scans were collected from three Vietnamese hospitals, including 300 NSCLC cases. Malignant FDG-sensitive lesions, identified via clinical PET/CT reports, were manually segmented in 3D (slice-by-slice) on PET images and validated by three experienced radiologists. The dataset includes both original and annotated DICOM files, along with clinical patient data. It achieved a dice similarity coefficient of 80.3 % and volume similarity of 81.9 %, demonstrating high segmentation accuracy comparable to other studies. This dataset supports AI-driven NSCLC research and contributes to global efforts in automated PET/CT analysis for nuclear medicine applications.
- 14 April 2025
- Published by National Research and Innovation Agency in Atom Indonesia
- Vol. 51 (2) , 137-143
Open AccessDevelopment of a Vietnamese PET/CT Dataset for Machine Learning-Based Analysis of Non-Small Cell Lung Cancer Images
Positron Emission Tomography and Computed Tomography (PET/CT), a key imaging modality in nuclear medicine, Combines Anatomical (CT) and functional (PET) data for cancer diagnosis. Despite advancements in machine learning for automated medical image analysis, publicly available PET/CT datasets remain scarce, limiting Artificial Intelligence (AI) research compared to CT and MRI. This study built a publicly accessible PET/CT Vietnamese dataset for Non-Small Cell Lung Cancer (NSCLC). A total of 416 PET/CT scans were collected from three Vietnamese hospitals, including 300 NSCLC cases. Malignant FDG-sensitive lesions, identified via clinical PET/CT reports, were manually segmented in 3D (slice-by-slice) on PET images and validated by three experienced radiologists. The dataset includes both original and annotated DICOM files, along with clinical patient data. It achieved a dice similarity coefficient of 80.3 % and volume similarity of 81.9 %, demonstrating high segmentation accuracy comparable to other studies. This dataset supports AI-driven NSCLC research and contributes to global efforts in automated PET/CT analysis for nuclear medicine applications.
- Open Access
- 24 March 2023
- Published by National Research and Innovation Agency in Atom Indonesia
- Vol. 1 (1) , 13-20
Simulation of Leksell Gamma Knife-4C System with Different Phantoms Using PHITS and Geant4
This study used PHITS and Geant4 code packages to simulate a Leksell Gamma Knife system in order to determine radiation dose distribution in two types of phantoms. The results observed in the water phantom with configurations of single source and 201 sources are in good accord with the prior research, including both simulation and experiment. Several characteristics of Leksell Gamma Knife 4C, such as dose profiles, output factor, FWHM, and penumbra size, are calculated based on Monte Carlo simulations, which show the best consistency with other results. The output factors for collimators of 14 mm, 8 mm, and 4 mm are 0.984, 0.949, and 0.872, respectively. The simulation results with an adult mesh-type reference phantom reveal considerable similarities with the established radiosurgery plans. It indicates that the absorbed dose in brain tumors was highest when utilizing the 18 mm collimator and subsequently reduced with collimator size to 0.65, 0.25, and 0.5 with the 14 mm, 8 mm, and 4 mm collimators, respectively. The absorbed dose has a very low value for other essential organs and decreases with distance from the brain tumor. These findings may explain why the dose to organs decreases linearly as target distance, volume, and collimator size increase.
- 24 March 2023
- Published by National Research and Innovation Agency in Atom Indonesia
- Vol. 1 (1) , 13-20
Open AccessSimulation of Leksell Gamma Knife-4C System with Different Phantoms Using PHITS and Geant4
This study used PHITS and Geant4 code packages to simulate a Leksell Gamma Knife system in order to determine radiation dose distribution in two types of phantoms. The results observed in the water phantom with configurations of single source and 201 sources are in good accord with the prior research, including both simulation and experiment. Several characteristics of Leksell Gamma Knife 4C, such as dose profiles, output factor, FWHM, and penumbra size, are calculated based on Monte Carlo simulations, which show the best consistency with other results. The output factors for collimators of 14 mm, 8 mm, and 4 mm are 0.984, 0.949, and 0.872, respectively. The simulation results with an adult mesh-type reference phantom reveal considerable similarities with the established radiosurgery plans. It indicates that the absorbed dose in brain tumors was highest when utilizing the 18 mm collimator and subsequently reduced with collimator size to 0.65, 0.25, and 0.5 with the 14 mm, 8 mm, and 4 mm collimators, respectively. The absorbed dose has a very low value for other essential organs and decreases with distance from the brain tumor. These findings may explain why the dose to organs decreases linearly as target distance, volume, and collimator size increase.