3D lymphoma segmentation on PET/CT images via multi‐scale information fusion with cross‐attention
This study presents an effective automatic segmentation method for DLBCL that leverages the complementary strengths of PET and CT imaging. The method demonstrates robust performance on both private and publicly available datasets, ensuring its reliability and generalizability. Our method provides clinicians with more precise tumor delineation, which can improve the accuracy of diagnostic interpretations and assist in treatment planning for DLBCL patients. The code for the proposed method is available at https://github.com/chenzhao2023/lymphoma_seg.
Authors
- Weihua Zhou (ORCID: https://orcid.org/0000-0002-1056-7612)
- H. K. Huang (ORCID: https://orcid.org/0009-0001-9719-7430)
- Jiaofen Nan (ORCID: https://orcid.org/0000-0001-6730-6977)
- Chuang Han (ORCID: https://orcid.org/0000-0002-1295-8991)
- Shenmiao Yang (ORCID: https://orcid.org/0000-0001-7261-8449)
- Zhao Chen (ORCID: https://orcid.org/0000-0002-5782-3329)
- Liheng Qiu
- Yanting Li (ORCID: https://orcid.org/0000-0002-2528-747X)
- Fubao Zhu
- Longxi Li (ORCID: https://orcid.org/0000-0001-7898-8838)
Institutions
- Michigan Technological University (US)
- Kennesaw State University (US)
- Peking University (CN)
- Zhengzhou University of Light Industry (CN)
- Peking University People's Hospital (CN)
- Biocom (US)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-03-20
- DOI
- https://doi.org/10.1002/mp.17763
- Citations
- 1
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- National Natural Science Foundation of China