Supervised Nonparametric Image Parcellation
ABSTRACT Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data
are summarized using a parametric atlas. Summarizing the data alleviates the computational burden at the expense of possibly
losing valuable information on inter-subject variability. This paper presents a novel framework for Supervised Nonparametric
Image Parcellation (SNIP). SNIP models the intensity and label images as samples of a joint distribution estimated from the
training data in a non-parametric fashion. By capitalizing on recently developed fast and robust pairwise image alignment
tools, SNIP employs the entire training data to segment a new image via Expectation Maximization. The use of multiple registrations increases robustness
to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with manual labels for the white
matter, cortex and subcortical structures. SNIP yields better segmentation than state-of-the-art algorithms in multiple regions
- SourceAvailable from: Juha Karhunen[Show abstract] [Hide abstract]
ABSTRACT: 51 52 Bayesian learning of latent variable models 2.1 Bayesian modeling and variational learning Unsupervised learning methods are often based on a generative approach where the goal is to find a latent variable model which explains how the observations were generated. It is assumed that there exist certain latent variables (also called in different contexts source signals, factors, or hidden variables) which have generated the observed data through an unknown mapping. The goal of generative learning is to identify both the latent variables and the unknown generative mapping. The success of a specific model depends on how well it captures the structure of the phenomena underlying the observations. Various linear models have been popular, because their mathematical treatment is fairly easy. However, in many realistic cases the observations have been generated by a nonlinear process. Unsupervised learning of a nonlinear model is a challenging task, because it is typically computationally much more demanding than for linear models, and flexible models require strong regularization for avoiding overfitting.
- [Show abstract] [Hide abstract]
ABSTRACT: We present a new non-parametric model constraint graph min-cut algorithm for automatic kidney segmentation in CT images. The segmentation is formulated as a maximum a-posteriori estimation of a model-driven Markov random field. A non-parametric hybrid shape and intensity model is treated as a latent variable in the energy functional. The latent model and labeling map that minimize the energy functional are then simultaneously computed with an expectation maximization approach. The main advantages of our method are that it does not assume a fixed parametric prior model, which is subjective to inter-patient variability and registration errors, and that it combines both the model and the image information into a unified graph min-cut based segmentation framework. We evaluated our method on 20 kidneys from 10 CT datasets with and without contrast agent for which ground-truth segmentations were generated by averaging three manual segmentations. Our method yields an average volumetric overlap error of 10.95%, and average symmetric surface distance of 0.79 mm. These results indicate that our method is accurate and robust for kidney segmentation.
- [Show abstract] [Hide abstract]
ABSTRACT: Learning-based approaches have become increasingly practical in medical imaging. For a supervised learning strategy, the quality of the trained algorithm (usually a classifier) is heavily dependent on the amount, as well as quality, of the available training data. It is often very time-consuming to obtain the ground truth manual delineations. In this paper, we propose a semi-supervised learning algorithm and show its application to skull stripping in brain MRI. The resulting method takes advantage of existing state-of-the-art systems, such as BET and FreeSurfer, to sample unlabeled data in an agreement-based framework. Using just two labeled and a set of unlabeled MRI scans, a voxel-based random forest classifier is trained to perform the skull stripping. Our system is practical, and it displays significant improvement over supervised approaches, BET and FreeSurfer in two datasets (60 test images).