Comparison of CNNs and Transformer Models in Diagnosing Bone Metastases in Bone Scans Using Grad-CAM
Compared with traditional CNN and transformer models, the ConvNeXt model demonstrated superior diagnostic performance in detecting bone metastases from bone scans, especially in cases of polymetastasis, suggesting its potential in medical image analysis.
Authors
- Ik Yang (ORCID: https://orcid.org/0000-0002-9606-4556)
- Hye Joo Son (ORCID: https://orcid.org/0000-0003-1290-0949)
- Dohyoung Rim (ORCID: https://orcid.org/0000-0003-2022-6333)
- Ji Young Woo (ORCID: https://orcid.org/0000-0002-6200-0159)
- Hee Sung Hwang (ORCID: https://orcid.org/0000-0002-2803-0282)
- Sehyun Pak (ORCID: https://orcid.org/0009-0006-6763-0674)
- Suk Hyun Lee (ORCID: https://orcid.org/0000-0003-4580-3918)
- Dongwoo Kim (ORCID: https://orcid.org/0000-0002-1723-604X)
- Min Seok Choi
Institutions
- SK Group (South Korea) (KR)
- Hallym University (KR)
- Hallym University Kangnam Sacred Heart Hospital (KR)
- Hallym University Sacred Heart Hospital (KR)
- Dankook University (KR)
Publication Details
- Journal
- Clinical Nuclear Medicine
- Published
- 2025-04-16
- DOI
- https://doi.org/10.1097/rlu.0000000000005898
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 4.08