Recent advancements in magnetic resonance imaging (MRI) are set to enhance the diagnostic precision for cervical cancer patients. A study published in the Journal of Applied Clinical Medical Physics explores how simultaneous multislice acceleration (SMS) and different tumor segmentation methods affect radiomics features derived from MRI parametric maps.
Study Methodology and Approach
The research involved 40 cervical cancer patients who underwent multi-b-value diffusion-weighted imaging (DWI) utilizing SMS with acceleration factors between 1 and 3. Radiomics features were extracted from various parametric maps, including the pure diffusion coefficient (D), pseudodiffusion coefficient (D*), perfusion fraction (f), mean diffusivity (MD), and mean kurtosis (MK). A total of 93 two-dimensional (2D) and 93 three-dimensional (3D) features were analyzed per map to assess their stability using the concordance correlation coefficient (CCC) and coefficients of variation (COV).
Key Findings and Implications
As SMS acceleration factors increased, feature stability declined, with only 9.1% of 2D and 12.7% of 3D radiomics features remaining stable (CCC > 0.9 and COV < 0.1). Among the parametric maps, ADC maps exhibited the highest stability, while D* and f maps were the least stable. Furthermore, 3D features demonstrated greater stability compared to 2D features.
Inferences include:
- Higher SMS acceleration reduces the reliability of radiomics features in MRI scans.
- Three-dimensional tumor segmentation offers more stable radiomics features than two-dimensional methods.
- ADC maps are preferable for extracting stable radiomics features in cervical cancer studies.
- Certain stable radiomics features can effectively discriminate between early and advanced cancer stages.
- An SMS acceleration factor of 2 provides an optimal balance for clinical radiomics research.
The study successfully identified 5 stable 2D and 25 stable 3D radiomics features capable of distinguishing between low and high-stage cervical cancer, achieving an area under the curve (AUC) between 0.66 and 0.83. These findings highlight the potential of tailored MRI protocols in improving the diagnostic and prognostic processes for cervical cancer patients.
Leveraging multi-b-value DWI with an SMS acceleration factor of 2 emerges as a recommended approach for clinical radiomics research. By optimizing imaging parameters, clinicians can enhance the stability and reliability of radiomics features, ultimately leading to more accurate staging and better-informed treatment strategies for individuals battling cervical cancer.
This article has been prepared with the assistance of AI and reviewed by an editor. For more details, please refer to our Terms and Conditions. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author.
