ResearcherUniversity of North Carolina at Chapel HillNo recent work listed

Xu Han

ORCID-verified (high confidence, 0.95), identity_conf@1As of 8 November 2026

Matched on ORCID iD 0000-0003-3491-8576; OpenAlex author ID A5102012659. Sources: OpenAlex.

Their work

Papers: 1
Trials: 0
Grants: 0
Labs led: 0
Collaborators: 6

Papers, trials and grants by year

2021: 1 paper

Papers 1

Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dose radiation treatment of pancreatic canc… Co-author DOI 10.1002/mp.14906 ↗

Closest collaborators

The 6 strongest of 6 by collab_strength@1: shared papers, trials and grants, recent and small-team work weighing most.

Jun Hong · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗
Carla Hajj · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗
Marsha Reyngold · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗
G. S. Mageras · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗
Marc Niethammer Page · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗
Christopher H. Crane · 1 shared paper, 2021 · strength 0.12
- Paper Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dos… DOI 10.1002/mp.14906 ↗

How to reach this person

A chain of introductions through people who have published, run trials or held grants together (warm_path@1: fewest links first, then the strongest). Built from public records only; no contact details are kept.