Zongwei Zhou

UNetPlusPlus. [IEEE TMI Best Paper Award] Official Implementation for UNet++

ModelsGenesis. [MICCAI 2019 Young Scientist Award] [MEDIA 2020 Best Paper Award] Models Genesis, one of the first "foundation" models in medical image analysis for multiple downstream tasks

SuPreM. [ICLR 2024 oral; top 1.2%] Supervised Pre-Trained 3D Models for Medical Image Analysis (9,262 CT volumes + 25 annotated classes)

SyntheticTumors. [CVPR 2023] Label-Free Liver Tumor Segmentation

AbdomenAtlas. [NeurIPS 2023] AbdomenAtlas 1.0 (5,195 CT volumes + 9 annotated classes)

DiffTumor. [CVPR 2024] Generalizable Tumor Synthesis - Realistic Synthetic Tumors in Liver, Pancreas, and Kidney

RadGPT. [ICCV 2025] AbdomenAtlas 3.0 (9,262 CT volumes + medical reports). These “superhuman” reports are more accurate, detailed, standardized, and generated faster than traditional human-made reports.

Touchstone. [NeurIPS 2024] Touchstone - Benchmarking AI on 5,172 o.o.d. CT volumes and 9 anatomical structures

R-Super. [MICCAI 2025 Best Paper Award] Learning Segmentation from Radiology Reports

PanTS. [NeurIPS 2025] PanTS: The Pancreatic Tumor Segmentation Dataset. PanTS is a vision-language dataset, which enables development and external evaluation of AI for pancreatic tumor detection, localization, and reporting, with multi-structure context and metadata to support robust, anatomy-aware modeling.

Active-Learning. [CVPR 2017] Official Implementation for AIFT

ContinualLearning. [MICCAI 2023] Continual Learning for Abdominal Multi-Organ and Tumor Segmentation

TextoMorph. [IEEE TMI] Tumor synthesis leveraging medical reports.

Pixel2Cancer. [MICCAI 2024] Cellular Automata for Tumor Development - Realistic Synthetic Tumors in Liver, Pancreas, and Kidney

SMILE. Python

CARE. [NeurIPS 2025] Completeness-Aware Reconstruction Enhancement

LabelCritic. [ISBI 2025] Design Data Before Models: Using large vision-language models to automatically enhance medical dataset annotations.

SimSID. [IEEE TPAMI] Anomaly Detection in Chest X-ray

ScaleMAI.

LabelAssemble. [ISBI 2023] Official Implementation for Label-Assemble

OnlineLearning. [MICCAI 2024] Embracing Massive Medical Data

Dissertation. Zongwei Zhou's Ph.D. Dissertation

MerlinPlus. [MICCAI 2026] Merlin Plus is the first large-scale public CT dataset with radiologist-created tumor masks across 9 organs (spleen, bladder, gallbladder, stomach, duodenum, prostate, adrenal glands, esophagus, and uterus), adding 1,153 per-voxel tumor masks to the Stanford Merlin dataset.

Eureka. Python

GenesisLung. Jupyter Notebook

bodymaps. JavaScript

bodymaps-website. Web App for NIfTI CT Scan + Segmentation Visualization

ColdStart. Cold Start Problem in Vision Active Learning

Stats. Jupyter Notebook