Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation

Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.

[1]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[2]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[3]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[4]  Pham The Bao,et al.  Fully automated MR liver volumetry using watershed segmentation coupled with active contouring , 2016, International Journal of Computer Assisted Radiology and Surgery.

[5]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[7]  Thierry Cresson,et al.  Liver Segmentation on CT and MR Using Laplacian Mesh Optimization , 2017, IEEE Transactions on Biomedical Engineering.

[8]  J P W Pluim,et al.  Evaluation of motion correction for clinical dynamic contrast enhanced MRI of the liver. , 2017, Physics in medicine and biology.

[9]  Alireza Behrad,et al.  Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network , 2012, Biomed. Signal Process. Control..

[10]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[11]  Mariano Alcañiz Raya,et al.  Liver segmentation in MRI: A fully automatic method based on stochastic partitions , 2014, Comput. Methods Programs Biomed..