Development and validation of a cross-modality tensor fusion model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion in hepatocellular carcinoma

Objectives

To develop and validate a cross-modality tensor fusion (CMTF) model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

Materials and methods

This study included 174 HCC patients (47 MVI-positive and 127 MVI-negative) confirmed by postoperative pathology. The synthetic minority over-sampling technique was used to augment MVI-positive samples. The amplified dataset of 254 samples (127 MVI-positive and 127 MVI-negative) was randomly divided into training and test cohorts in a 7:3 ratio. Radiomics features were respectively extracted from arterial phase, delayed phase, diffusion-weighted imaging, and fat-suppressed T2-weighted imaging. The least absolute shrinkage and selection operator was used for feature selection. Univariate and multivariate logistic regression analyses were employed to identify clinical and radiological independent predictors. The selected multi-modality MRI radiomics features, clinical and radiological characteristics were used to construct the CMTF model, single modality (SM) model, early fusion (EF) model.

Results

The CMTF model demonstrated superior performance in predicting MVI compared to the SM and EF models. When integrating four MRI modalities, the CMTF model achieved a high area under the curve (AUC) with 95 % confidence interval (95 % CI) of 0.894 (0.820–0.968). Additionally, incorporating clinical and radiological characteristics further enhanced the predictive performance of CMTF model, the AUC (95 % CI) value increased to 0.945 (0.892–0.998).

Conclusion

The CMTF model showed promising performance in preoperative MVI prediction, providing a more effective non-invasive detection tool for HCC patients.