Qi Zhang张琦

Reconstructing Isotropic 3D Cervical MRI from Anisotropic Clinical Scans via Anatomy-Style Decoupled INRs

Qi Zhang^†, Xiuyuan Chen^†, Yibo Hu, Hongxing Shen, Jianqi Sun

Medical Image Computing and Computer Assisted Intervention - MICCAI 2026 · 2026 · 16888 · 478-487

Published online 26 September 2026. Springer lists 2027 as the citation year.

An anatomy-style decoupled hybrid implicit neural representation reconstructs an isotropic 3D cervical MRI volume from routine anisotropic multi-view scans. The method uses unified spatial coordinates, view-specific style embeddings, and stochastic view dropout without paired high-resolution supervision.

DOI10.1007/978-3-032-38179-8_46

@inproceedings{zhang2026jointsr,
  title={Reconstructing Isotropic 3D Cervical MRI from Anisotropic Clinical Scans via Anatomy-Style Decoupled INRs},
  author={Zhang, Qi and Chen, Xiuyuan and Hu, Yibo and Shen, Hongxing and Sun, Jianqi},
  booktitle={Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026},
  series={Lecture Notes in Computer Science},
  volume={16888},
  pages={478--487},
  publisher={Springer Nature Switzerland},
  year={2027},
  doi={10.1007/978-3-032-38179-8_46}
}

UniTransAD: Unified Translation Framework for Anomaly Detection in Brain MRI

Qi Zhang, Xia Li, Yibo Hu, Jianqi Sun

IEEE Transactions on Medical Imaging · 2026 · 45(9) · 4876-4891

A unified translation framework addresses brain MRI anomaly detection across diseases, sequences, and missing-input settings. Dynamic style prototypes and dual-level evidence support flexible inference under different combinations of MRI inputs.

DOI10.1109/TMI.2026.3711975

@article{zhang2026unitransad,
  title={UniTransAD: Unified Translation Framework for Anomaly Detection in Brain MRI},
  author={Zhang, Qi and Li, Xia and Hu, Yibo and Sun, Jianqi},
  journal={IEEE Transactions on Medical Imaging},
  year={2026},
  volume={45},
  number={9},
  pages={4876--4891},
  doi={10.1109/TMI.2026.3711975}
}

U2AD: Uncertainty-based unsupervised anomaly detection framework for detecting T2 hyperintensity in MRI spinal cord

Qi Zhang^†, Xiuyuan Chen^†, Ziyi He^†, Kun Wang^†, Lianming Wu, Hongxing Shen, Jianqi Sun

Medical Image Analysis · 2026 · 109 · 103939

U2AD detects spinal-cord T2 hyperintensity without requiring abnormal-region annotations. Its uncertainty-guided masking strategy balances reconstruction of normal anatomy with sensitivity to anomalies.

DOI10.1016/j.media.2026.103939

@article{zhang2026u2ad,
  title={U2AD: Uncertainty-based unsupervised anomaly detection framework for detecting T2 hyperintensity in MRI spinal cord},
  author={Zhang, Qi and Chen, Xiuyuan and He, Ziyi and Wang, Kun and Wu, Lianming and Shen, Hongxing and Sun, Jianqi},
  journal={Medical Image Analysis},
  volume={109},
  pages={103939},
  year={2026},
  doi={10.1016/j.media.2026.103939}
}

Pathology-Guided AI System for Accurate Segmentation and Diagnosis of Cervical Spondylosis

Qi Zhang^†, Xiuyuan Chen^†, Ziyi He^†, Lianming Wu, Kun Wang, Jianqi Sun, Hongxing Shen

IEEE Journal of Biomedical and Health Informatics · 2026 · 30(2) · 1216-1229

This pathology-guided system links cervical MRI segmentation with automated calculation of clinically relevant indicators. The design emphasises interpretable measurements and validation across clinical data sources.

DOI10.1109/JBHI.2025.3598469

@article{zhang2026pathology,
  title={Pathology-Guided AI System for Accurate Segmentation and Diagnosis of Cervical Spondylosis},
  author={Zhang, Qi and Chen, Xiuyuan and He, Ziyi and Wu, Lianming and Wang, Kun and Sun, Jianqi and Shen, Hongxing},
  journal={IEEE Journal of Biomedical and Health Informatics},
  volume={30},
  number={2},
  pages={1216--1229},
  year={2026},
  doi={10.1109/JBHI.2025.3598469}
}