Toward reliable automatic liver and tumor segmentation using convolutional neural network based on 2.5D models

Purpose We investigated the parameter configuration in the automatic liver and tumor segmentation using a convolutional neural network based on 2.5D model. The implementation of 2.5D model shows promising results since it allows the network to have a deeper and wider network architecture while still accommodates the 3D information. However, there has been no detailed investigation of the parameter configurations on this type of network model. Methods Some parameters, such as the number of stacked layers, image contrast, and the number of network layers, were studied and implemented on neural networks based on 2.5D model. Networks are trained and tested by utilizing the dataset from liver and tumor segmentation challenge (LiTS). The network performance was further evaluated by comparing the network segmentation with manual segmentation from nine technical physicians and an experienced radiologist. Results Slice arrangement testing shows that multiple stacked layers have better performance than a single-layer network. However, the dice scores start decreasing when the number of stacked layers is more than three layers. Adding higher number of layers would cause overfitting on the training set. In contrast enhancement test, implementing contrast enhancement method did not show a statistically significant different to the network performance. While in the network layer test, adding more layers to the network architecture does not always correspond to the increasing dice score result of the network. Conclusions This paper compares the performance of the network based on 2.5D model using different parameter configurations. The result obtained shows the effect of each parameter and allow the selection of the best configuration in order to improve the network performance in the application of automatic liver and tumor segmentation.

[1]  Alan D. Lopez,et al.  The Burden of Primary Liver Cancer and Underlying Etiologies From 1990 to 2015 at the Global, Regional, and National Level , 2017, JAMA oncology.

[2]  Francisco Herrera,et al.  An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics , 2013, Inf. Sci..

[3]  Bjoern H. Menze,et al.  Automated Unsupervised Segmentation of Liver Lesions in CT scans via Cahn-Hilliard Phase Separation , 2017, ArXiv.

[4]  Samuel Kadoury,et al.  Liver segmentation: indications, techniques and future directions , 2017, Insights into Imaging.

[5]  M. Desco,et al.  3D liver segmentation in preoperative CT images using a levelsets active surface method , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Akinobu Shimizu,et al.  Automatic Liver Segmentation Method based on Maximum A Posterior Probability Estimation and Level Set Method , 2007 .

[8]  J. Furst,et al.  A Hybrid Approach for Liver Segmentation , 2007 .

[9]  Thomas Lange,et al.  Shape Constrained Automatic Segmentation of the Liver based on a Heuristic Intensity Model , 2007 .

[10]  Geraint Rees,et al.  Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy , 2018, ArXiv.

[11]  Xiao Han,et al.  Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method , 2017, ArXiv.

[12]  Fernando Bello,et al.  A Discussion on the Evaluation of A New Automatic Liver Volume Segmentation Method for Specified CT Image Datasets , 2007 .

[13]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[14]  L. Ruskó,et al.  Fully automatic liver segmentation for contrast-enhanced CT images , 2007 .

[15]  David Dagan Feng,et al.  Automatic Liver Lesion Detection using Cascaded Deep Residual Networks , 2017, ArXiv.

[16]  Paul Suetens,et al.  Landmark based liver segmentation using local shape and local intensity models , 2007 .

[17]  Hans Meine,et al.  Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing , 2018, Scientific Reports.

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

[19]  Hans-Peter Meinzer,et al.  A Statistical Deformable Model for the Segmentation of Liver CT Volumes , 2007 .

[20]  Hao Chen,et al.  The Liver Tumor Segmentation Benchmark (LiTS) , 2019, Medical Image Anal..

[21]  Jun Fu,et al.  Densely connected deconvolutional network for semantic segmentation , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).