Predictors of Ablation Therapy Response in Moderately Differentiated HCC using Radiomics Features from Multi-phasic DCE-MRI
Motivation: Recurrence following thermal ablation for HCC underscores the need for quantitative imaging tools to optimize treatment and accurately assess response. Goal(s): This study aims to identify and evaluate radiomics features from multiphase MRI that can distinguish between responders and non-responders to thermal ablation therapy in moderately differentiated HCC. Approach: Retrospective analysis was conducted on 24 responders and 20 non-responders, with radiomics features extracted from multiphase MRI. Mann-Whitney U tests were used for statistical analysis to identify significant features. Results: Significant differences in radiomics features were identified in the hepatobiliary and pre-contrast phases. No significant differences were observed in the arterial or portal phases. Impact: This study identifies radiomics shape and texture-based features from multiphase MRI that differentiate responders from non-responders to thermal ablation in moderately differentiated HCC. These features offer insights into quantitative biomarkers, emphasizing the role of imaging in optimizing therapy.
Authors
- Abhinav Suri (ORCID: https://orcid.org/0000-0002-7900-8763)
- David Lu (ORCID: https://orcid.org/0000-0001-5618-5217)
- Jason Chiang (ORCID: https://orcid.org/0000-0003-2896-1930)
- Kyunghyun Sung (ORCID: https://orcid.org/0000-0003-4175-5322)
- Xinyi Li (ORCID: https://orcid.org/0000-0002-0221-0525)
- Qi Miao (ORCID: https://orcid.org/0000-0003-2235-8997)
- Pedram Keshavarz
- Zahra Mohammadigolda
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/4300
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00