VQPET: Leveraging Vector-Quantized Codebook Prior for PET Image Synthesis
A two-stage PET synthesis framework that learns a vector-quantized codebook prior from high-quality PET data and uses it to guide synthesis.
PET SynthesisRead paper
Shanghai Jiao Tong University Shanghai, China
Xiaoqian
Zhang张啸谦 / Shawno
Medical intelligence.
From representations to systems.
I study how machines learn from medical images — and build the research tools around them. M.S. student in Medical Imaging Technology at SJTU, with a background in biomedical engineering at Beihang.
Research & engineeringMedical imaging · Machine learning
Selected work
Explore all workIEEE TMI— VQPET
Learning codebook priors for PET image synthesis.
IVC— MoMIL
Multiple instance learning for whole-slide pathology.
Repo— ShawnoBot
A controlled gateway to the research workstation.
Research in focus
Learning the structure
behind the image.
My work connects representation learning with medical imaging: aggregating whole-slide information, learning synthesis priors, and understanding complementary imaging modalities.
MoMIL: Multi-order Enhanced Multiple Instance Learning for Computational Pathology
A journal article on multi-order enhanced multiple instance learning for stronger whole-slide representation learning in computational pathology.
Computational PathologyRead paper
Research Progress and Clinical Translation of Photoacoustic–Ultrasound Fusion Imaging in Breast Cancer Diagnosis and Therapy
A review of photoacoustic–ultrasound fusion imaging, AI-enhanced interpretation, and clinical translation for breast cancer diagnosis and therapy.
Photoacoustic ImagingRead paper
Also exploring
3D perception and spatially aware representations for volumetric medical data.
Research directionsBuilt for the workflow
Research needs
good systems, too.
Research infrastructure
ShawnoBot
A controlled bridge between Feishu and a local research workstation. Inspect GPU usage, training logs, and jobs; run allowlisted tasks and sandboxed Codex workflows from chat.
Explore ShawnoBotInterfaceFeishu message
ControlAuthorization & allowlists
WorkstationGPU · Logs · Codex tasks
Literature intelligence
notion-monthly-research
From recent arXiv papers to a structured research digest. Scheduled collection, model-assisted trend synthesis, and archival in Notion.
Explore the workflowLocal-first application
BetDogEye
A sports-betting portfolio analysis app with exposure and return analytics, local storage, data portability, and optional AI-assisted insights.
Explore the applicationThe foundation
Engineering roots.
Medical perspective.
Biomedical engineering training, medical imaging research, and hands-on experience with tissue data.
Full curriculum vitaeBeihang University
B.E. in Biomedical Engineering
BGI Research Institute
Research internship · Spatial transcriptomics, tissue annotation, and image segmentation
Shanghai Jiao Tong University
M.S. in Medical Imaging Technology
School of Medical Technology
Momenta
Algorithm Intern · Multi-camera BEV perception, 3D detection evaluation, calibration checks, and temporal-state validation
United Imaging Surgical
Internship · Multi-view endoscopic reconstruction and research engineering
Start a conversation
Shared questions.
Better research.
Interested in medical imaging, representation learning, or tools for research? Let’s talk.
xiaoqian_shawno@sjtu.edu.cn