Performance of deep learning-based segmentation of soft tissue sarcoma by MRI sequence, tumor type and location
Deep learning models achieve high accuracy for STS segmentation. However, their performance is critically dependent on tumor location and histology.
Authors
- Linda C. Kelahan (ORCID: https://orcid.org/0000-0003-2142-6003)
- Tugce Agirlar Trabzonlu (ORCID: https://orcid.org/0000-0001-7142-2612)
- Linkai Peng
- Zuzanna Kobus
- Amir A. Borhani (ORCID: https://orcid.org/0000-0001-8963-2984)
- Laetitia Perronne (ORCID: https://orcid.org/0000-0002-6752-3354)
- Mirinae Seo (ORCID: https://orcid.org/0000-0002-8989-9504)
- Bagci Ulas
- Pedro Hermida de Viveiros
- Nicolo Gennaro
- Seth M. Pollack
- Akhil Chawla
- Ryan Avery
- Spyridon Bakas
- Ahmad Pour Rashidi
- Chase Krumpelman
- Kamal Subedi
- Sean Sachdev
Institutions
- Northwestern University (US)
- Robert H. Lurie Comprehensive Cancer Center of Northwestern University
- Indiana University School of Medicine
- Indiana University – Purdue University Indianapolis (US)
Publication Details
- Journal
- Skeletal Radiology
- Published
- 2026-03-04
- DOI
- https://doi.org/10.1007/s00256-026-05178-3
- Primary Topic
- Sarcoma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00