Influence of early through late fusion on pancreas segmentation from imperfectly registered multimodal magnetic resonance imaging
Fusion in specific blocks can improve performance, but the best blocks for fusion are model-specific, and the gains are small. In imperfectly registered datasets, fusion is a nuanced problem, with the art of design remaining vital for uncovering potential insights. Future innovation is needed to better address fusion in cases of imperfect alignment of abdominal image pairs. The code associated with this project is available here https://github.com/MASILab/influence_of_fusion_on_pancreas_segmentation.
Authors
- Lianrui Zuo (ORCID: https://orcid.org/0000-0002-5923-9097)
- Samuel W. Remedios (ORCID: https://orcid.org/0000-0001-8634-8128)
- John Virostko (ORCID: https://orcid.org/0000-0003-3413-8801)
- Adam M. Saunders (ORCID: https://orcid.org/0000-0003-2912-9759)
- Alvin C. Powers (ORCID: https://orcid.org/0000-0003-1941-5786)
- Shunxing Bao (ORCID: https://orcid.org/0000-0001-6376-4292)
- Lucas W. Remedios
- Yuankai Huo (ORCID: https://orcid.org/0000-0002-2096-8065)
- Bennett A. Landman (ORCID: https://orcid.org/0000-0001-5733-2127)
- Han Liu (ORCID: https://orcid.org/0000-0002-0014-4675)
Institutions
- Johns Hopkins University (US)
- Vanderbilt University (US)
- The University of Texas at Austin (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-04-26
- DOI
- https://doi.org/10.1117/1.jmi.12.2.024008
- Citations
- 2
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.71
Funders
- National Science Foundation
- Leona M. and Harry B. Helmsley Charitable Trust
- Vanderbilt Institute for Clinical and Translational Research
- National Institutes of Health
- National Institute of Diabetes and Digestive and Kidney Diseases
- National Center for Advancing Translational Sciences