Impact of deep learning based reconstruction algorithms on CT radiomic features of carotid plaques
Both ASIR-V and DLIR algorithms profoundly impact carotid plaque radiomics, with higher strengths exacerbating feature instability. Texture features exhibited superior robustness across all reconstruction protocols. Our findings advocate for a stability-driven approach to model development: prioritizing robust texture features and employing lower-strength DLIR are crucial steps to ensure the generalizability of radiomic biomarkers.
Authors
- Aiyun Sun
- Jingkai Xu (ORCID: https://orcid.org/0000-0002-3640-1602)
- Chengeng Ye
- Haibo Wang (ORCID: https://orcid.org/0000-0003-4809-4897)
- Jinjin Liu (ORCID: https://orcid.org/0000-0002-3838-6012)
- Xiangwu Zheng (ORCID: https://orcid.org/0000-0001-7512-6036)
- Guoquan Cao (ORCID: https://orcid.org/0000-0001-9450-2690)
- Shuyang Wang (ORCID: https://orcid.org/0009-0000-6082-0332)
Institutions
- Wenzhou Medical University (CN)
- First Affiliated Hospital of Wenzhou Medical University (CN)
- United Imaging Healthcare (China) (CN)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2025-11-01
- DOI
- https://doi.org/10.1002/acm2.70346
- Primary Topic
- Cerebrovascular and Carotid Artery Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Zhejiang Province