Brief Bio

Dr. Han Liu is an AI Scientist at Siemens Healthineers, leading projects on scalable AI algorithms for whole-body oncology. His research spans classification, segmentation, detection, registration, and synthesis across 2D and 3D medical imaging, with publications in top venues including MICCAI and IEEE TMI, and multiple 1st place finishes in international challenges.

During his Ph.D. at Vanderbilt University, he developed innovative annotation-efficient deep learning algorithms, including methods for domain adaptation, missing modality problems, and partial label learning.

755 College Road East,
Princeton, NJ 08540
Digital Technology and Innovation (DTI)
Siemens Healthineers

Email: han.liu@siemens-healthineers.com

[Curriculum Vitae]

Education

AUG.2019 - MAY.2024

Vanderbilt University

Ph.D. in Computer Science (IBM Fellowship, University Graduate fellowship)

AUG.2016 - AUG.2017

Yale University

M.S. in Biomedical Engineering

AUG.2012 - MAY.2016

Rensselaer Polytechnic Institute

B.S. in Biomedical Engineering and Electrical Engineering (Dean's List)

Experience

JUNE.2024 - PRESENT

Siemens Healthineers

AI/ML Scientist

MAY.2022 - DEC.2022

Siemens Healthineers

Research Intern. Advisor: Dr. Zhoubing Xu

  • Universal 3D Segmentation Model with Partially Labeled Datasets [paper]
SEP.2017 - MAY.2019

University of Pittsburgh Medical Center

Research Associate. Advisor: Prof. Jiantao Pu

  • Thoracic disease classification on Chest X-ray [paper]
  • Optic disc/cup segmentation on fundus images [paper]
  • Vasculature identification surrounding pulmonary nodules [paper]

Competitions

vlm3d

VLM3D Challenge - 1st Place

Team: Han Liu, Bogdan Georgescu, Yanbo Zhang, Gengyan Zhao, Youngjin Yoo, Eli Gibson, Sasa Grbic

Topic: Multi-abnormality Classification on Chest CT

[Paper] [Code]

panorama

PANORAMA Challenge - 1st Place

Team: Han Liu, Riqiang Gao, Sasa Grbic

Topic: Early Detection of Pancreatic Ductal Adenocarcinoma (PDAC) on Abdominal Contrast-enhanced CTs

[Paper] [Code]

crossmoda2023

CrossMoDA 2023 Challenge - 1st Place

Team: Han Liu, Yubo Fan, Zhoubing Xu, Benoit Dawant, Ipek Oguz

Topic: MRI Cross-modality Synthesis and Tumor Segmentation

[Paper] [Code]

msspine

MS-Multi-Spine 2025 Challenge - 1st Place

Team: Jiacheng Wang, Han Liu, Hao Li, Francesca Bagnato, Ipek Oguz

Topic: Multiple Sclerosis Spinal Cord Lesion Detection with Missing Modalities

[Paper] [Code]

Selected Publications

Please check Google Scholar for the full list of my publications.

revisting

Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification

Han Liu, Bogdan Georgescu, Yanbo Zhang, Youngjin Yoo, Michael Baumgartner, Riqiang Gao, Jianing Wang, Gengyan Zhao, Eli Gibson, Dorin Comaniciu, Sasa Grbic

Under submission (🏆1st place in VLM3D Challenge)

[Paper] [Code]

pandx

PanDx: AI-assisted Early Detection of Pancreatic Ductal Adenocarcinoma on Contrast-enhanced CT

Han Liu, Riqiang Gao, Eileen Krieg, Sasa Grbic

MICCAI AMAI 2025 (🏆1st place in PANORAMA Challenge)

[Paper] [Code]

cosst

COSST: Multi-organ Segmentation with Partially Labeled Datasets Using Comprehensive Supervisions and Self-training

Han Liu, Zhoubing Xu, Riqiang Gao, Hao Li, Jianing Wang, Guillaume Chabin, Ipek Oguz, and Sasa Grbic

IEEE Transactions on Medical Imaging, 2024

[Paper]

intrastyler

IntraStyler: Exemplar-based Style Synthesis for Cross-modality Domain Adaptation

Han Liu, Yubo Fan, Hao Li, Dewei Hu, Daniel Moyer, Zhoubing Xu, Benoit Dawant, Ipek Oguz

Technical Report (Extension of 🏆1st place solution of CrossMoDA 2023 Challenge)

[Paper] [Code]

colossal

COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation

Han Liu, Hao Li, Xing Yao, Yubo Fan, Dewei Hu, Benoit Dawant, Vishwesh Nath, Zhoubing Xu, and Ipek Oguz

MICCAI 2023

[Paper] [Code]

crossmoda

Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptation

Han Liu, Yubo Fan, Zhoubing Xu, Benoit Dawant, and Ipek Oguz

MICCAI BrainLes 2023 (🏆1st place in CrossMoDA 2023 Challenge)

[Paper] [Code]

evaluation

Evaluation of synthetically generated computed tomography for use in transcranial focused ultrasound procedures

Han Liu, Michelle Sigona, Thomas Manuel, Li Min Chen, Benoit Dawant, Charles Caskey

Journal of Medical Imaging, 2023

[Paper] [Code]

moddrop++

ModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalities

Han Liu, Yubo Fan, Hao Li, Jiacheng Wang, Dewei Hu, Can Cui, Ho Hin Lee, Huahong Zhang, and Ipek Oguz

MICCAI 2022 (Early Accept)

[Paper] [Code]

sdfn

SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images

Han Liu, Lei Wang, Yandong Nan, Faguang Jin, and Jiantao Pu

Computerized Medical Imaging and Graphics, 2019

[Paper]

Professional Activities

Journal Reviewer

  • Medical Image Analysis (MedIA)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Journal of Biomedical and Health Informatics (JBHI)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • The Journal of Machine Learning for Biomedical Imaging (MELBA)
  • Computers in Biology and Medicine (CIBM)
  • Computerized Medical Imaging and Graphics (CMIG)

Conference Reviewer

  • Medical Image Computing and Computer Assisted Interventions (MICCAI)
  • Medical Imaging with Deep Learning (MIDL)
  • International Symposium on Biomedical Imaging (ISBI)
  • Simulation and Synthesis in Medical Imaging
  • Medical Imaging Meets NeurIPS
  • Knowledge Discovery and Data Mining (KDD)

Guest Lectures

  • CS-8395 (2022 Fall): Open Source Programming for Medical Image Processing
  • CS-6357 (2023 Fall): Open Source Programming for Medical Image Analysis