Radiogenomic explainable AI with neural ordinary differential equation for identifying post‐SRS brain metastasis radionecrosis
The HBNODE model effectively identifies BM radionecrosis from recurrence, enhancing explainability within XAI frameworks. Its performance encourages further exploration in clinical settings and suggests potential applicability across various XAI domains.
Authors
- Scott Floyd (ORCID: https://orcid.org/0000-0002-8067-2426)
- Peter E. Fecci (ORCID: https://orcid.org/0000-0002-2912-8695)
- Zachary J. Reitman (ORCID: https://orcid.org/0000-0002-9122-9550)
- Hangjie Ji (ORCID: https://orcid.org/0000-0001-7613-8522)
- Kyle J. Lafata (ORCID: https://orcid.org/0000-0002-4513-6249)
- Ke Lü (ORCID: https://orcid.org/0000-0001-8513-3352)
- Zhenyu Yang (ORCID: https://orcid.org/0000-0002-7137-2552)
- Eugene Vaios (ORCID: https://orcid.org/0000-0003-2122-6650)
- John P. Kirkpatrick (ORCID: https://orcid.org/0000-0002-4019-0350)
- Deshan Yang (ORCID: https://orcid.org/0009-0002-1335-4054)
- Jingtong Zhao
- Chunhao Wang
Institutions
- North Carolina State University (US)
- Duke University (US)
- Duke Kunshan University (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-01-29
- DOI
- https://doi.org/10.1002/mp.17635
- Citations
- 8
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 10.88
Funders
- National Institutes of Health
- National Cancer Institute