TNThanh Binh Nguyen

Thanh Binh Nguyen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Thanh Binh Nguyen has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Penicillin-resistant Streptococcus dysgalactiae subsp. equisimilis and the association with penicillin-binding protein mutations: a population genotypic and phenotypic study

    by Ouli Xie, Aimee Tan, Thanh Binh Nguyen, Andrew J. Hayes, Ravindra Dotel, Glen Carter, Matthew V. N. O'SUllivan, Katherine Bond, Christopher A. McDevitt, Tony M. Korman, et al.

    Streptococcus dysgalactiae subspecies equisimilis (SDSE) is increasingly recognized as a cause of human disease. Despite decades of penicillin use, SDSE is near universally penicillin-susceptible. Here we report and characterize by whole genome sequencing (WGS) three penicillin-resistant SDSE isolates (minimum inhibitory concentration [MIC] ≥0.256 mg/L) isolated from blood and skin in an individual with recurrent cellulitis on penicillin prophylaxis. The isolates carried 11 penicillin-binding protein (PBP) PBP2x, five PBP1a, and one PBP2b mutations that were distinct from the only previously reported WGS-characterized penicillin-resistant SDSE isolates ( n = 4). We then took a genotype-led approach to test the MICs of penicillin and amoxicillin for 63 isolates with PBP2x, PBP1a, and PBP2b variants selected from a well-characterized database of invasive SDSE isolates from Australia (2011–2023, n = 436). PBPs were highly conserved in Australian invasive SDSE genomes. Only a single isolate carrying a PBP2x variant with five mutations around the penicillin-binding cleft found in 1/436 invasive isolates demonstrated a four-fold rise in penicillin MIC, although remaining below clinical breakpoints. Strains with PBP2b and PBP1a variants alone were not associated with raised MICs. To provide broader context for PBP variants, we then examined a global database of SDSE genomes ( n = 1,160). PBP2x mutations in isolates with raised and/or resistant penicillin MICs were found in only nine global SDSE database genomes. SDSE penicillin resistance is rare and associated with multiple PBP mutations, particularly PBP2x. WGS with phenotypic testing of novel PBP variants could be used to monitor emerging mutations associated with raised penicillin MICs.

  • Open Access

    LAD: A Hybrid Deep Learning System for Benign Paroxysmal Positional Vertigo Disorders Diagnostic

    by Trung Xuan Pham, Jin Woong Choi, Rusty John Lloyd Mina, Thanh Nguyen, Sultan Rizky Madjid, Chang Dong Yoo

    Herein, we introduce "Look and Diagnose" (LAD), a hybrid deep learning-based system that aims to support doctors in the medical field in diagnosing effectively the Benign Paroxysmal Positional Vertigo (BPPV) disorder. Given the body postures of the patient in the Dix-Hallpike and lateral head turns test, the visual information of both eyes is captured and fed into LAD for analyzing and classifying into one of six possible disorders the patient might be suffering from. The proposed system consists of two streams: (1) an RNN-based stream that takes raw RGB images of both eyes to extract visual features and optical flow of each eye followed by ternary classification to determine left/right posterior canal (PC) or other; and (2) pupil detector stream that detects the pupil when it is classified as Non-PC and classifies the direction and strength of the beating to categorize the Non-PC types into the remaining four classes: Geotropic BPPV (left and right) and Apogeotropic BPPV (left and right). Experimental results show that with the patient's body postures, the system can accurately classify given BPPV disorder into the six types of disorders with an accuracy of 91% on the validation set. The proposed method can successfully classify disorders with an accuracy of 93% for the Posterior Canal disorder and 95% for the Geotropic and Apogeotropic disorder, paving a potential direction for research with the medical data.