2026

Multi-level Asymmetric Contrastive Learning for Medical Image Segmentation Pre-training
Multi-level Asymmetric Contrastive Learning for Medical Image Segmentation Pre-training

Shuang Zeng, Lei Zhu, Xinliang Zhang, Qian Chen, Hangzhou He, Lujia Jin, Zifeng Tian, Zhaoheng Xie, Micky C Nnamdi, Wenqi Shi, J Ben Tamo, May D. Wang, Yanye Lu# (# corresponding author)

IEEE Journal of Biomedical and Health Informatics 2026 中科院二区Top, IF:6.8

We propose a novel Multi-level Asymmetric Contrastive Learning framework named MACL by introducing an asymmetric CL structure and a multi-level CL strategy to realize one-stage encoder-decoder synchronous pre-training for medical image segmentation.

[Paper] [Code]

Multi-level Asymmetric Contrastive Learning for Medical Image Segmentation Pre-training

Shuang Zeng, Lei Zhu, Xinliang Zhang, Qian Chen, Hangzhou He, Lujia Jin, Zifeng Tian, Zhaoheng Xie, Micky C Nnamdi, Wenqi Shi, J Ben Tamo, May D. Wang, Yanye Lu# (# corresponding author)

IEEE Journal of Biomedical and Health Informatics 2026 中科院二区Top, IF:6.8

We propose a novel Multi-level Asymmetric Contrastive Learning framework named MACL by introducing an asymmetric CL structure and a multi-level CL strategy to realize one-stage encoder-decoder synchronous pre-training for medical image segmentation.

[Paper] [Code]

SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training
SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training

Shuang Zeng, Lei Zhu, Xinliang Zhang, Hangzhou He, Yanye Lu# (# corresponding author)

IEEE Transactions on Image Processing 2026 中科院一区Top, IF:13.7

We propose SuperCL, a superpixel-guided contrastive learning framework for medical image segmentation pre-training, which exploits the structural prior and pixel correlation of images by introducing two novel contrastive pairs generation strategies: Intra-image Local Contrastive Pairs (ILCP) Generation and Inter-image Global Contrastive Pairs (IGCP) Generation.

[Paper] [Code]

SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training

Shuang Zeng, Lei Zhu, Xinliang Zhang, Hangzhou He, Yanye Lu# (# corresponding author)

IEEE Transactions on Image Processing 2026 中科院一区Top, IF:13.7

We propose SuperCL, a superpixel-guided contrastive learning framework for medical image segmentation pre-training, which exploits the structural prior and pixel correlation of images by introducing two novel contrastive pairs generation strategies: Intra-image Local Contrastive Pairs (ILCP) Generation and Inter-image Global Contrastive Pairs (IGCP) Generation.

[Paper] [Code]

2025

Improve retinal artery/vein classification via channel coupling
Improve retinal artery/vein classification via channel coupling

Shuang Zeng, Chee Hong Lee, Kaiwen Li, Boxu Xie, Ourui Fu, Hanghzou He, Lei Zhu#, Yanye Lu#, Fangxiao Cheng# (# corresponding author)

Expert Systems With Applications 2025 中科院一区Top, IF:7.5

We design a novel loss named Channel-Coupled Vessel Consistency Loss to enforce the coherence and consistency between vessel, artery and vein predictions and a regularization term named intra-image pixel-level contrastive loss to extract more discriminative feature-level fine-grained representations for accurate retinal A/V classification.

[Paper] [Code]

Improve retinal artery/vein classification via channel coupling

Shuang Zeng, Chee Hong Lee, Kaiwen Li, Boxu Xie, Ourui Fu, Hanghzou He, Lei Zhu#, Yanye Lu#, Fangxiao Cheng# (# corresponding author)

Expert Systems With Applications 2025 中科院一区Top, IF:7.5

We design a novel loss named Channel-Coupled Vessel Consistency Loss to enforce the coherence and consistency between vessel, artery and vein predictions and a regularization term named intra-image pixel-level contrastive loss to extract more discriminative feature-level fine-grained representations for accurate retinal A/V classification.

[Paper] [Code]

Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation
Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation

Shuang Zeng*, Chee Hong Lee*, Micky C. Nnamdi, Wenqi Shi, J. Ben Tamo, Hangzhou He, Xinliang Zhang, Qian Chen, May D. Wang, Lei Zhu#, Yanye Lu#, Qiushi Ren# (* equal contribution, # corresponding author)

Image and Vision Computing 2025

We propose a new retinal vessel segmentation model named AttUKAN to selectively filter skip connection features and a Label-guided Pixel-wise Contrastive Loss (LPCL) to extract more discriminative features by distinguishing between foreground vessel-pixel sample pairs and background sample pairs.

