GANsfer Learning: Combining labelled and unlabelled data for GAN based data augmentation

11/26/2018
by   Christopher Bowles, et al.
0

Medical imaging is a domain which suffers from a paucity of manually annotated data for the training of learning algorithms. Manually delineating pathological regions at a pixel level is a time consuming process, especially in 3D images, and often requires the time of a trained expert. As a result, supervised machine learning solutions must make do with small amounts of labelled data, despite there often being additional unlabelled data available. Whilst of less value than labelled images, these unlabelled images can contain potentially useful information. In this paper we propose combining both labelled and unlabelled data within a GAN framework, before using the resulting network to produce images for use when training a segmentation network. We explore the task of deep grey matter multi-class segmentation in an AD dataset and show that the proposed method leads to a significant improvement in segmentation results, particularly in cases where the amount of labelled data is restricted. We show that this improvement is largely driven by a greater ability to segment the structures known to be the most affected by AD, thereby demonstrating the benefits of exposing the system to more examples of pathological anatomical variation. We also show how a shift in domain of the training data from young and healthy towards older and more pathological examples leads to better segmentations of the latter cases, and that this leads to a significant improvement in the ability for the computed segmentations to stratify cases of AD.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 8

research
10/25/2018

GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

One of the biggest issues facing the use of machine learning in medical ...
research
10/22/2021

Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations

Semantic segmentation based on deep learning methods can attain appealin...
research
03/19/2018

Factorised spatial representation learning: application in semi-supervised myocardial segmentation

The success and generalisation of deep learning algorithms heavily depen...
research
05/11/2022

RustSEG – Automated segmentation of corrosion using deep learning

The inspection of infrastructure for corrosion remains a task that is ty...
research
02/11/2019

Semi-Supervised and Task-Driven Data Augmentation

Supervised deep learning methods for segmentation require large amounts ...
research
04/22/2020

Red-GAN: Attacking class imbalance via conditioned generation. Yet another medical imaging perspective

Exploiting learning algorithms under scarce data regimes is a limitation...
research
01/07/2023

Multiclass Semantic Segmentation to Identify Anatomical Sub-Regions of Brain and Measure Neuronal Health in Parkinson's Disease

Automated segmentation of anatomical sub-regions with high precision has...

Please sign up or login with your details

Forgot password? Click here to reset