Van Nhat Thang Le

Dr. Van Nhat Thang Le

Pediatric Dentistry, University of Medicine and Pharmacy, Hue University, Huế, Thừa Thiên-Huế, Vietnam
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
15 June 2020 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
KOKanghan Oh
Kanghan Oh
IOIL-Seok Oh
IL-Seok Oh
VLVan Nhat Thang Le
Van Nhat Thang Le
DLDae-Woo Lee
Dae-Woo Lee
In the past decade, anatomical context features have been widely used for cephalometric landmark detection and significant progress is still being made. However, most existing methods rely on handcrafted graphical models rather than incorporating anatomical context during training, leading to suboptimal performance. In this study, we present a novel framework that allows a Convolutional Neural Network (CNN) to learn richer anatomical context features during training. Our key idea consists of the Local Feature Perturbator (LFP) and the Anatomical Context loss (AC loss). When training the CNN, the LFP perturbs a cephalometric image based on prior anatomical distribution, forcing the CNN to gaze relevant features more globally. Then AC loss helps the CNN to learn the anatomical context based on spatial relationships between the landmarks. The experimental results demonstrate that the proposed framework makes the CNN learn richer anatomical representation, leading to increased performance. In the performance comparisons, the proposed scheme outperforms state-of-the-art methods on the ISBI 2015 Cephalometric X-ray Image Analysis Challenge.

19 November 2021 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
EKEun-Gyeong Kim
Eun-Gyeong Kim
IOIL-Seok Oh
IL-Seok Oh
JSJeong-Eun So
Jeong-Eun So
JKJunhyeok Kang
Junhyeok Kang
VLVan Nhat Thang Le
Van Nhat Thang Le
DLDae-Woo Lee
Dae-Woo Lee
Recently, the estimation of bone maturation using deep learning has been actively conducted. However, many studies have considered hand–wrist radiographs, while a few studies have focused on estimating cervical vertebral maturation (CVM) using lateral cephalograms. This study proposes the use of deep learning models for estimating CVM from lateral cephalograms. As the second, third, and fourth cervical vertebral regions (denoted as C2, C3, and C4, respectively) are considerably smaller than the whole image, we propose a stepwise segmentation-based model that focuses on the C2–C4 regions. We propose three convolutional neural network-based classification models: a one-step model with only CVM classification, a two-step model with region of interest (ROI) detection and CVM classification, and a three-step model with ROI detection, cervical segmentation, and CVM classification. Our dataset contains 600 lateral cephalogram images, comprising six classes with 100 images each. The three-step segmentation-based model produced the best accuracy (62.5%) compared to the models that were not segmentation-based.

Verified
Journal Article
Open access
PDF file
VLVan Nhat Thang Le
Van Nhat Thang Le
JKJunhyeok Kang
Junhyeok Kang
IOIL-Seok Oh
IL-Seok Oh
JKJae-Gon Kim
Jae-Gon Kim
YYYeon-Mi Yang
Yeon-Mi Yang
DLDae-Woo Lee
Dae-Woo Lee
Detection of cephalometric landmarks has contributed to the analysis of malocclusion during orthodontic diagnosis. Many recent studies involving deep learning have focused on head-to-head comparisons of accuracy in landmark identification between artificial intelligence (AI) and humans. However, a human–AI collaboration for the identification of cephalometric landmarks has not been evaluated. We selected 1193 cephalograms and used them to train the deep anatomical context feature learning (DACFL) model. The number of target landmarks was 41. To evaluate the effect of human–AI collaboration on landmark detection, 10 images were extracted randomly from 100 test images. The experiment included 20 dental students as beginners in landmark localization. The outcomes were determined by measuring the mean radial error (MRE), successful detection rate (SDR), and successful classification rate (SCR). On the dataset, the DACFL model exhibited an average MRE of 1.87 ± 2.04 mm and an average SDR of 73.17% within a 2 mm threshold. Compared with the beginner group, beginner–AI collaboration improved the SDR by 5.33% within a 2 mm threshold and also improved the SCR by 8.38%. Thus, the beginner–AI collaboration was effective in the detection of cephalometric landmarks. Further studies should be performed to demonstrate the benefits of an orthodontist–AI collaboration.

1 October 2021 in International Dental Journal
Verified
Journal Article
Open access
VLVan Nhat Thang Le
Van Nhat Thang Le
MDMinh-Huy Dang
Minh-Huy Dang
JKJae-Gon Kim
Jae-Gon Kim
YYYeon-Mi Yang
Yeon-Mi Yang
DLDae-Woo Lee
Dae-Woo Lee
Because of the heterogeneous nature of the evidence regarding dentists' job satisfaction, an overview was necessary to examine dentists' level of job satisfaction and to determine related work environmental factors. A literature search was conducted using preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. Electronic database searches of PubMed/MEDLINE, EMBASE, and Web of Science were performed until March 1, 2020. Two independent authors collected data and assessed the methodological quality of primary studies using the Newcastle Ottawa Scale. Nine studies were included from the 1987 initially retrieved. Among the included studies, 5 exhibited a neutral level of satisfaction and originated from China, South Korea, Egypt, and the United States, and 3 studies from Canada, Lithuania, and the United States showed a high level of satisfaction. Only 1 study did not report the mean job satisfaction score. According to bias evaluation, 9 studies were considered low risk. The findings showed that dentists were satisfied with their jobs at a moderate to high level, and specialists were more satisfied than general dentists. Regarding work environmental factors, the 6 most satisfied factors were patient relationships, respect, delivery of care, staff, professional relationship, and professional environment. Five of the least satisfied factors were personal time, stress, income, practice management, and professional time. However, longitudinal studies would be required to identify changes in these factors. Further studies should be performed in middle- and low-income countries using the Dentist Satisfaction Survey, including stress evaluation.

1 May 2021
Verified
Journal Article
Closed access
VLVan Nhat Thang Le
Van Nhat Thang Le
JKJae-Gon Kim
Jae-Gon Kim
YYYeon-Mi Yang
Yeon-Mi Yang
DLDae-Woo Lee
Dae-Woo Lee

1 September 2020 in Journal of Dental Sciences
Verified
Journal Article
Open access
VLVan Nhat Thang Le
Van Nhat Thang Le
JKJae-Gon Kim
Jae-Gon Kim
YYYeon-Mi Yang
Yeon-Mi Yang
DLDae-Woo Lee
Dae-Woo Lee
Pre-eruptive intracoronal resorption (PEIR) is usually detected accidently in radiographs. However, treatment modality is still not reported systematically. The current study aimed to conduct a systematic review of the treatment modality of PEIR case reports and to report a case on the preservation of a vital pulp with surgical exposure in permanent maxillary canine. We systematically searched case reports from PubMed/MEDLINE, EMBASE, and Web of science databases. The treatment modality, suspected etiology, and follow up periods were collected from each study and reviewed by two authors independently. The initial search identified 100 studies. After the title/abstract screening, 37 articles received a full-text reading; and finally, 24 articles (29 patients and 37 affected teeth) were selected for the final review. Among the 24 unerupted teeth, surgical opening and restoration treatment of PEIR was chosen as a high priority for treatment options (n = 9, 36%). Among the 13 erupted teeth, restoration was applied for the prevention such as developing in size and fracture (n = 4, 31%). According to this systematic review, treatment modalities were based on the progressive nature of the lesion size and eruption state to establish the optimal approach for each patient. Clinicians should take into account the eruption status, lesion progression, the size of the lesion, and the degree of pulp involvement.