Magnetic Resonance Image Radiomic Reproducibility: The Impact of Preprocessing on Extracted Features from Gross and High-Risk Clinical Tumor Volumes in Cervical Cancer Patients before Brachytherapy
The results presented here showed that MRI radiomic features are vulnerable to changes in preprocessing, and this issue must be understood and applied before any clinical decision-making. Features with ICC > 0.90 were considered the most reproducible features. Shape and first-order radiomic features were the most reproducible features in both GTV and HR-CTV. Our results also showed that GTV and HR-CTV radiomic features had similar changes against preprocessing sets.
Authors
- Seied Rabi Mahdavi (ORCID: https://orcid.org/0000-0003-1973-2140)
- Mohammad Javad Tahmasebi Birgani (ORCID: https://orcid.org/0000-0002-8748-3505)
- Younes Qasempour (ORCID: https://orcid.org/0000-0002-5519-2383)
- Fatemeh Mohammadian
- Khadijeh Hosseini
- Maryam Hazbavi (ORCID: https://orcid.org/0000-0002-8195-7925)
- Neda Abdalvand (ORCID: https://orcid.org/0000-0002-5163-1246)
- Hamid Abdollahi (ORCID: https://orcid.org/0000-0003-0761-1309)
- Mahdi Sadeghi
Institutions
- Ahvaz Jundishapur University of Medical Sciences (IR)
- Iran University of Medical Sciences (IR)
- Kerman University of Medical Sciences (IR)
Publication Details
- Journal
- Journal of Medical Signals & Sensors
- Published
- 2024-08-01
- DOI
- https://doi.org/10.4103/jmss.jmss_57_22
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.21
Funders
- Iran University of Medical Sciences