trieu-nghi HOANG-THI

Dr. trieu-nghi HOANG-THI

Vinmec Healthcare System, Ho Chi Minh City, Hồ Chí Minh, Vietnam
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021 in Medical Image Analysis
Verified
Journal Article
Closed access
CGChassagnon Guillaume
Chassagnon Guillaume
MVMaria Vakalopoulou
Maria Vakalopoulou
EBEnzo Battistella
Enzo Battistella
SCStergios Christodoulidis
Stergios Christodoulidis
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
NPNikos Paragios
Nikos Paragios
1

9 November 2022 in Japanese Journal of Radiology
Verified
Journal Article
Closed access
PDF file
CGChassagnon Guillaume
Chassagnon Guillaume
CMConstance De Margerie-Mellon
Constance De Margerie-Mellon
MVMaria Vakalopoulou
Maria Vakalopoulou
RMRafael Marini
Rafael Marini
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
PSPhilippe Soyer
Philippe Soyer

1 November 2021 in Diagnostic and Interventional Imaging
Verified
Journal Article
Closed access
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
MVMaria Vakalopoulou
Maria Vakalopoulou
SCStergios Christodoulidis
Stergios Christodoulidis
NPNikos Paragios
Nikos Paragios
MRMarie-Pierre Revel
Marie-Pierre Revel
CGChassagnon Guillaume
Chassagnon Guillaume

18 December 2018 in BMC Pulmonary Medicine
Verified
Journal Article
Open access
PDF file
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
MRMarie-Pierre Revel
Marie-Pierre Revel
PBPierre-Régis Burgel
Pierre-Régis Burgel
LBLaurence Bassinet
Laurence Bassinet
IHIsabelle Honoré
Isabelle Honoré
CGChassagnon Guillaume
Chassagnon Guillaume
The present study aimed to develop an automated computed tomography (CT) score based on the CT quantification of high-attenuating lung structures, in order to provide a quantitative assessment of lung structural abnormalities in patients with Primary Ciliary Dyskinesia (PCD). Adult (≥18 years) PCD patients who underwent both chest CT and spirometry within a 6-month period were retrospectively included. Commercially available lung segmentation software was used to isolate the lungs from the mediastinum and chest wall and obtain histograms of lung density. CT-density scores were calculated using fixed and adapted thresholds based on various combinations of histogram characteristics, such as mean lung density (MLD), skewness, and standard deviation (SD). Additionally, visual scoring using the Bhalla score was performed by 2 independent radiologists. Correlations between CT scores, forced expiratory volume in 1 s (FEV1) and forced vital capacity (FVC) were evaluated. Sixty-two adult patients with PCD were included. Of all histogram characteristics, those showing good positive or negative correlations to both FEV1 and FVC were SD (R = − 0.63 and − 0.67; p < 0.001) and Skewness (R = 0.67 and 0.67; p < 0.001). Among all evaluated thresholds, the CT-density score based on MLD + 1SD provided the best negative correlation with both FEV1 (R = − 0.68; p < 0.001) and FVC (R = − 0.71; p < 0.001), close to the correlations of the visual score (R = − 0.60; p < 0.001 for FEV1 and R = − 0.62; p < 0.001, for FVC). Automated CT scoring of lung structural abnormalities lung in primary ciliary dyskinesia is feasible and may prove useful for evaluation of disease severity in the clinic and in clinical trials.

10 April 2021 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
CGChassagnon Guillaume
Chassagnon Guillaume
THThông Hua-Huy
Thông Hua-Huy
VBVeronique Boussaud
Veronique Boussaud
Anh Tuan Dinh-XuanAnh Tuan Dinh-Xuan
Anh Tuan Dinh-Xuan
MRMarie Pierre Revel
Marie Pierre Revel
Chronic lung allograft dysfunction (CLAD) remains the leading cause of morbidity and mortality after lung transplantation. The term encompasses both obstructive and restrictive phenotypes, as well as mixed and undefined phenotypes. Imaging, in addition to pulmonary function tests, plays a major role in identifying the CLAD phenotype and is essential for follow-up after lung transplantation. Quantitative imaging allows for the performing of reader-independent precise evaluation of CT examinations. In this review article, we will discuss the role of quantitative imaging methods for evaluating the airways and the lung parenchyma on computed tomography (CT) images, for an early identification of CLAD and for prognostic estimation. We will also discuss their limits and the need for novel approaches to predict, understand, and identify CLAD in its early stages.

6 April 2026
Verified
Thesis
Closed access
THtrieu-nghi HOANG-THI
trieu-nghi HOANG-THI
L'analyse quantitative des lésions pulmonaires en imagerie thoracique tomodensitométrique est désormais possible grâce aux outils d'aide au diagnostic (ou Computer-Aided Diagnosis - CAD). Cette approche permet également une meilleure compréhension des mécanismes physiopathologiques grâce aux outils d'intelligence artificielle et à l'approche radiomique. Dans le cadre de notre Thèse, nous avions pu appliquer les outils de CAD et d'intelligence artificielle (machine learning et deep-learning) pour construire des scores de sévérité dans la dyskinésie ciliaire primitive (DCP), prédire la survenue du dysfonctionnement chronique du greffon pulmonaire (DCGP) et la mortalité à court terme de la sclérodermie systémique (ScS). Nous avions également combiné les résultats de machine learning sur les deux types de filtre médiastinal et pulmonaire du scanner thoracique. Nous avions ainsi amélioré l'efficacité des algorithmes d'apprentissage profond sans avoir recours à la nouvelle acquisition de scanner irradié. En pratique, nous avions montré que la caractéristique radiomique de premier ordre autorise la quantification automatique des modifications des images et l'établissement d'un score objectif pour évaluer la gravité de la DCP. L'analyse préliminaire de la combinaison des caractéristiques de densité en histogramme et de texture de la radiomique des scanners inspiratoires pourrait également prédire les modifications fonctionnelles respiratoires de la DCGP 6 mois avant leur survenue. Mais les résultats de notre étude préliminaire, n'étant pas statistiquement significatifs, nécessitent des études à plus grande échelle passant par des collaborations multicentriques. Pour la ScS, l'algorithme de « deep-learning » AtlasNet permet la quantification des lésions du parenchyme pulmonaire et la prédiction de la mortalité à court terme. Dans le dernier chapitre de notre thèse, nous rapportons l'influence du choix de filtre de reconstruction en TDM sur l'entrainement des modèles de machine learning pour la segmentation des zones lésionnelles pulmonaires interstitielles dans la ScS et la COVID-19, permettant ainsi d'augmenter la performance des modèles combinant les deux filtres de reconstruction.