Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning (2018-10-29T00:00:00.000000Z)

TL;DR

This work proposes a novel method based on Generative Adversarial Networks (GANs) to train a segmentation model with both labeled and unlabeled images, which prevents over-fitting by learning to discriminate between true and fake patches obtained by a generator network.

Abstract

We address the problem of segmenting 3D multi-modal medical images in scenarios where very few labeled examples are available for training. Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a novel method based on Generative Adversarial Networks (GANs) to train a segmentation model with both labeled and unlabeled images. The proposed method prevents over-fitting by learning to discriminate between true and fake patches obtained by a generator network. Our work extends current adversarial learning approaches, which focus on 2D single-modality images, to the more challenging context of 3D volumes of multiple modalities. The proposed method is evaluated on the problem of segmenting brain MRI from the iSEG-2017 and MRBrainS 2013 datasets. Significant performance improvement is reported, compared to state-of-art segmentation networks trained in a fully-supervised manner. In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches. Our code is publicly available at this https URL

Authors

Christian Desrosiers

6 papers

J. Dolz

14 papers

Arnab Kumar Mondal

1 papers

TL;DR

Abstract

Authors

References40 items

A Robust Deep Attention Network to Noisy Labels in Semi-supervised Biomedical Segmentation

Few-Shot Segmentation Propagation with Guided Networks

Constrained‐CNN losses for weakly supervised segmentation☆

Adversarial Learning for Semi-supervised Semantic Segmentation

Meta-Learning for Semi-Supervised Few-Shot Classification

Conditional Networks for Few-Shot Semantic Segmentation

Data Distillation: Towards Omni-Supervised Learning

Semi Supervised Semantic Segmentation Using Generative Adversarial Network

Brain Tumor Segmentation Using an Adversarial Network

Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images

One-Shot Learning for Semantic Segmentation

Conditional Adversarial Network for Semantic Segmentation of Brain Tumor

Good Semi-supervised Learning That Requires a Bad GAN

Semi-supervised Deep Learning for Fully Convolutional Networks

A survey on deep learning in medical image analysis

Calibrating Energy-based Generative Adversarial Networks

3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

Semantic Segmentation using Adversarial Networks

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

Matching Networks for One Shot Learning

Improved Techniques for Training GANs

DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

Deep Residual Learning for Image Recognition

Cross Modal Distillation for Supervision Transfer

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

Weakly Supervised Semantic Segmentation with Convolutional Networks

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

One-shot learning of object categories

Semi-supervised multi-organ segmentation via multi-planar co-training

GENERATIVE ADVERSARIAL NETS

An Overview of Current Evaluation Methods Used in Medical Image Segmentation

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names