Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics

by   Matthias Perkonigg, et al.

Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial static training set, model performance and reliability suffer from changes of acquisition characteristics as data and targets may become inconsistent. Continual learning can help to adapt models to the changing environment by training on a continuous data stream. However, continual manual expert labelling of medical imaging requires substantial effort. Thus, ways to use labelling resources efficiently on a well chosen sub-set of new examples is necessary to render this strategy feasible. Here, we propose a method for continual active learning operating on a stream of medical images in a multi-scanner setting. The approach automatically recognizes shifts in image acquisition characteristics - new domains -, selects optimal examples for labelling and adapts training accordingly. Labelling is subject to a limited budget, resembling typical real world scenarios. To demonstrate generalizability, we evaluate the effectiveness of our method on three tasks: cardiac segmentation, lung nodule detection and brain age estimation. Results show that the proposed approach outperforms other active learning methods, while effectively counteracting catastrophic forgetting.


page 2

page 5

page 14

page 15

page 23


Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition

Imaging in clinical routine is subject to changing scanner protocols, ha...

Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation

Deep learning for medical imaging suffers from temporal and privacy-rela...

Few-Shot Continual Active Learning by a Robot

In this paper, we consider a challenging but realistic continual learnin...

What is Wrong with Continual Learning in Medical Image Segmentation?

Continual learning protocols are attracting increasing attention from th...

ALPS: Active Learning via Perturbations

Small, labelled datasets in the presence of larger, unlabelled datasets ...

Semantic Parsing in Limited Resource Conditions

This thesis explores challenges in semantic parsing, specifically focusi...

A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning

Current deep learning research is dominated by benchmark evaluation. A m...

Please sign up or login with your details

Forgot password? Click here to reset