A supervised patch-based approach for human brain labeling

By François Rousseau, Piotr A. Habas, Colin Studholme. IEEE Transactions on Medical Imaging, 2011

296 citations recorded by the source corpus.

We propose in this work a patch-based image labeling method relying on a label propagation framework. Based on image intensity similarities between the input image and an anatomy textbook, an original strategy which does not require any nonrigid registration is presented. Following recent developments in nonlocal image denoising, the similarity between images is represented by a weighted graph computed from an intensity-based distance between patches. Experiments on simulated and in vivo magnetic resonance images show that the proposed method is very successful in providing automated human brain labeling.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1cece25ec5598acf0da58810f877a4eae5fa76fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy (2017, methodology): “Previous results in patch-based segmentation have, however, demonstrated the advantage of propagating not only the center label but also neighboring labels (Rousseau et al., 2011).”
Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch (2013, methodology): “To take advantage of the information redundancy in similar patches across different subjects, patch-based methods have been shown to be highly efficient in applications such as segmentation [8,9].”
volBrain: An Online MRI Brain Volumetry System (2015, methodology): “To intrinsically provide some degree of label regularity we used a block-wise vote scheme similar to the one proposed by Coupé et al. (2008) for denoising and applied to segmentation in Rousseau et al. (2011).”
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) (2015, background): “In addition, it was observed that a good understanding of the image resolution and amount of image subsampling can lead to a good trade-off between speed improvements and segmentation quality.”
Multi-Atlas Segmentation of Biomedical Images: A Survey (2014, methodology): “his technique was introduced to biomedical MAS by Coupe et al. (2011) and recently has been gaining popularity (Asman and Landman, 2013; Bai et al., 2013; Fonov et al., 2012; Konukoglu et al., 2013; Rousseau et al., 2011; Wang et al., 2011, 2013b; Wolz et al., 2013; Wang et al., 2014e; Zhang et al.,”
A review on automatic fetal and neonatal brain MRI segmentation (2017, unknown): “The spatio-temporal probabilistic atlas of the neonatal brain constructed by Serag et al. (2012). A.”