A Generic, Robust and Fully-Automatic Workflow for 3D CT Liver Segmentation

Abstract

Liver segmentation in 3D CT images is a fundamental step for surgery planning and follow-up. Robustness, automation and speed are required to fulfill this task efficiently. We propose a fully-automatic workflow for liver segmentation built on state-of-the-art algorithmic components to meet these requirements. The liver is first localized using regression forests. A liver probability map is computed, followed by a global-to-local segmentation strategy using a template deformation framework. We evaluate our method on the SLIVER07 reference database and confirm its state-of-the-art results on a large, varied database of 268 CT volumes. This extensive validation demonstrates the robustness of our approach to variable fields of view, liver contrast, shape and pathologies. Our framework is an attractive tradeoff between robustness, accuracy (mean distance to ground truth of 1.7mm) and computational speed (46s). We also emphasize the genericity and relative simplicity of our framework, which requires very limited liver-specific tuning.

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

“…Briefly, automatic liver segmentation was performed by using an anatomic liver model derived from an independent dataset of 50 T1-weighted contrast-enhanced abdominal MR images. Probability maps of the liver’s location were determined by the random forest algorithm and weighted by organ atlases (26–29). The liver model then underwent implicit template deformation with a classic principal components analysis.…”

“…The control point editing was based on non-Euclidean geometry and the theory of radial functions (30), and the liver contour editing relied on voxel signal intensities and an edge-detection algorithm (31). The theories underlying the prototype software (eg, regression forests for organ localization, computed organ probability maps, and implicit template deformation for segmentation) have been previously validated in multiple large imaging databases of diverse organs (26–29). …”

Feature Learning Based Random Walk for Liver Segmentation

“…The methods of Heimann [39], Saddi [40], van Rikxoort [41], and Gauriau [42] were performed using the MICCAI 2007 grand challenge database as the proposed FLRW and evaluated with same criteria. Comparative results show that the proposed FLRW was superior to three methods in the total score, and same as or better than the fourth method in ASD and RMSE.…”

Multi-organ localization with cascaded global-to-local regression and shape prior

“…First, it directly enables faster data navigation and visualization of target structures which can undoubtedly save the radiologist some time (Andriole et al, 2011). Second, organ localization is a key initialization step for tasks such as segmentation or registration (for the liver segmentation for example (Gauriau et al, 2013)). It is, overall, a crucial component to streamline complex workflows such as medical treatment planning and follow-up (in liver radiotherapy for instance, the volume of the liver is required to compute the dose (Murthy et al, 2005)).…”