Liver segmentation in MRI: A fully automatic method based on stochastic partitions

Abstract

There are few fully automated methods for liver segmentation in magnetic resonance images (MRI) despite the benefits of this type of acquisition in comparison to other radiology techniques such as computed tomography (CT). Motivated by medical requirements, liver segmentation in MRI has been carried out. For this purpose, we present a new method for liver segmentation based on the watershed transform and stochastic partitions. The classical watershed over-segmentation is reduced using a marker-controlled algorithm. To improve accuracy of selected contours, the gradient of the original image is successfully enhanced by applying a new variant of stochastic watershed. Moreover, a final classifier is performed in order to obtain the final liver mask. Optimal parameters of the method are tuned using a training dataset and then they are applied to the rest of studies (17 datasets). The obtained results (a Jaccard coefficient of .91 ± .02) in comparison to other methods demonstrate that the new variant of stochastic watershed is a robust tool for automatic segmentation of the liver in MRI.

Automatic 3D model-based method for liver segmentation in MRI based on active contours and total variation minimization

“…Fully automatic methods that use all or some of these metrics are recent works by Huynh et al [17], Oh et al [29], Masoumi [12], López-Mir et al [14] and Gloger et al [15]. The metrics obtained by these methods in comparison to ours are gathered in Table 2.…”

“…In comparison to the others we find they are slower. López-Mir [14] uses 16 datasets ranging from 76 to 104 slices of 512 × 512 size. His proposed method needs from 7 to 11 min for extracting the liver volume.…”

“…To minimize the energy it is necessary to iterate (13) and (14). The values c 1 and c 2 are updated every N defined iterations.…”

“…Features are extracted from these regions to feed the neural network architecture. Recently, watershed techniques have also been proposed in combination with stochastic partitions to enhance the gradient of the original MRI image and it has been validated as a robust method in [14].…”

Automatic Liver Segmentation from Abdominal MRI Images using Active Contours

“…They first applied multi-class linear discriminant analysis as a fast and efficient dimensionality reduction technique and then generated probability maps to be further used for liver segmentation. F. Lopez-Mir et.al in [24] presented a new method for liver segmentation based on the watershed transform and stochastic partitions. They initially selected the first slice to localize the liver and then applied the segmentation algorithm.…”