Published on Wed Apr 29 2020

An Auto-Encoder Strategy for Adaptive Image Segmentation

Evan M. Yu, Juan Eugenio Iglesias, Adrian V. Dalca, Mert R. Sabuncu

Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and voxel-level labels. We present a variational autoencoder that is flexible and adaptive.

0
0
0
Abstract

Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of anatomical regions on a large number of cases can be prohibitively expensive. Thus there is a strong need for deep learning-based segmentation tools that do not require heavy supervision and can continuously adapt. In this paper, we propose a novel perspective of segmentation as a discrete representation learning problem, and present a variational autoencoder segmentation strategy that is flexible and adaptive. Our method, called Segmentation Auto-Encoder (SAE), leverages all available unlabeled scans and merely requires a segmentation prior, which can be a single unpaired segmentation image. In experiments, we apply SAE to brain MRI scans. Our results show that SAE can produce good quality segmentations, particularly when the prior is good. We demonstrate that a Markov Random Field prior can yield significantly better results than a spatially independent prior. Our code is freely available at https://github.com/evanmy/sae.

Tue Aug 13 2019
Computer Vision
Few Labeled Atlases are Necessary for Deep-Learning-Based Segmentation
biomedical image segmentation in the scenario of only a few labeled MR images. Current multi-atlas based segmentation methods use image registration to warp segments onto a new scan.
0
0
0
Wed Feb 03 2021
Computer Vision
Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation
Existing image segmentation networks mainly leverage large-scale labeled datasets to attain high accuracy. labeling medical images is very expensive since it requires sophisticated expert knowledge. We propose to learn the probability distributions of deformations of different unlabeled MRI images with respect to the atlas.
0
0
0
Thu Apr 25 2019
Computer Vision
Unsupervised Deep Learning for Bayesian Brain MRI Segmentation
Probabilistic atlas priors have been commonly used to derive adaptive androbust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive.
0
0
0
Thu Mar 07 2019
Computer Vision
Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
We consider the problem of segmenting a biomedical image into anatomicalregions of interest. We employ unpaired segmentation images to build an anatomical prior. Critically these segmentations can be derived from imaging data from a different dataset and imaging modality.
0
0
0
Mon Feb 25 2019
Computer Vision
Data augmentation using learned transformations for one-shot medical image segmentation
Image segmentation is an important task in many medical applications. Methods based on convolutional neural networks attain state-of-the-art accuracy. Labeling medical images requires significant expertise and time. We present an automated data augmentation method.
0
0
0
Wed Mar 04 2020
Computer Vision
A Learning Strategy for Contrast-agnostic MRI Segmentation
SynthSeg leverages a set of training segmentations to generate synthetic sample images of widely varying contrasts on the fly during training. These samples are produced using the generative model of the classical Bayesian segmentation framework.
1
0
1