[Paper] [Code]

Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation

Shuang Zeng*, Chee Hong Lee*, Micky C. Nnamdi, Wenqi Shi, J. Ben Tamo, Hangzhou He, Xinliang Zhang, Qian Chen, May D. Wang, Lei Zhu#, Yanye Lu#, Qiushi Ren# (* equal contribution, # corresponding author)

Image and Vision Computing 2025

We propose a new retinal vessel segmentation model named AttUKAN to selectively filter skip connection features and a Label-guided Pixel-wise Contrastive Loss (LPCL) to extract more discriminative features by distinguishing between foreground vessel-pixel sample pairs and background sample pairs.

[Paper] [Code]

Publication Lists

  • [20] Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration. Zhengjian Yao, Jiakui Hu, Kaiwen Li, Hangzhou He, Xinliang Zhang, Shuang Zeng, et al. arXiv preprint, 2026. [Paper]
  • [19] AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs. Xinliang Zhang, Lei Zhu, Hangzhou He, Shuang Zeng, Ourui Fu, Jiakui Hu, Zhengjian Yao, Yanye Lu arXiv preprint, 2025. [Paper]
  • [18] MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics. Yuxing Lu, Xukai Zhao, J. Ben Tao, Micky C. Nnamdi, Rui Peng, Shuang Zeng, et al. arXiv preprint, 2025. [Paper]
  • [17] I^2R: Inter and Intra-image Refinement in Few Shot Segmentation. Ourui Fu, Hangzhou He, Xinliang Zhang, Lei Zhu, Shuang Zeng, et al. arXiv preprint, 2025. [Paper]
  • [16] Multi-level asymmetric contrastive learning for volumetric medical image segmentation pre-training. Shuang Zeng, et al. IEEE Journal of Biomedical and Health Informatics, 2026. [Paper]
  • [15] Supercl: Superpixel guided contrastive learning for medical image segmentation pre-training. Shuang Zeng, et al. IEEE Transactions on Image Processing, 2026. [Paper]
  • [14] Improve retinal artery/vein classification via channel coupling. Shuang Zeng, et al. Expert Systems With Applications, 2025. [Paper]
  • [13] Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation. Shuang Zeng, et al. Image and Vision Computing, 2025. [Paper]
  • [12] MultiMed-RAG: Leveraging Multi-Source Knowledge and Agent Collaboration for Medical Tasks. Yuxing Lu, Goi Sin Yee, Shuang Zeng, et al. IEEE Engineering in Medicine and Biology Society - Biomedical and Health Informatics (BHI), 2025. [Paper]
  • [11] Assessing Large Language Models for Metabolomics. Yuxing Lu, Goi Sin Yee, Shuang Zeng, et al. IEEE Engineering in Medicine and Biology Society - Biomedical and Health Informatics (BHI), 2025. [Paper]
  • [10] One-Month Changes in Choroidal Vascularity Index of Medium Vessel Layer in Children with Myopia Wearing Orthokeratology Lenses: a Predictor for One-Year Changes in Axial Length. Junmeng Li, Bei Rong, Lei Zhu, Ruilin Zhu, Xin Rong, Yuwei Wang, Yadi Zhang, Xiaopeng Gu, Shuang Zeng, et al. Ophthalmology and Therapy, 2025. [Paper]
  • [9] Points-supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning. Kaiwen Li, Hangzhou He, Shuang Zeng, et al. IEEE Transactions on Medical Imaging (TMI), 2025. [Paper]
  • [8] V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer. Hangzhou He, Lei Zhu, Xinliang Zhang, Shuang Zeng, et al. AAAI Conference on Artificial Intelligence (AAAI), 2025. [Paper]
  • [7] Exploiting Inherent Class Label: Towards Robust Scribble Supervised Semantic Segmentation. Xinliang Zhang, Lei Zhu, Shuang Zeng, et al. arXiv preprint, 2025. [Paper]
  • [6] Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation. Lei Zhu, Xinliang Zhang, Hangzhou He, Qian Chen, Sha Li, Shuang Zeng, et al. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024. [Paper]
  • [5] LUCIDA: Low-dose Universal-tissue CT Image Domain Adaptation For Medical Segmentation. Yixin Chen, Xiangxi Meng, Yan Wang, Shuang Zeng, et al. Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024. [Paper]
  • [4] Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation. Qian Chen, Lei Zhu, Hangzhou He, Xinliang Zhang, Shuang Zeng, et al. Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024. [Paper]
  • [3] Choroidal Optical Coherence Tomography Angiography: Noninvasive Choroidal Vessel Analysis via Deep Learning. Lei Zhu, Junmeng Li, Yicheng Hu, Ruilin Zhu, Shuang Zeng, et al. Health Data Science, 2024. [Paper]
  • [2] Choroidal Vascularity Index and Choroidal Structural Changes in Children With Nephrotic Syndrome. Wenbo Zhang, Junmeng Li, Lei Zhu, Shuang Zeng, et al. Translational Vision Science & Technology (TVST), 2024. [Paper]
  • [1] Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography images. Bin Qiu, Shuang Zeng, et al. Journal of Biophotonics, 2021. [Paper]