Research

Publications & Projects

Generative models, diagnostic reasoning and medical image analysis.

Publications

Peer-reviewed papers and preprints

MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

Di Dai^†, Bo Liu^†, Youcheng Li^†, Haojun Yu^†, Zhuohang Bian, Quanlin Wu, Dong Wang, Sichen Meng, Hongye Xuan, Zijie Lan, Shenda Hong, Liwei Wang † co-first author

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2: 10785-10794

KDD 2026 arXiv PDF Code & Dataset

A foundation generative model for breast ultrasound image analysis

Haojun Yu^†, Youcheng Li^†, Nan Zhang^†, Zihan Niu^†, Xuantong Gong, Yanwen Luo, Haotian Ye, Siyu He, Quanlin Wu, Wangyan Qin, Mengyuan Zhou, Jie Han, Jia Tao, Ziwei Zhao, Di Dai, Di He, Dong Wang, Binghui Tang, Ling Huo, James Zou, Qingli Zhu, Yong Wang, Liwei Wang † co-first author

Nature Biomedical Engineering

Nature BME Preprint PDF Online Demo

A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories

Haojun Yu^†, Youcheng Li^†, Zihan Niu^†, Nan Zhang^†, Xuantong Gong^†, Huan Li^†, Zhiying Zou^†, Haifeng Qi^†, Zhenxiao Cao^†, Zijie Lan, Xingjian Yuan, Jiating He, Haokai Zhang, Shengtao Zhang, Zicheng Wang, Dong Wang, Ziwei Zhao, Congying Chen, Yong Wang, Wangyan Qin, Qingli Zhu, Liwei Wang † co-first author

Scientific Data 13(1): 370

Scientific Data arXiv Preprint PDF Dataset

Using artificial intelligence system for assisting the classification of breast ultrasound glandular tissue components in dense breast tissue

Hongju Yan, Chaochao Dai, Xiaojing Xu, Yuxuan Qiu, Lifang Yu, Lewen Huang, Bei Lin, Jianan Huang, Chenxiang Jiang, Yingzhao Shen, Jing Ji, Youcheng Li, Lingyun Bao

Scientific Reports 15(1): 11754

Full Text

Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses

Haojun Yu, Youcheng Li, Nan Zhang, Zihan Niu, Xuantong Gong, Yanwen Luo, Quanlin Wu, Wangyan Qin, Mengyuan Zhou, Jie Han, Jia Tao, Ziwei Zhao, Di Dai, Di He, Dong Wang, Binghui Tang, Ling Huo, Qingli Zhu, Yong Wang, Liwei Wang

arXiv preprint arXiv:2407.16634

arXiv PDF

ST-CellSeg: Cell segmentation for imaging-based spatial transcriptomics using multi-scale manifold learning

Youcheng Li, Leann Lac, Qian Liu, Pingzhao Hu

PLOS Computational Biology 20(6): e1012254

Full Text

Mining Negative Temporal Contexts for False Positive Suppression in Real-Time Ultrasound Lesion Detection

Haojun Yu, Youcheng Li, QuanLin Wu, Ziwei Zhao, Dengbo Chen, Dong Wang, Liwei Wang

Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 3-13

Conference arXiv PDF

Research Projects

Models, benchmarks and open research

BUSGen: A Foundation Generative Model for Breast Ultrasound

A generative model pretrained on more than 3.5 million breast ultrasound images. Few-shot adaptation produces task-specific synthetic data for downstream screening, diagnosis and prognosis research.

Medical AIGenerative AI

Nature BME Demo

BUS-CoT: Breast Ultrasound Diagnostic Reasoning

A breast ultrasound dataset with 11,439 images, 11,850 lesions and 4,838 patients, covering 99 histopathology categories. Expert annotations connect observations, imaging features, diagnoses and pathology.

Medical AIDataset

Scientific Data arXiv Dataset

MammoExpert: Reasoning in Mammography

A mammography benchmark with 2,379 images and 67 histopathology subtypes. Structured annotations cover observation, assessment and diagnostic synthesis.

Medical AIDiagnostic ReasoningDataset

KDD 2026 Code & Dataset

ST-CellSeg: Spatial Transcriptomics Cell Segmentation

A cell segmentation method for imaging-based spatial transcriptomics that combines image information with multi-scale manifold learning.

Computer VisionMachine Learning

PLOS Comp Bio

UltraDet: Real-time Ultrasound Lesion Detection

A video-based lesion detection method that uses negative temporal context to suppress false positives in real-time breast ultrasound.

Medical AIComputer Vision

MICCAI 2023 arXiv

TAILOR: Knowledge-driven AI-generated Data Pipeline

A knowledge-driven pipeline for generating synthetic breast ultrasound data to study diagnosis under long-tailed and rare-case data distributions.