A comparative study between deep learning and radiomics models in grading liver tumors using hepatobiliary phase contrast-enhanced MR images

Purpose

To compare a deep learning model with a radiomics model in differentiating high-grade (LR-3, LR-4, LR-5) liver imaging reporting and data system (LI-RADS) liver tumors from low-grade (LR-1, LR-2) LI-RADS tumors based on the contrast-enhanced magnetic resonance images.

Methods

Magnetic resonance imaging scans of 361 suspected hepatocellular carcinoma patients were retrospectively reviewed. Lesion volume segmentation was manually performed by two radiologists, resulting in 426 lesions from the training set and 83 lesions from the test set. The radiomics model was constructed using a support vector machine (SVM) with pre-defined features, which was first selected using Chi-square test, followed by refining using binary least absolute shrinkage and selection operator (LASSO) regression. The deep learning model was established based on the DenseNet. Performance of the models was quantified by area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity and F1-score.

Results

A set of 8 most informative features was selected from 1049 features to train the SVM classifier. The AUCs of the radiomics model were 0.857 (95% confidence interval [CI] 0.816–0.888) for the training set and 0.879 (95% CI 0.779–0.935) for the test set. The deep learning method achieved AUCs of 0.838 (95% CI 0.799–0.871) for the training set and 0.717 (95% CI 0.601–0.814) for the test set. The performance difference between these two models was assessed by t-test, which showed the results in both training and test sets were statistically significant.

Conclusion

The deep learning based model can be trained end-to-end with little extra domain knowledge, while the radiomics model requires complex feature selection. However, this process makes the radiomics model achieve better performance in this study with smaller computational cost and more potential on model interpretability.

A Multimodality-Contribution-Aware TripNet for Histologic Grading of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is a type of primary liver malignant tumor with a high recurrence rate and poor prognosis even undergoing resection or transplantation. Accurate discrimination of the histologic grades of HCC plays a critical role in the management and therapy of HCC patients. In this paper, we discuss a deep learning-based diagnostic model for HCC histologic grading with multimodal Magnetic Resonance Imaging (MRI) images to overcome the problem of limited well-annotated data and extract the discriminated fusion feature referring to the clinical diagnosis experience of radiologists. Accordingly, we propose a novel Multimodality-Contribution-Aware TripNet (MCAT) based on the metric learning and the attention-aware weighted multimodal fusion. The novelty of the method lies in the multimodality small-shot learning architecture designation and the multimodality adaptive weighted computing scheme. The comprehensive experiments are done on the clinic dataset with the well-annotation of lesion location by the professional radiologist. The experimental results show that our proposed MCAT is not only able to achieve acceptable quantitative measuring of HCC histologic grading based on the MRI sequences with small cases but also outperforms previous models in HCC histologic grading, reaching an accuracy of 84 percent, a sensitivity of 87 percent and precision of 89 percent.

Grading of hepatocellular carcinoma using 3D SE-DenseNet in dynamic enhanced MR images

BACKGROUND

Clinical histological grading of hepatocellular carcinoma (HCC) differentiation is of great significance in clinical diagnoses, treatments, and prognoses. However, it is challenging for radiologists to evaluate HCC gradings from medical images.

PURPOSE

In this study, a novel deep neural network was developed by combining the squeeze-and-excitation networks (SENets) in a three-dimensional (3D) densely connected convolutional network (DenseNet), which is referred to as a 3D SE-DenseNet, for the classification of HCC grading using enhanced clinical magnetic resonance (MR) images obtained from two different clinical centers.

METHOD

In the proposed architecture, the SENet was added as an additional layer between the dense blocks of the 3D DenseNet, to mitigate the impact of feature redundancy. For the HCC grading task, the 3D SE-DenseNet was trained after data augmentation, and it outperformed the 3D DenseNet based on the clinical dataset.

RESULTS

The quantitative evaluations of the 3D SE-DenseNet on a two-class HCC grading task were conducted based on the dataset, which included 213 samples of the dynamic enhanced MR images. The proposed 3D SE-DenseNet demonstrated an accuracy of 83%, when compared with the 72% accuracy of the 3D DenseNet.

CONCLUSION

Owing to the advantage of useful automatic feature learning by the SE layer, the 3D SE-DenseNet can simultaneously handle useful feature enhancement and superfluous feature suppression. The quantitative experiments confirm the excellent performance of the 3D SE-DenseNet in the evaluation of the HCC grading.