Junguo Ni

Junguo Ni

Auto-generated profile, based on publicly available information

Junguo Ni

Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
19 December 2025 in Journal of Orthopaedic Translation
Verified
Journal Article
Open access
HWHantang Wang
Hantang Wang
LZLanlan Zhang
Lanlan Zhang
YZYuqi Zhang
Yuqi Zhang
WWWei Wang
Wei Wang
JNJunguo Ni
Junguo Ni
CWCHUNYI WEN
CHUNYI WEN
Current methods to assess growth plate predominantly rely on rudimentary metrics such as tissue thickness, which fail to capture the dynamic, spatial and functional heterogeneity of chondrocyte populations during endochondral ossification. To address this gap, we developed a computational histomorphometric pipeline (Growth Plate Professional Analyzer, “GP Pro”), designed to quantify chondrocyte kinetics and maturation gradients at single-cell resolution using routine histological tissue sections. GP Pro integrates three automated modules: (1) batch processing of whole-slide images (WSIs) with growth plate localization, (2) segmentation of the growth plate using Segment Anything Model 2 (SAM2), and (3) single-cell lacunae analysis to extract morphometric and spatial distribution features across differentiation stages. For GP PRO's feasibility study, we conducted high-throughput testing on mouse/hamster/rat knee sections stained with Safranin-O/fastgreen (Safranin-O) and Hematoxylin & Eosin (H&E) to evaluate the computational efficiency and accuracy of the whole system and built-in functions. For GP PRO's application validation, tibial growth plates from normotensive Wistar-Kyoto (WKY) and spontaneously hypertensive rats (SHRs) were tested by the pipeline, correlating outputs with histochemical staining and micro-CT scanning results. GP PRO demonstrates satisfactory computational efficiency, with a processing time as low as 3.6 s per section and achieves an end-to-end automated processing success rate of above 95 %. Additionally, it boasts an average chondrocyte identification accuracy of 90.28 % and a macro-precision of 94.76 % in cell classification. In the application of SHR, GP Pro revealed a 4.03 percentage points increase in proliferative chondrocyte proportion (p < 0.05; 95 % CI: 0.59–7.47) and the presence of aberrantly elongated pre-hypertrophic chondrocytes at 3-month-old, indicative of maturation arrest. These cellular perturbations aligned with micro-CT showing a 36.04 percentage points decrease in primary spongiosa bone volume fraction (p < 0.001; 95 % CI: 30.10–41.97), suggesting compromised osteogenic coupling. Histology confirmed premature hyperproliferation and delayed hypertrophic differentiation in SHR growth plates. GP Pro establishes a scalable platform for mapping chondrocyte behavior in situ, enabling unprecedented resolution of growth plate pathobiology. By linking hypertrophic differentiation delays to trabecular bone deficits in hypertension, this tool advances mechanistic studies of endochondral ossification and offers translational potential for diagnosing growth disorders or monitoring therapeutic interventions in multiple species. This study introduces GP Pro, an AI-driven histomorphometric platform that bridges pre-clinical research and clinical applications by enabling high-throughput, single-cell resolution analysis of growth plate dynamics directly from WSIs.