Abstract
Liver and liver tumor segmentation based on abdomen computed tomography (CT) images is an essential step in computer-assisted clinical interventions. However, liver and tumor segmentation remains the difficult issue in the medical image processing field, which is ascribed to the anatomical complexity of the liver and the poor demarcation between the liver and other nearby organs on the image. The existing 3D automatic liver and tumor segmentation algorithms based on full convolutional networks, such as V-net, have utilized the loss functions on the basis of integration (summing) over a segmented region (like Dice or cross-entropy). Unfortunately, the number of foreground and background voxels is usually highly imbalanced in liver and tumor segmentation tasks. This greatly varies the value of regional loss between various segmentation classes, and affects the training stability and effect. In the present study, an improved V-net algorithm was applied for 3D liver and tumor segmentation based on region and distance metrics. The distance metric-based loss function utilized a distance metric of the contour (or shape) space rather than the area. The model was jointly trained by the original regional loss and the three distance-based loss functions (including Boundary (BD) loss, Hausdorff (HD) loss, and Signed Distance Map (SDM) loss) to solve the problem of the highly unbalanced liver and tumor segmentation. Besides, the algorithm was tested in two databases LiTS 2017 (Technical University of Munich, Munich, Germany, 2017) and 3D-IRCADb (Research Institute against Digestive Cancer, Strasbourg Cedex, France, 2009), and the results proved the effectiveness of improvement.
Highlights
Liver together with related lesion automatic segmentation represents a vital link to obtain quantitative biomarkers for the support systems to accurately diagnose in the clinic and make decisions based on the computer [1]
We utilized the values of Dice Similarity Coefficient (DSC), the 95th percentile of the Hausdorff Distance (HD) metrics (HD95), the average symmetric surface distance (ASD), together with the True Negative Rate (TNR, specificity) and True Positive Rate (TPR, sensitivity) as the evaluation indicators
The HD95 was defined as the 95th percentile of the Hausdorff distance between the predicted delineation and the ground truth annotation, which was a common indicator in image segmentation tasks
Summary
Liver together with related lesion automatic segmentation represents a vital link to obtain quantitative biomarkers for the support systems to accurately diagnose in the clinic and make decisions based on the computer [1]. Liver segmentation remains a challenge in the medical image processing field, which is due to the anatomical complexity of the liver and the poor demarcation between the liver and other neighboring organs [2]. Accurate measurements based on the computed tomography (CT) image, such as location, shape, and the volume of the tumor, together with the functional liver volume, helps physicians evaluate hepatocellular carcinoma (HCC) and plan treatment [3]. Two grand challenges benchmarks were carried out with the coordination of the MICCAI (Medical Image Computing and Computer-Assisted Intervention Society) conference to segment the liver and related lesions in 2007 and 2008, respectively [4,5]. Several approaches based on artificial design features were proposed for liver and related lesion segmentation base on CT images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
