3D MRI brain tumor segmentation using autoencoder regularization

  title={3D MRI brain tumor segmentation using autoencoder regularization},
  author={Andriy Myronenko},
  • A. Myronenko
  • Published in BrainLes@MICCAI 16 September 2018
  • Computer Science
Automated segmentation of brain tumors from 3D magnetic resonance images (MRIs) is necessary for the diagnosis, monitoring, and treatment planning of the disease. [] Key Method Due to a limited training dataset size, a variational auto-encoder branch is added to reconstruct the input image itself in order to regularize the shared decoder and impose additional constraints on its layers. The current approach won 1st place in the BraTS 2018 challenge.

Robust Semantic Segmentation of Brain Tumor Regions from 3D MRIs

This work explores best practices of 3D semantic segmentation, including conventional encoder-decoder architecture, as well combined loss functions, in attempt to further improve the segmentation accuracy in Multimodal brain tumor segmentation challenge.

Automatic Brain Tumor Segmentation Using 3D Architecture Based on ROI Extraction

An automatic brain tumor segmentation method based on the U-Net architecture, which is composed of ROI (region of interest) extraction and 3D segmentation networks with long and short skip connections, is presented.

Brain Tumor Segmentation using 3D-CNNs with Uncertainty Estimation

This work proposes a 3D encoder-decoder architecture, based on V-Net, which is trained with patching techniques to reduce memory consumption and decrease the effect of unbalanced data.

Brain Tumor Segmentation based on Knowledge Distillation and Adversarial Training

A 3D MRI brain tumor segmentation architecture based on the encoder-decoder structure is proposed, which introduces knowledge distillation and adversarial training methods, which compresses and improves the accuracy and robustness of the model.

Brain Tumor Segmentation Using 3D Convolutional Neural Network

This paper proposes an additional path to enhance the encoder part and two separate up-sampling paths for the decoder part of the model and the analysis of 3D medical images.

Multi-modal brain tumor segmentation utilizing convolutional neural networks

This work proposed a novel adaptation of the Tversky index loss formula to avoid label imbalance and proposes multiple architectures, training phases and evaluation metrics in order to facilitate reliable and automatic delineation of tumorous tissues.

Multi-Decoder Networks with Multi-Denoising Inputs for Tumor Segmentation

An end-to-end deep-learning-based segmentation method using a multi-decoder architecture by jointly learning three separate sub-problems using a partly shared encoder and applying smoothing methods to the input images to generate denoised versions as additional inputs to the network is developed.

MRI brain tumor segmentation and uncertainty estimation using 3D-UNet architectures

3D encoder-decoder architectures trained with patchbased techniques to reduce memory consumption and decrease the effect of unbalanced data are studied and voxel-wise uncertainty information is introduced, both epistemic and aleatoric using test-time dropout and data-augmentation respectively.

Glioma Subregions Segmentation with a Discriminative Adversarial Regularized 3D Unet

A new 3D Unet embedded with in a discriminative adversarial network form, designed for the segmentation of glioblastoma subregions including tumor core (TC), enhancing tumor (ET) and whole tumor (WT) from multiple Magnetic Resonance Imaging (MRI) sequences is proposed.

Adaptive Weighted Loss Makes Brain Tumors Segmentation More Accurate in 3D MRI Volume

This paper added the adaptive weighted loss to a 3D MRI brain tumor segmentation network using auto-encoder regularization (3D-AE), and performed extensive validation on the MICCAI Brain Tumor Segmentation Challenge 2018 dataset (BRATS 2018), showing better performance than the state-of-the-art in both dice score and precision.



Learning Contextual and Attentive Information for Brain Tumor Segmentation

This work designs multiple deep architectures of varied structures to learning contextual and attentive information, then ensemble the predictions of these models to obtain more robust segmentation results, and shows that the risk of overfitting in segmentation is reduced.

Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks

A cascade of fully convolutional neural networks is proposed to segment multi-modal Magnetic Resonance (MR) images with brain tumor into background and three hierarchical regions: whole tumor, tumor

Ensembles of Densely-Connected CNNs with Label-Uncertainty for Brain Tumor Segmentation

We introduce a new family of classifiers based on our previous DeepSCAN architecture, in which densely connected blocks of dilated convolutions are embedded in a shallow U-net-style structure of

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

The set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences are reported, finding that different algorithms worked best for different sub-regions, but that no single algorithm ranked in the top for all sub-Regions simultaneously.

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods to reduce the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database.

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features

This set of labels and features should enable direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as performance evaluation of computer-aided segmentation methods.