A Tumor Volume Segmentation Algorithm Based on Radiomics Features in FDG-PET in Lung Cancer Patients, Validated Using Surgical Specimens
We found that, for small lesions, results obtained using conventional threshold-based segmentation compared well with pathological volumes. For lesions larger than 3 ccm, the novel algorithm based on Local Entropy performed best. These findings confirm the results of our previous phantom studies. This algorithm is therefore worthy of inclusion in future studies for further confirmation and application.
Authors
- Ralph A. Bundschuh (ORCID: https://orcid.org/0000-0001-7291-9372)
- Glen Kristiansen (ORCID: https://orcid.org/0000-0003-4149-5487)
- Markus Essler (ORCID: https://orcid.org/0009-0009-1884-1944)
- V. Prokić
- J Buermann
- Marieta Toma (ORCID: https://orcid.org/0000-0002-4803-3712)
- Lena Bundschuh
- Joachim Schmidt (ORCID: https://orcid.org/0009-0000-3159-652X)
Institutions
- Koblenz University of Applied Sciences (DE)
- University Hospital Bonn (DE)
- University Hospital Augsburg (DE)
- Klinik und Poliklinik für Nuklearmedizin (DE)
Publication Details
- Journal
- Diagnostics
- Published
- 2024-11-25
- DOI
- https://doi.org/10.3390/diagnostics14232654
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00