Impact of metadata in multimodal classification of bone tumours
The joint fusion approach developed in this study, integrating clinical metadata and imaging data, outperformed state-of-the-art models in classifying primary bone tumours. The use of SHAP values provided insights into the impact of different metadata on the model's performance, highlighting the significant role of age. This approach has potential implications for improving diagnostic accuracy and understanding the influence of clinical factors in tumour classification.
Authors
- Daniel Rueckert (ORCID: https://orcid.org/0000-0002-5683-5889)
- Sarah Consalvo (ORCID: https://orcid.org/0000-0001-7518-2177)
- Alexandra S. Gersing (ORCID: https://orcid.org/0000-0003-1687-5541)
- Jan Neumann (ORCID: https://orcid.org/0000-0003-4388-737X)
- Rüdiger von Eisenhart‐Rothe (ORCID: https://orcid.org/0000-0002-2352-1357)
- Michael Guenther (ORCID: https://orcid.org/0009-0001-5091-5060)
- Klaus Woertler (ORCID: https://orcid.org/0000-0002-0124-9735)
- Rainer Burgkart (ORCID: https://orcid.org/0000-0002-9107-4229)
- Florian Hinterwimmer (ORCID: https://orcid.org/0000-0002-0273-0643)
Institutions
- TUM Klinikum (DE)
- Imperial College London (GB)
- Technical University of Munich (DE)
Publication Details
- Journal
- BMC Musculoskeletal Disorders
- Published
- 2024-10-19
- DOI
- https://doi.org/10.1186/s12891-024-07934-9
- Citations
- 9
- Primary Topic
- Sarcoma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.77
Funders
- Technische Universität München