QKQuang Huy Khuat

Quang Huy Khuat

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Quang Huy Khuat has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    QUANTITATIVE ANALYSIS OF 238U, 232TH, AND 40K IN ENVIRONMENTAL SAMPLES USING A PHYSICS-INFORMED NEURAL NETWORK: BRIDGING SIMULATED AND EXPERIMENTAL GAMMA SPECTRA

    by Duong Thuy Tran, Ha Ngoc Bui, Ngoc Toan Tran, Dinh Thuy Mai, Quang Huy Khuat, Tat Thang Nguyen, Thu Trang Vu, Hai Quan Ho

    Gamma-ray spectrometry using high-purity germanium (HPGe) detectors is the standard method for environmental radiation monitoring. Traditional analysis procedures rely on manual expert intervention to identify regions of interest (ROI), subtract background, and apply physical corrections, which limits computational efficiency on large datasets. Automating spectral analysis with deep neural networks requires a substantial amount of data. However, the domain shift between ideal simulated spectra and noisy experimental spectra degrades the predictive performance of purely data-driven models. This study evaluates a physics-informed neural network (PINN) framework, in which a 1D-ResNet is pre-trained on 6,000 MCNP-simulated spectra and fine-tuned on 640 experimental spectra. The loss function of the model embeds the radioactive isotope quantitative analysis equation. A Monte Carlo Dropout mechanism is applied during inference to estimate measurement uncertainty. The predictions from the PINN model achieve a coefficient of determination (R2) ranging from 0.937 to 0.949 when quantifying 40K, 232Th and 238U with lower RMSE and MAE compared to the standard 1D-ResNet architecture. Bland-Altman analysis demonstrates that the model-estimated uncertainty agrees with the benchmark method. The results from this study contribute to the development of an automated quantitative analysis pipeline that complies with radiation statistical principles, while determining operational limits when the system experiences significant hardware drift.

  • Open Access

    Benchmarking Deep Learning for NSCLC PET/CT Segmentation on a Histologically Confirmed Vietnamese Dataset: Validation and Generalization

    by Quang Tuan Ho, Ngoc Ha Bui, Thuy Duong Tran, Quang Huy Khuat, Ngoc Toan Tran, Xuan Chung Le, Huu Quyet Nguyen, Tat Thang Nguyen, Van Thai Nguyen, Dinh Thuy Mai, et al.

    Accurate segmentation of non-small cell lung cancer (NSCLC) on positron emission tomography/computed tomography (PET/CT) is an essential prerequisite for automated metabolic tumor volume (MTV) quantification and staging. Although deep learning models achieve high performance on large-scale datasets, their generalization across different clinical domains is limited by variations in imaging protocols and patient demographics. This study aims to evaluate several deep learning architectures and investigate a transfer learning strategy to mitigate domain shift. Three architectures, including ResNet-backbone 3D U-Net, nnU-Net v2, and Swin UNETR, were benchmarked from scratch and compared with a fine-tuned nnU-Net initialized with AutoPET II weights. Results on the internal dataset showed that the fine-tuned nnU-Net achieved a Dice similarity coefficient (DSC) of 83.4 ± 6.5%, a 95% Hausdorff distance (HD95) of 5.1 ± 3.6 mm, and a precision of 89.6 ± 8.2%. Compared to the nnU-Net v2, the fine-tuned nnU-Net improved the absolute DSC by 6.8% while reducing local training time by 37.5% by bypassing the initial feature-learning phase. The fine-tuned nnU-Net model also demonstrated a high correlation between the MTV and the ground truth (Pearson r = 0.96, p < 0.001), indicating its potential as a reliable automated approach for quantitative MTV extraction and NSCLC prognostic-related analysis.

  • Open Access

    Benchmarking Deep Learning for NSCLC PET/CT Segmentation on a Histologically Confirmed Vietnamese Dataset: Validation and Generalization

    by Quang Tuan Ho, Ngoc Ha Bui, Duong Tran Thuy, Quang Huy Khuat, Ngoc Toan Tran, Xuan Chung Le, Huu Quyet Nguyen, Tat Thang Nguyen, Van Thai Nguyen, Dinh Thuy Mai, et al.

    Accurate segmentation of non-small cell lung cancer (NSCLC) on positron emission tomography/computed tomography (PET/CT) is a critical foundation for automated metabolic tumor volume (MTV) quantification and staging. Although deep learning models achieve high performance on large-scale datasets, their generalization across different clinical domains remains challenged by variations in imaging protocols and patient demographics. This study aims to evaluate several deep learning architectures and investigate a transfer learning strategy to mitigate domain shift on a dataset of 400 PET/CT scans from Vietnamese NSCLC patient cohort. Three architectures, including 3D U-Net, nnU-Net v2, and Swin UNETR, were benchmarked from scratch and compared with a fine-tuned nnU-Net initialized with AutoPET II weights. Results on the internal dataset showed that the fine-tuned nnU-Net achieved a Dice similarity coefficient (DSC) of 83.4 ± 6.5%, a 95% Hausdorff distance (HD95) of 5.1 ± 3.6 mm, and precision of 89.6 ± 8.2%. Compared to the nnU-Net v2, the fine-tuned nnU-Net improved the absolute DSC by 6.8% while reducing the training time by 37.5%. The fine-tuned nnU-Net model also demonstrated a good correlation between the MTV and the ground truth (Pearson r = 0.96, p < 0.001), indicating its potential as a reliable automated approach for quantitative MTV extraction and NSCLC prognostic related analysis.