What question did this study set out to answer?

The aim is to assess the predictive value of 2D MRI slices for microvascular invasion in hepatocellular carcinoma using a novel machine learning approach.

March 16, 2026BMC Medical Imaging0 citationsOpen Access

Are 2D MRI slices equally important in microvascular invasion prediction: a study based on multiple instance learning with attention

YLYingying Liu YDYafang Dou WYWenning Yuan

Key Points

The aim is to assess the predictive value of 2D MRI slices for microvascular invasion in hepatocellular carcinoma using a novel machine learning approach.
Retrospective analysis of 174 patients evaluated with MRI scans in different phases.
Utilization of a multiple instance learning method with an attention mechanism to determine slice importance.
Training of eighteen MRI phase-specific and six combined-phase models with evaluation metrics like AUC and F1 score.
The hybrid model achieved a test AUC of 0.80, indicating strong predictive ability for microvascular invasion.
The arterial phase model outperformed others with a test AUC of 0.78.
Top MRI slices showed a strong correlation with microvascular invasion, highlighting their potential clinical relevance.

Abstract

Microvascular invasion (MVI) is a critical prognostic indicator of hepatocellular carcinoma (HCC). Although MRI-based prediction of MVI has drawn great attention, many previous studies focused on either 3D volumetric regions of tumors or the slices of the largest tumors size in the axial plane. This study aimed to investigate the predictive value of 2D MRI slices on MVI, based on a multiple instance learning (MIL) method with an attention block to estimate the slice-wise importance. A total of 174 patients (training cohort: 121 patients; testing cohort: 53 patients) were evaluated in this retrospective study. MRI scans of arterial phase, venous phase and delayed phase, as well as sixteen clinical characteristics were collected. A transformer-based model was utilized to extract features from the original and dilated tumor regions (with 5 mm and 10 mm margins). A MIL based method was developed to predict MVI, with an attention block to estimate the slice-wise weights. Eighteen phase-specific and six combined-phase models were trained and tested. Three hybrid models were constructed from the best-performed models. Area under the curve (AUC), precision, accuracy, F1 were utilized to evaluate model performance. Centered kernel alignment (CKA) analysis was employed to assess the value of the learned weights of MRI slices by estimating their correlation with histopathological image. Arterial phase outperformed other phase-specific and combined-phase models on test AUC (two best models: 0.78, 95%CI: 0.63, 0.91; 0.78, 95%CI: 0.64, 0.90). The hybrid model using soft voting strategy achieved the highest test AUC (0.80, 95%CI: 0.69, 0.92) in this study. CKA analysis of one patient’s data showed that the top 5 MRI slices of the highest weights have stronger correlation with MVI than others (0.87 versus 0.75). The group of 2D MRI slices demonstrated predictive value for MVI prediction using a MIL method. The learned weights of MRI slices from the attention block indicate their potential relevance with MVI. These findings may help to identify the most relevant MRI slices for MVI prediction, which may be utilized in MVI diagnosis in future applications. Not applicable.

AIに質問

Bookmark

View Full Paper

Cite This Study

Liu et al. (Fri,) studied this question.

synapsesocial.com/papers/69b79dce8166e15b153ab0c1 https://doi.org/https://doi.org/10.1186/s12880-026-02282-7

AIに質問

Bookmark

View Full Paper