Investig Magn Reson Imaging.  2021 Jun;25(2):118-128. 10.13104/imri.2021.25.2.118.

Benign versus Malignant Soft-Tissue Tumors: Differentiation with 3T Magnetic Resonance Image Textural Analysis Including Diffusion-Weighted Imaging

• Lee Y
• Jee WH
• Whang YS
• Jung CK
• Chung YG
• Lee SY

• KMID: 2517247
• DOI: http://doi.org/10.13104/imri.2021.25.2.118

Abstract

Purpose
To investigate the value of MR textural analysis, including use of diffusionweighted imaging (DWI) to differentiate malignant from benign soft-tissue tumors on 3T MRI.
Materials and Methods
We enrolled 69 patients (25 men, 44 women, ages 18 to 84 years) with pathologically confirmed soft-tissue tumors (29 benign, 40 malignant) who underwent pre-treatment 3T-MRI. We calculated MR texture, including mean, standard deviation (SD), skewness, kurtosis, mean of positive pixels (MPP), and entropy, according to different spatial-scale factors (SSF, 0, 2, 4, 6) on axial T1-and T2-weighted images (T1WI, T2WI), contrast-enhanced T1WI (CE-T1WI), high b-value DWI (800 sec/mm² ), and apparent diffusion coefficient (ADC) map. We used the Mann-Whitney U test, logistic regression, and area under the receiver operating characteristic curve (AUC) for statistical analysis.
Results
Malignant soft-tissue tumors had significantly lower mean values of DWI, ADC, T2WI and CE-T1WI, MPP of ADC, and CE-T1WI, but significantly higher kurtosis of DWI, T1WI, and CE-T1WI, and entropy of DWI, ADC, and T2WI than did benign tumors (P < 0.050). In multivariate logistic regression, the mean ADC value (SSF, 6) and kurtosis of CE-T1WI (SSF, 4) were independently associated with malignancy (P ≤ 0.009). A multivariate model of MR features worked well for diagnosis of malignant soft-tissue tumors (AUC, 0.909).
Conclusion
Accurate diagnosis could be obtained using MR textural analysis with DWI and CE-T1WI in differentiating benign from malignant soft-tissue tumors.

Keyword

Magnetic resonance imaging; Diffusion; Texture analysis; Sarcoma; Neoplasm