Tongxu Zhang

Tongxu Zhang

Knee osteoarthritis (OA) assessment involves a natural but often underused label hierarchy: a coarse binary OA decision and a fine-grained Kellgren--Lawrence (KL) severity grade. Existing deep learning studies commonly treat these targets as separate classification problems, either reducing OA assessment to disease presence or directly optimizing noisy ordinal KL labels. In this work, we ask whether this clinical hierarchy can serve as a representation-level supervisory prior. Rather than introducing a complex architecture, we use a deliberately simple dual-head model with a shared encoder and two task-specific heads as a probe of hierarchical supervision. We compare single-OA, single-KL, and dual-head training across multiple 3D backbones under the same test protocol. Beyond standard classification metrics, we perform paired statistical comparisons, analyze latent severity-axis geometry, and examine saliency overlap with cartilage regions. The results show that dual-head supervision produces backbone-dependent gains, with clear improvements in KL-related metrics for selected backbones. More importantly, the gains are accompanied by a more ordered coarse-to-fine latent organization and, for responsive backbones, stronger anatomical alignment of saliency with cartilage. These findings suggest that even simple hierarchical dual-head supervision can reshape disease representations under noisy coarse/fine labels, providing a useful inductive bias for OA diagnosis and severity grading.

Tongxu Zhang

Point cloud upsampling is crucial for tasks like 3D reconstruction. While existing methods rely on patch-based inputs, and there is no research discussing the differences and principles between point cloud model full input and patch based input. Ergo, we propose a novel approach using whole model inputs i.e. Average Segment input. Our experiments on PU1K and ABC datasets reveal that patch-based inputs consistently outperform whole model inputs. To understand this, we will delve into factors in feature extraction, and network architecture that influence upsampling results.

Tongxu Zhang, Bei Wang

High-fidelity 3D anatomical reconstruction is a prerequisite for downstream clinical tasks such as preoperative planning, radiotherapy target delineation, and orthopedic implant design. We present Med-PU, a knowledge-driven framework that integrates volumetric medical image segmentation with point cloud upsampling for accurate pelvic shape reconstruction. Unlike landmark- or PCA-based statistical shape models, Med-PU learns an implicit anatomical prior directly from large-scale 3D shape data, enabling dense completion and refinement from sparse segmentation-derived point sets. The pipeline couples SAM-Med3D-based voxel segmentation, point extraction, deep upsampling, and surface reconstruction, yielding smooth and topologically consistent meshes. We evaluate Med-PU on pelvic CT datasets (MedShapePelvic for training and Pelvic1k for validation), benchmarking against state-of-the-art upsampling methods using comprehensive geometry and surface metrics. Med-PU consistently improves surface quality and anatomical fidelity while reducing artifacts, demonstrating robustness across input densities. Although validated on the pelvis, the approach is anatomy-agnostic and applicable to other skeletal regions and organs. These results suggest Med-PU as a practical, generalizable tool to bridge segmentation outputs and clinically usable 3D models.

Tongxu Zhang, Bei Wang

In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both global and local structural features of point clouds. Specifically, we extracted global features from uniformly segmented inputs (Average Segments) and local features from patch-based inputs of the same point cloud. These two types of features were processed through parallel autoencoders, fused, and then fed into a shared decoder for upsampling. This dual-input design improved feature completeness and cross-scale consistency, especially in sparse and noisy regions. Our framework was applied to several state-of-the-art autoencoder-based networks and validated on standard datasets. Experimental results demonstrated consistent improvements in geometric fidelity and robustness. In addition, saliency maps confirmed that parallel global-local learning significantly enhanced the interpretability and performance of point cloud upsampling.

Tongxu Zhang

Background and Objective: Radiomics of knee MRI requires robust, anatomically meaningful regions of interest (ROIs) that jointly capture cartilage and subchondral bone. Most existing work relies on manual ROIs and rarely reports quality control (QC). We present LM-CartSeg, a fully automatic pipeline for cartilage/bone segmentation, geometric lateral/medial (L/M) compartmentalisation and radiomics analysis. Methods: Two 3D nnU-Net models were trained on SKM-TEA (138 knees) and OAIZIB-CM (404 knees). At test time, zero-shot predictions were fused and refined by simple geometric rules: connected-component cleaning, construction of 10 mm subchondral bone bands in physical space, and a data-driven tibial L/M split based on PCA and k-means. Segmentation was evaluated on an OAIZIB-CM test set (103 knees) and on SKI-10 (100 knees). QC used volume and thickness signatures. From 10 ROIs we extracted 4 650 non-shape radiomic features to study inter-compartment similarity, dependence on ROI size, and OA vs. non-OA classification on OAIZIB-CM Results: Post-processing improved macro ASSD on OAIZIB-CM from 2.63 to 0.36 mm and HD95 from 25.2 to 3.35 mm, with DSC 0.91; zero-shot DSC on SKI-10 was 0.80. The geometric L/M rule produced stable compartments across datasets, whereas a direct L/M nnU-Net showed domain-dependent side swaps. Only 6 to 12 percent of features per ROI were strongly correlated with volume or thickness. Radiomics-based models models restricted to size-linked features. Conclusions: LM-CartSeg yields automatic, QCd ROIs and radiomic features that carry discriminative information beyond simple morphometry, providing a practical foundation for multi-centre knee OA radiomics studies.

Tongxu Zhang, Zhiming Liang, Bei Wang

Point clouds have become an increasingly important representation for 3D medical imaging, offering a compact, surface-preserving alternative to traditional voxel or mesh-based approaches. Recent advances in deep learning have enabled rapid progress in extracting, modeling, and analyzing anatomical shapes directly from point cloud data. This paper provides a comprehensive and systematic survey of learning-based shape analysis for medical point clouds, focusing on three fundamental tasks: registration, reconstruction, and variation modeling. We review recent literature from 2021 to 2025, summarize representative methods, datasets, and evaluation metrics, and highlight clinical applications and unique challenges in the medical domain. Key trends include the integration of hybrid representations, large-scale self-supervised models, and generative techniques. We also discuss current limitations, such as data scarcity, inter-patient variability, and the need for interpretable and robust solutions for clinical deployment. Finally, future directions are outlined for advancing point cloud-based shape learning in medical imaging.

Tongxu Zhang, Bei Wang

In recent years, multitudes of researches have applied deep learning to automatic sleep stage classification. Whereas actually, these works have paid less attention to the issue of cross-subject in sleep staging. At the same time, emerging neuroscience theories on inter-subject correlations can provide new insights for cross-subject analysis. This paper presents the MViTime model that have been used in sleep staging study. And we implement the inter-subject correlation theory through contrastive learning, providing a feasible solution to address the cross-subject problem in sleep stage classification. Finally, experimental results and conclusions are presented, demonstrating that the developed method has achieved state-of-the-art performance on sleep staging. The results of the ablation experiment also demonstrate the effectiveness of the cross-subject approach based on contrastive learning.