Noninvasive evaluation of the pathologic grade of hepatocellular carcinoma using MCF-3DCNN: A pilot study
Da-wei Yang1,2, Xiao-pei Wang1, Zheng-han Yang1, Zhen-chang Wang1, and Xi-bin Jia3

1Beijing friendship hospital, Capital medical university, Beijing, China, 2Beijing Key Laboratory of Translational Medicine on Liver Cirrhosis, Beijing, China, 3Beijing University of Technology, Beijing, China


This pilot study indicated that the MCF-3DCNN model may be valuable for the noninvasive evaluation of the pathologic grade of HCCs; however, further improvement would be necessary to achieve a better diagnostic performance for moderately and poorly differentiated HCCs.


To evaluate the diagnostic performance of deep learning with a multichannel fusion three-dimensional convolutional neural network (MCF-3DCNN) in the differentiation of the pathologic grades of hepatocellular carcinoma (HCC) based on dynamic contrast-enhanced magnetic resonance images (DCE-MR images).

Methods and Materials

Fifty-one histologically proven HCCs from 42 consecutive patients from January 2015 to September 2017 were included in this retrospective study. Pathologic examinations revealed nine well-differentiated, 35 moderately differentiated, and seven poorly differentiated HCCs. DCE-MR images with five phases were collected using a 3.0 Tesla MR scanner. The 4D-tensor representation was employed to organize the collected data in one temporal and three spatial dimensions by referring to the phases and 3D scanning slices of the DCE-MR images. A deep learning diagnosis model with MCF-3DCNN was proposed, and the structure of MCF-3DCNN was determined to approximate clinical diagnosis experience by taking into account the significance of the spatial and temporal information from DCE-MR images. Then, MCF-3DCNN was trained based on well-labeled samples of HCC lesions from real patient cases by experienced radiologists. The accuracy when differentiating the pathologic grades of HCC was calculated, and the performance of MCF-3DCNN in lesion diagnosis was assessed. Additionally, the areas under the receiver operating characteristic curves (AUC) for distinguishing well-differentiated, moderately differentiated, and poorly differentiated HCCs were calculated.


The average accuracy of the gross differentiation of the pathologic grade of HCC via the MCF-3DCNN in the test data was 0.7396±0.0104, and the average sensitivity and precision were 0.7396±0.0104 and 0.8042±0.0198, respectively. MCF-3DCNN also achieved the highest diagnostic performance for discriminating well-differentiated HCCs from others, with an average AUC, accuracy, sensitivity and specificity of 0.96, 91.00%, 96.88%, and 89.62%, respectively.


This study indicates that MCF-3DCNN can be a promising technology for evaluating the pathologic grade of HCC based on DCE-MR images.


The authors would like to express our enormous appreciation and gratitude to all participants.


  1. Tang Y, Wang H, Ma L, et al. Diffusion-weighted imaging of hepatocellular carcinomas: a retrospective analysis of correlation between apparent diffusion coefficients and histological grade. Abdom Radiol 2016;41:1539-1545.
  2. Bruix J, Sherman M. Management of hepatocellular carcinoma. Hepatology 2005; 42:1208-1236.
  3. Kim DJ, Clark PJ, Heimbach J, et al. Recurrence of hepatocellular carcinoma: importance of mRECIST response to chemoembolization and tumor size. Am J Transplant 2014;14:1383-1390.
  4. Choi JW, Lee JM, Kim SJ, et al. Hepatocellular carcinoma: imaging patterns on gadoxetic acid-enhanced MR Images and their value as an imaging biomarker. Radiology 2013;267: 776-786.
  5. Castellano G, Bonilha L, Li LM, Cendes F. Texture analysis of medical images. Clin Radiol 2004;59:1061-1069.


Figure 1 Data representation with 4th-order tensor.

Figure 2 The architecture of the MCF-3D CNN.

Figure 3 The average area under the ROC curve for 3DCNN for discriminating well-differentiated HCCs from the others was 0.96.

Proc. Intl. Soc. Mag. Reson. Med. 27 (2019)