Phi Nguyen
Research
Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis

MICCAI 2024

Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis

Phi Nguyen Van, Tri Phi Nguyen Ha, Huy Hieu Pham, Quoc Long Tran

This study introduces a training-free method for generating echocardiograms from a single segmentation map using 3D-Unet with Temporal Attention Layers. It addresses data scarcity in medical imaging by generating plausible echocardiograms without additional training datasets, evaluated on CAMUS and EchoNet-Dynamic.

MedIDM: Synthesis Medical Video Segmentation Dataset via Implicit Motion Representation from Diffusion Model

Preprint

MedIDM: Synthesis Medical Video Segmentation Dataset via Implicit Motion Representation from Diffusion Model

Phi Nguyen Van, Tri Phi Nguyen Ha, Minh Nguyen Tuan, Huy Hieu Pham, Quoc Long Tran

MedIDM presents a synthetic dataset for medical video segmentation using an implicit motion representation model, focusing on diffusion methods for training and testing in medical imaging applications.

Echocardiography Segmentation Using Neural ODE-based Diffeomorphic Registration Field

arXiv Preprint

Echocardiography Segmentation Using Neural ODE-based Diffeomorphic Registration Field

Phi Nguyen Van, Huy Hieu Pham, Quoc Long Tran

This paper explores a novel approach for echocardiography segmentation using Neural ODE-based diffeomorphic registration fields, enhancing robustness in medical image segmentation.

Ensemble Learning of Myocardial Displacements for Myocardial Infarction Detection in Echocardiography

Frontiers in Cardiovascular Medicine (Vol. 10)

Ensemble Learning of Myocardial Displacements for Myocardial Infarction Detection in Echocardiography

Tuan Nguyen, Phi Nguyen, Dai Tran, Hung Pham, Quang Nguyen, Thanh Le, Hanh Van, Bach Do, Phuong Tran, Vinh Le, Thuy Nguyen, Long Tran, Hieu Pham

This publication introduces an ensemble learning approach for myocardial displacement tracking, supporting myocardial infarction detection with high accuracy in echocardiography.

Echocardiography Video Synthesis from End Diastolic Semantic Map via Diffusion Model

ICASSP 2024

Echocardiography Video Synthesis from End Diastolic Semantic Map via Diffusion Model

Phi Nguyen Van, Minh Duc Tran, Huy Hieu Pham, Quoc Long Tran

Presented at ICASSP 2024, this research introduces a novel method for synthesizing echocardiogram video sequences using diffusion models based on a single end-diastolic semantic map.

Teaching
Data Processing with Python

Data Processing with Python
Teaching

Course content for Data Processing with Python.
Advanced Programming

Advanced Programming
Teaching

Course content for Advanced Programming.
Computer Graphics

Computer Graphics
Teaching

Course content for Computer Graphics.