Decision Forests for Tissue-Specific Segmentation of High-Grade Gliomas in Multi-channel MR

By Darko Zikic, Ben Glocker, Ender Konukoglu, Antonio Criminisi, Çağatay Demiralp, Jamie Shotton, Owen M. Thomas, Tilak Das, R. Jena, Stephen J. Price. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2012

304 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/eade72229c1b20d1572b1167c9f297efa5ac8df5

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

In Neurology

Citations in the corpus

A survey of MRI-based medical image analysis for brain tumor studies (2013, unknown): “Example from Zikic et al. (2012).”
Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods (2016, methodology): “Conditional random fields (CRF) 23, 24 and connected components (CC) 27, 29 are among the popular choices.”
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation (2017, background): “The past few years saw rapid developments of machine learning methods, with Random Forests being among the most successful [9,10].”
Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks (2017, background): “Representative works include classification based on support vector machines [19] and decision trees [32].”
A survey of MRI-based brain tumor segmentation methods (2014, methodology): “In parametric deformable models, the important [106] SVM + Kernel feature selection Good results tested in T1w, T2w and T1c, low computation time [107] step of brain tumor segmentation is to ﬁnd the boundary of brain tumors.”
DeepMedic for Brain Tumor Segmentation (2016, methodology): “The state of the art was raised further by supervised learning methods, initially represented mainly by Random Forests, coupled with models such as Gaussian Mixtures for the extraction of tissue type priors [6], MRFs for spatial regularisation and a variety of engineered features [7].”
Fully Automatic Brain Tumor Segmentation using End-To-End Incremental Deep Neural Networks in MRI images (2018, background): “However, Discriminative models ([10]) directly learn the characteristics of tumor and how to segment it from manually annotated data (created by radiologists).”
Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation (2016, methodology): “Zikic et al. (2012) combine this with a generative Gaussian Mixture Model (GMM) to obtain tissue-speciﬁc probabilistic priors (Van Leemput et al. (1999)).”
Deep learning based brain tumor segmentation: a survey (2020, result): “This learning exercise is beneficial to lesion segmentation and is also in line with the early research of using the combination of prior image information [122], [123].”
Brain tumor segmentation with Deep Neural Networks (2015, methodology): “Classical discriminative learning techniques such as SVMs [4, 41, 30] and decision forests [48] have also been used.”
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images (2016, background): “A variety of features were proposed in the literature: encoding context [15], [16], [21], ﬁrst-order and fractals-based texture [14], [15], [18], [21], [22], gradients [14], [15], brain symmetry [14], [15], [19], and physical properties [19].”
Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors and Machine-learning Approaches (2017, methodology): “Supervised Learning Supervised learning is a primary learning scheme that has been applied in recent radiomic studies.(16,23) Supervised learning is conceptually divided into 2 phases.”