Discriminative Parameter Estimation for Random Walks Segmentation: Technical Report
This work addresses the parameter tuning bottleneck for medical image segmentation, though it is incremental as it builds on the existing Random Walks method.
The paper tackled the problem of hand-tuning parameters in the Random Walks segmentation algorithm by proposing a discriminative learning framework that estimates parameters from training data, resulting in significant performance improvements on a dataset of 3D MRI volumes of skeletal muscles.
The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate segmentations of medical images in a fully automated manner. However, one of the main drawbacks of using the RW algorithm is that its parameters have to be hand-tuned. we propose a novel discriminative learning framework that estimates the parameters using a training dataset. The main challenge we face is that the training samples are not fully supervised. Speci cally, they provide a hard segmentation of the images, instead of a proba-bilistic segmentation. We overcome this challenge by treating the optimal probabilistic segmentation that is compatible with the given hard segmentation as a latent variable. This allows us to employ the latent support vector machine formulation for parameter estimation. We show that our approach signi cantly outperforms the baseline methods on a challenging dataset consisting of real clinical 3D MRI volumes of skeletal muscles.