Pre-trained convolutional neural network with transfer learning by artificial illustrated images classify power Doppler ultrasound images of rheumatoid arthritis joints
Artificial images may be useful for training VGG-16. The present novel approach of using artificial images as an alternative to actual images for training a CNN has the potential to be applied in medical imaging fields that face difficulties in collecting real clinical images.
Authors
- Tatsunori Horie
- Yoshiharu Amasaki
- Yuichiro Fujieda (ORCID: https://orcid.org/0000-0003-4705-341X)
- Tamotsu Kamishima (ORCID: https://orcid.org/0000-0002-7293-7471)
- Tatsuya Atsumi (ORCID: https://orcid.org/0000-0001-5657-962X)
- Jun Fukae (ORCID: https://orcid.org/0000-0001-7482-8765)
- Yuki Sone
- Ken Katagishi
Institutions
- Sapporo University (JP)
- Hokkaido University (JP)
- Hokkaido University Hospital (JP)
Publication Details
- Journal
- Journal of International Medical Research
- Published
- 2025-02-01
- DOI
- https://doi.org/10.1177/03000605251318195
- Citations
- 5
- Primary Topic
- Rheumatoid Arthritis Research and Therapies
- Type
- article
- Field-Weighted Citation Impact
- 8.34